CMUSphinx & Dialog Systems 2018


Notes:

  • Agent
  • Agents
  • Assistant
  • Assistants
  • Bot
  • Bots
  • Chatbot
  • Chatbots

Resources:

Wikipedia:

See also:

100 Best CMUSphinx Videos | 100 Best VoiceXML Videos | PocketSphinx 2018


Next-generation of virtual personal assistants (Microsoft Cortana, Apple Siri, Amazon Alexa and Google Home)
V Ke?puska, G Bohouta – 2018 IEEE 8th Annual Computing …, 2018 – ieeexplore.ieee.org
… Facebook is training Facebook’s new virtual assistant for Messenger with supervised learning, a process … 3. The Structure of The Next-Generation of Virtual Personal Assistants … recognition systems such as Microsoft API, Google API, Amazon API and CMU Sphinx, all information …

Experimental Evaluation of a Novel Personal Assistant in Greek Language for Ambient Assisted Living Environments employing home robots
A Spournias, K Christopoulos… – 2018 South-Eastern …, 2018 – ieeexplore.ieee.org
… Thus, on the one hand, the CMU Sphinx platform will be used at the local … for Emerging Intelligent Web Services, http://lucida.ai/ [12] Sirius intelligent personal assistant (IPA), http … sl: OASIS, 2014 [26] CMUSphinx Open Source Speech Recognition, https://cmusphinx.github.io/ [27 …

Spoken dialog system in bodo language for agro services
A Deka, MK Deka – Advances in Electronics, Communication and …, 2018 – Springer
… A spoken dialog system is computer agent that interacts with people by understanding spoken language … In this work we design and develop a spoken dialog system for Bodo speaking people through … Sci Issues (IJCSI) (2012)Google Scholar. 5. http://cmusphinx.sourceforge.net …

Domain Specific Intelligent Personal Assistant with Bilingual Voice Command Processing
SS Chowdhury, A Talukdar, A Mahmud… – TENCON 2018-2018 …, 2018 – ieeexplore.ieee.org
… Some recommended improvements: by using a larger audio/speech corpus for training the CMU Sphinx, the success rate can be increased significantly … 1] J. Kurpansky, “What Is an Intelligent Digital Assistant?”, Medium, 2017 … [3] S. Springenberg, “Intelligent Personal Assistants …

Towards Reactive Acoustic Jamming for Personal Voice Assistants
P Cheng, IE Bagci, J Yan, U Roedig – Proceedings of the 2nd …, 2018 – dl.acm.org
… PocketSphinx [10] is the optimized version of CMU’s SPHINX (an open source LVCSR system) for resource limited embedded systems … 3 PERSONAL VOICE ASSISTANT JAMMING It is our aim to design a reactive jamming framework which can be used to … 4] CMUSphinx. 2006 …

Investigation and development of the intelligent voice assistant for the Internet of Things using machine learning
EV Polyakov, MS Mazhanov, AY Rolich… – … on Electronic and …, 2018 – ieeexplore.ieee.org
… Siri vs. Cortana vs. Google Assistant: A Comparison of Speech-Based Natural User Interfaces //International Conference on Applied Human Factors and Ergonomics. – Springer, Cham, 2017. – ? … IEEE, 2017. – ?. 1-8. [9] CMU Sphinx Toolkit: http://cmusphinx.sourceforge.net.

Personal Assistants in a Virtual Education Space
J Todorov, V Valkanov, S Stoyanov, B Daskalov… – Practical Issues of …, 2018 – Springer
… portal and in this way to ensure interaction with the personal assistant LISSA and the operative assistants of the … For voice recognition in offline mode, we use the CMU Sphinx library [44 … with DeLC 2.0, delivers data for the creation of a profile and desires of the personal assistant …

A Hybrid Semantic Analysis Approach Using Rule Based and Learning Techniques for Human-Robot Interaction in a Robotic Assistant
KIP Liyanage, GU Ganegoda… – … on Advances in ICT …, 2018 – ieeexplore.ieee.org
… However, if the technologies used by commercial virtual personal assistants such as Siri, Google Assistant … approach would be to use an editable speech recognizer such as CMUSphinx [19] that … The problem that exists during the initiation stage of the robotic assistant is the lack …

Implementation of Google Assistant on Rasberry Pi
S Mischie, L Mâ?iu-Iovan… – … on Electronics and …, 2018 – ieeexplore.ieee.org
… [2] V. Kepuska and G. Bohouta, “Next Generation of Virtulal Personal Assistants (Microsoft Cortana, Apple … [5] Open Source Speech Recognition Toolkit, https://cmusphinx.github.io/, accessed July 7, 2018 … [8] Chi Zhao, “Text Labeling Applied in Shopping Assistant Robot using …

Voice to Text transcription using CMU Sphinx A mobile application for healthcare organization
B Lakdawala, F Khan, A Khan, Y Tomar… – 2018 Second …, 2018 – ieeexplore.ieee.org
Page 1. ?Voice to Text transcription using CMU Sphinx … Dr. Ashfaq Shaikh Assistant professor, Department of IT, MHSS College of Engineering , Mumbai,India ashfaq.mhss@gmail.com … It uses the CMUSphinx toolkit for speech recognition …

Neural Network Control Interface of the Speaker Dependent Computer System «Deep Interactive Voice Assistant DIVA» to Help People with Speech Impairments
T Khorosheva, M Novoseltseva, N Geidarov… – … on Intelligent Information …, 2018 – Springer
… voice assistants, for instance, Apple’s Siri, Google Assistant, Amazon’s Alexa and Alisa, created by Yandex. The code of free software open-source, which makes it possible to refine and adapt them for various situations. The most popular open-source systems are CMU Sphinx …

A Python-based Assistant Agent able to Interact with Natural Language
F Longo, C Santoro – ceur-ws.org
… The concept is that we, as users, expect that speech-based assistants can establish a meaningful dialogue with us … The assistant implemented, called Laura, has the objective of helping the user in browsing Wikipedia with speech-based … Available: http://cmusphinx.github.io …

Word assistant app with speech recognition
AK Hannemann – 2018 – upcommons.upc.edu
… Page 14. 3.2 Voice assistant services Voice assistant services are intelligent assistants which the user controls with his voice. There are many different voice assistant services. During the research I focused on five popular services by big companies: Siri by the Apple Inc …

Data-Driven Language Understanding for Spoken Dialogue Systems
N Mrkši? – 2018 – repository.cam.ac.uk
… Siri, Google Assistant and Amazon’s Alexa are permeating into every aspect of human life … data-driven language understanding paradigm in the context of real-world personal assistants … et al., 2002), CMUSphinx (Walker et al., 2004) and more recently Kaldi (Povey et al., 2011) …

DialogOS: Simple and extensible dialog modeling
A Koller, T Baumann, A Köhn – pdfs.semanticscholar.org
… We have presented DialogOS, a recently open-sourced spoken dialog system that is built with … R. Singh, W. Walker, M. Warmuth, and P. Wolf, “The CMU Sphinx-4 speech … are better responses: Introducing incrementality into sociable virtual personal assistants,” in Proceedings of …

Building multi-domain conversational systems from single domain resources
D Griol, JM Molina – Neurocomputing, 2018 – Elsevier
… a growing demand for natural human-machine interaction and favored the intelligent assistant metaphor, in … and a Japanese chatbot, dialogs between humans and an English chatbot, and dialog … source tools for speech recognition are AT&T speech API 4 , CMU Sphinx 5 , and …

Developing Applications for Voice Enabled IoT Devices to Improve Classroom Activities
M Ali, AM Hassan – 2018 21st International Conference of …, 2018 – ieeexplore.ieee.org
… EECSI, Yogyakarta, Indonesia, 2017. [13] VL Beattie, “SCIENTIFIC LEARNING READING ASSISTANT™: CMU SPHINX TECHNOLOGY IN A COMMERCIAL EDUCATIONAL SOFTWARE APPLICATION,” 2010. [14] R. Kapadia, S …

Voice Recognition Software on Embedded Devices
P Vojtas, J Stepan, D Sec, R Cimler… – Asian Conference on …, 2018 – Springer
… Some of them even contain smart algorithms which analyze whole sentences, trying to find contextual information and offer a solution, for example, Siri assistant by Apple, Cortana assistant by Microsoft, and Alexa built into Amazon Echo devices … CMU Sphinx …

Interactive Voice Response Using Automatic Speech Recognition Techniques for Call Centers
RR Sehgal, G Raj – 2018 – papers.ssrn.com
… 1. CMU SPHINX is a python based voice recognition system which works offline … for addressing the user queries and it basically provides a platform to develop conversational chatbots … We’ll be implementing the basic ChatBot Configuration in order to ensure that the same bot …

Building Test Speech Dataset on Russian Language for Spoken Document Retrieval Task
A Tatarinova, D Prozorov – 2018 IEEE East-West Design & Test …, 2018 – ieeexplore.ieee.org
… Building Test Speech Dataset on Russian Language for Spoken Document Retrieval Task Alexandra Tatarinova assistant at Vyatka State University tatarinova.alexg@gmail.com … [20] CMU Sphinx, Open Source Toolkit For Speech Recognition. http://cmusphinx.sourceforge.net …

Robot Magic: A Robust Interactive Humanoid Entertainment Robot
J Baltes – Recent Trends and Future Technology in Applied …, 2018 – books.google.com
… Page 266. Robot Magic: A Robust Interactive Humanoid Entertainment Robot 249 Fig. 2. High Level Agent Architecture card corners … In our system we use CMUSphinx to cre- ate a trained acoustic model for the assistant’s voice, that will then be used by PocketSphinx for …

Robot Magic: A Robust Interactive Humanoid Entertainment Robot
KJ Morris, V Samonin, J Anderson, MC Lau… – … Conference on Industrial …, 2018 – Springer
… 2. High Level Agent Architecture … In our system we use CMUSphinx to create a trained acoustic model for the assistant’s voice, that will then be used by PocketSphinx for speech recognition during the performance (for the assistant as well as the audience members) …

Human-centered manipulation and navigation with Robot DE NIRO
F Falck, S Doshi, N Smuts, J Lingi, K Rants… – arXiv preprint arXiv …, 2018 – arxiv.org
… [19] M. Ding, T. Matsubara, Y. Funaki, R. Ikeura, T. Mukai, and T. Oga- sawara, “Generation of comfortable lifting motion for a human transfer assistant robot,” International … [27] CM University, “CMU Sphinx documentation,” https://cmusphinx. github.io/wiki/, 2018 …

Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation
X He, QH Tran, W Havard, L Besacier… – arXiv preprint arXiv …, 2018 – arxiv.org
… In spoken dialog systems, however, the agent would only have ac- cess to noisy ASR transcriptions … sys- tem, oracle transcriptions of utterances are usually not available, ie the agent does not … Tran et al., 2017a), we use ASR transcripts, produced by the CMUSphinx ASR system …

Dictionary Application With Speech Recognition And Speech Synthesis
GV Sanjay, KS Mohan, KA Sham… – International …, 2018 – search.ebscohost.com
… SYNTHESIS Gaikwad Vijayendra Sanjay, Assistant Professor, Dept. of Computer Engineering, ABMSP’s Anantrao Pawar College of Engineering & Research, Savitribai Phule Pune University, Pune, Maharashtra, India … II. EXISTING RELATED WORK A. CMU Sphinx IV …

Development of Spoken Story Database in Malayalam Language
G Deekshitha, KR Sreelakshmi… – 2018 4th International …, 2018 – ieeexplore.ieee.org
… A speech recognizer is realized using this database with the help of CMU Sphinx … We also thank former research assistants Anjana Mariya Baby, Priya G Kurup, and all other speakers for their immense support towards the development of the … 2016. [5] https://cmusphinx.github.io …

Robonaut 2 and Watson: Cognitive dexterity for future exploration
JM Badger, P Strawser, L Farrell… – 2018 IEEE …, 2018 – ieeexplore.ieee.org
… Robonaut 2 (shown in Figure 1) was envisioned to be a robotic astronaut assistant or a … 3 https://github.com/cmusphinx/sphinxbase 4 https://github.com/cmusphinx/pocketsphinx 5 http://pointclouds.org … of relevant procedures) and to generate a task plan for the multi-agent team …

Privacy protection in cloud-A three stage model
A Tyagi, S Goel, A Srivastava… – Journal of Innovation in …, 2018 – indianjournals.com
IndianJournals.com – Gateway to access, disperse and preserve knowledge!

POSTER: I Can’t Hear This Because I Am Human: A Novel Design of Audio CAPTCHA System
J Choi, T Oh, W Aiken, SS Woo, H Kim – … of the 2018 on Asia Conference …, 2018 – dl.acm.org
… bots with their correct responses, rather than their incorrect ones. CCS CONCEPTS • Security and privacy ? Web application security; • Computing methodologies ? Speech recognition; Neural networks; KEYWORDS CAPTCHA; machine learning; speech recognition; bot …

Voice processing with Internet of Things for a home automation system
J Celis, R Llanos, S Castro, S Sepúlveda… – 2018 IEEE XXV …, 2018 – ieeexplore.ieee.org
… COMPARISON OF SYSTEM CHARACTERISTICS Characteristics Assistant IoT OZOM System Bandwidth Consumes 2 kB per command sent Turns the light on or off in the room Weight 2 Megabytes 14,5 Megabytes … [9] CMU Sphinx Project by … http://cmusphinx.sourceforge.net …

Candidate’S Declaration
MH Subaid – 2018 – cse.buet.ac.bd
… Supervisor: Dr. Rifat Shahriyar Assistant Professor Department of Computer Science and Engineering … CMUSphinx CMUSphinx, a set of libraries and tools, is used for speech recognition related developments … system. Sphinx3 is a slower, more accurate decoder …

Commandersong: A systematic approach for practical adversarial voice recognition
X Yuan, Y Chen, Y Zhao, Y Long, X Liu… – 27th {USENIX} Security …, 2018 – usenix.org
… Indiana University Bloomington, USA Abstract The popularity of automatic speech recognition (ASR) systems, like Google Assistant, Cortana, brings in secu- rity concerns, as demonstrated by recent attacks. The impacts of such …

Satja: Thai Elderly Speech Corpus for Speech Recognition
S Prajongjai, T Triyason, P Mongkolnam – Proceedings of the 10th …, 2018 – dl.acm.org
… Speech processing technology has evolved extensively, especially intelligent assistants and home-grown … To evaluate the performance of the database, we used the CMUSphinx toolkit from … of voice-based intelligent homes serving for the elderly, intelligent assistant, and elderly …

Pronunciation Detection for Foreign Language Learning Using MFCC and SVM
J Byun, D van der Haar – International Conference on Information Science …, 2018 – Springer
… There are other systems that aim for improving non-native English speakers’ pronunciation. Such systems include CMUSphinx, ELSA, Duolingo, and FLUENCY … This digital language learning assistant will be available to anyone, regardless of time and space …

A taxonomy of attacks via the speech interface
MK Bispham, I Agrafiotis, M Goldsmith – 2018 – ora.ox.ac.uk
… Several researchers have investigated the ways in which voice-controlled digital assistants might be exploited simply by using standard voice commands … Carlini et al. [37] speech recognition in voice-controlled digital assistant (Google Now) / speech recognition (CMU Sphinx) …

Design and Development of Voice Control System for Micro Unmanned Aerial Vehicles
C Thomas, R Bharadwaj, AK Mondal… – 2018 Aviation …, 2018 – arc.aiaa.org
… Engineering, UPES, Dehradun, India 3 Chief Research Scientist, Department of Aerospace Engineering, Indian Institute of Science, Bangalore, India 4 Assistant Professor, Department of … Various engines were considered like CMU Sphinx, Pocket Sphinx, Kaldi, Julius and HTK …

Design, Analysis & Prototyping of a Semi-Automated Staircase-Climbing Rehabilitation Robot
S Jha, H Chaudhary, S Satardey, P Kumar… – Proceedings of the …, 2018 – dl.acm.org
… While going through the stairs the bot traverses very slowly such that the friction between the caterpillar track … 2 Voice Teleoperation Voice recognition task is implemented on Raspberry Pi 2 using the open-source CMUSphinx toolkit … The cmu sphinx-4 speech recognition system …

Recognizing zero-resourced languages based on mismatched machine transcriptions
W Chen, M Hasegawa-Johnson… – 2018 IEEE International …, 2018 – ieeexplore.ieee.org
… Error Rate (PER) of different recognition systems from BUT (Hungarian, English, Czech, Russian), I2R (English and Mandarin), and CMU Sphinx (Mandarin) … [5] Vanessa Lim, Hui Shan Ang, Estelle Lee, and Boon Pang Lim, “Towards an Interactive Voice Agent for Singapore …

Multilingual Low-Resourced Prototype System for Voice-Controlled Intelligent Building Applications
A Caranica, L Georgescu, A Vulpe, H Cucu – World Conference on …, 2018 – Springer
… Here, the effort made by Google and Amazon, to rapidly push into the consumer market their vision of home personal assistants, can be mentioned [2]. Both popular systems rely on the “cloud” model to push relevant … CMU Sphinx Toolkit. http://cmusphinx.sourceforge.net. 16 …

A Vulnerability Test Method for Speech Recognition Systems Based on Frequency Signal Processing
H Yang, D Liang, X Kuang, C Xu – 2018 IEEE Third International …, 2018 – ieeexplore.ieee.org
… issued a simulation model based on the vulnerability priority policy HTAC (Highest Threat Agent Count) based on the CVSS vector and … to verify our approach to testing and discovering the vulnerability of speech systems, we chose the classical CMU Sphinx speech recognition …

A Voice Command Detection system for controlling Movement of SCOUT Robot
S Azargoshasb, AH Korayem… – 2018 6th RSI …, 2018 – ieeexplore.ieee.org
… I. INTRODUCTION Today, robots are used as partners, assistants and companions for different purposes … A new intentional speech control is proposed and the speech recognition is implemented using CMU Sphinx [4]. ? Corresponding Author …

Building Blocks of Assistant Based Speech Recognition for Air Traffic Management Applications
M Kleinert, H Helmke, H Ehr, C Kern, D Klakow… – 2018 – publications.idiap.ch
… Assistant System, which provides eg radar data, flight plan information, weather data and additional information (eg landing sequence) … To be able to model all possi- ble commands spoken by ATCos, we expand standard CMU-Sphinx dictionary (of Carnegie Mellon University …

A Two-layer Authentication Using Voiceprint for Voice Assistants
YT Chang – 2018 – digital.lib.washington.edu
… smart homes [7], assistant robot [33], or drug delivery [12]. 2.1.2 Abuses and attacks While voice assistants become more and more efficient and useful, the abuses of voice assistant can cause serious loss to users. For instance, a little girl asked Alexa in her home, “Can you …

Robotic assistance in the coordination of patient care
M Gombolay, XJ Yang, B Hayes… – … Journal of Robotics …, 2018 – journals.sagepub.com
We conducted a study to investigate trust in and dependence upon robotic decision support among nurses and doctors on a labor and delivery floor. There is evide…

Analysis of the Computational Complexity of Algorithms for Phonemic Transcription
D Prozorov, A Tatarinova – 2018 IEEE East-West Design & Test …, 2018 – ieeexplore.ieee.org
… Alexandra Tatarinova assistant at Vyatka State University tatarinova.alexg@gmail.com Abstract … [10] CMU Sphinx. Open Source Toolkit For Speech Recognition // http://cmusphinx.sourceforge. net [11] Accord.Net Framework // http://accord-framework.net …

Iterative Learning of Speech Recognition Models for Air Traffic Control
A Srinivasamurthy, P Motlicek, M Singh… – Proceedings of the …, 2018 – isca-speech.org
… Virtual assistants capable of natural language understanding, even within a lim- ited domain of … that introducing au- tomation into this process in the form of ASR, called Assistant … such as airlines and waypoints are combined and added to the standard CMU-Sphinx dictionary to …

MIRTO: an open-source robotic platform for education
K Androutsopoulos, L Aristodemou, J Boender… – Proceedings of the 3rd …, 2018 – dl.acm.org
… A number of options are available for younger children: sev- eral variants of the Bee-Bot platform are commonly used in pri … The team involved in teaching the first year includes academic and teaching assistants delivering sessions; teaching assistants are also employed to …

Discussion-facilitator: towards enabling students with hearing disabilities to participate in classroom discussions
MA Alzubaidi, M Otoom – International Journal of Technology …, 2018 – researchgate.net
… “Automatic speech recognition for under-resourced languages: A survey,” Speech Communication, 56: 85-100. 2014. [35] “CMU Sphinx Open Source Toolkit For Speech Recognition Project”. sourceforge Website. http://cmusphinx.sourceforge.net. Web. 15 July 2016 …

Development of a Human-AI Teaming Based Mobile Language Learning Solution for Dual Language Learners in Early and Special Educations
S Shukla – 2018 – rave.ohiolink.edu
… pronunciation ….. 33 Page 7. vii LIST OF TABLES Table 2.1: Phonemes from CMU Sphinx and their sample usage ….. 9 Table … a native speaker is not available to assist. It will serve as a virtual assistant at the school for the …

Touch-Supported Voice Recording to Facilitate Forced Alignment of Text and Speech in an E-Reading Interface
B Axtell, C Munteanu, C Demmans Epp, Y Aly… – … on Intelligent User …, 2018 – dl.acm.org
… Modifications to Classic Forced Alignment All use of forced alignment for both TFA and classic FA uses CMUSphinx’s implementation of … changes made to the pronunciation dictionary to include words in the read texts missing from the provided CMU Sphinx English language …

Semi-supervised Adaptation of Assistant Based Speech Recognition Models for different Approach Areas
M Kleinert, H Helmke, G Siol, H Ehr… – 2018 IEEE/AIAA 37th …, 2018 – ieeexplore.ieee.org
… BUILDING BLOCKS OF ASSISTANT BASED SPEECH RECOGNITION Assistant Based Speech Recognition (ABSR) normally uses three main models (dark blue … To be able to model all possible commands spoken by ATCos, we expand standard CMU- Sphinx dictionary [41] by …

Sign Language Converter
S Jagruti, MPM Kochar, MCM Bajpayee – ijecscse.org
… 3.2.3. CMU Sphinx CMU Sphinx, is also called as Sphinx in short, is the general name of speech recognition … Prof. Jagruti S. Wankhade Assistant Professor, Information Technology, Jawaharlal Darda Institute Of Engineering & Technology, Yavatmal Email: jswankhade86@gmail …

BackDoor: Sounds that a microphone can record, but that humans can’t hear
N Roy, H Hassanieh, RR Choudhury – GetMobile: Mobile Computing …, 2018 – dl.acm.org
… 63–74. [5] Cmu sphinx. http://cmusphinx.sourceforge.net. [6] Perez, JPA, Pueyo, SC, and Lopez, BCAgc fundamentals. In Automatic Gain Control … Haitham Hassanieh is an assistant professor in ECE and CS at UIUC. He received his PhD Degree in EECS from MIT in 2016 …

Web-based Mobile Robot Control and Monitoring
DLH Ma, N Zhou – cs.binghamton.edu
… commands which can be converted to ROS commands to publish and subscribe ROS topics and request ROS services for operations of the Turtle- Bot. The feature of controlling the TurtleBot through speech commands is enabled by using the CMU Sphinx speech recognition …

Innovations in Smart Cities and Applications: Proceedings of the 2nd Mediterranean Symposium on Smart City Applications
MB Ahmed, AA Boudhir – 2018 – books.google.com
… Citizens, the inhabitants of the intelligent cities become agents of change, fully aware of the city challenges and play a qualified role in the civic network, characterized by participation, civic engagement, ter- ritorial commitment, and the will of sharing knowledge of creativity …

Speech and Gestures for Smart-Home Control and Interaction for Older Adults
JSA Lee – Proceedings of the 3rd International Workshop on …, 2018 – dl.acm.org
… on the difficulties they encountered at home and experiences with smart assistant technology … same participants, namely older adults who are inexperienced in using smart assistants such as … also usable in well-known speech recognition frameworks such as the CMU Sphinx-4. It …

New Technologies to Enhance Computer Generated Interactive Virtual Humans
KT Yao, DM Davis, JJ Liu, NJ Kaimakis – the Proceedings of the SISO …, 2018 – hpc-educ.org
… for Multi-party Dialogue in Immersive Virtual Worlds.” In Proceedings of the first International Joint Conference on Autonomous Agents and Multi-agent Systems: part … “Introduction to Arabic Speech Recognition using CMU Sphinx Sys- tem … “Designing a Personal Assistant for Life …

Automatic speech recognition for launch control center communication using recurrent neural networks with data augmentation and custom language model
K Yun, J Osborne, M Lee, T Lu… – … in Information Sciences, 2018 – spiedigitallibrary.org
… 0 Kaldi RNN IBM CMU Sphinx Google RNN + data RNN + data augmentation augmentation + language models … We compared the word error rate (%) between Kaldi 21, CMUSphinx 22, IBM Watson Speech to Text, Google Speech API, RNN, and RNN with data augmentation …

Continuous density hidden markov model for hindi speech recognition
S Sinha, SS Agrawal, A Jain – GSTF Journal on Computing (JoC), 2018 – dl6.globalstf.org
… expanded from simplest system of digit recognition to spontaneous dialogue systems.Such growth … special characters like period and hyphen.Tools like CMUSphinx requires simple … 2001 [23] CMU-Sphinx Speaker Independent Speech Recognition System http://www.speech.cs …

A comparison of mobile search interfaces for isiXhosa speakers
M Modise – 2018 – open.uct.ac.za
Page 1. University of Cape Town A Comparison of Mobile Search Interfaces for isiXhosa Speakers By MOREBODI MODISE Department of Computer Science UNIVERSITY OF CAPE TOWN A dissertation submitted to the University …

An efficient speech recognition system for arm?disabled students based on isolated words
KA Darabkh, L Haddad, SZ Sweidan… – Computer …, 2018 – Wiley Online Library
… In reference [69], an Arabic speech recognition system was proposed utilizing open source Carnegie Melon University (CMU) Sphinx-4 and hidden Markov models (HMM). Actually, HMM is considered as an effective statistical model …

Mapping language to vision in a real-world robotic scenario
K Štepánová, FB Klein, A Cangelosi… – IEEE Transactions on …, 2018 – ieeexplore.ieee.org
… important for understanding hu- man cognition but is also applicable in many areas, such as verbal control of interactive ro- bots [28], automatic … can learn new sym- bols using already grounded ones and their combination [5] and how to transfer knowledge between agents [52] …

Impulsive intermodal cyber bullying recognition from public nets
JI Sheeba, SP Devaneyan – International Journal of Advanced …, 2018 – researchgate.net
… JISheeba Assistant Professor, Department of Computer Science and Engineering Pondicherry Engineering College Puducherry,India … Here the audio will be converted into text using CMU Sphinx tool.In the converted text cyberbully will be detected using trained dataset [17] …

An Embedded Prototype System for People with Disabilities Using Google’s Speech
M Aguirre-Munizaga, V Vergara-Lozano… – … Europe Middle East & …, 2018 – Springer
… from what they normally are delayed performing the same activities without the system and with the help of their personal assistant … AAAI (2014, in press)Google Scholar. 7. Këpuska, V.: Comparing speech recognition systems (Microsoft API, Google API and CMU Sphinx). Int …

An Embedded Prototype System for People with Disabilities Using Google’s Speech
C Delgado, J Ramirez-Yela… – Information Systems and …, 2018 – books.google.com
… the use of the system, from what they normally are delayed performing the same activities without the system and with the help of their personal assistant … AAAI (2014, in press) 7. Këpuska, V.: Comparing speech recognition systems (Microsoft API, Google API and CMU Sphinx) …

A Voice Controlled E-Commerce Web Application
MS Kandhari, F Zulkemine… – 2018 IEEE 9th Annual …, 2018 – ieeexplore.ieee.org
… They compared the Hidden Markov Model Toolkit (HTK) with HDecode and Julius, CMU Sphinx, and the Kaldi toolkit … 123 Page 7. commerce websites to some extent. In the future, we will focus on incorporating a virtual assistant to provide recommendations …

Automated Lexical Analysis of Interviews with Schizophrenic Patients
S Xu, Z Yang, D Chakraborty, Y Tahir… – … Dialogue Systems …, 2018 – pdfs.semanticscholar.org
… 1 https://cloud.google.com/speech/ 2 https://cmusphinx.github.io/ 3 https://azure.microsoft.com/ en-us/services/cognitive-services/speech/ Page 6. 6 … 21. Kpuska, V. and Bohouta, G., 2017. Comparing speech recognition systems (Microsoft API, Google API and CMU Sphinx). Int …

Hand, Foot or Voice: Alternative Input Modalities for Touchless Interaction in the Medical Domain
B Hatscher, C Hansen – Proceedings of the 2018 on International …, 2018 – dl.acm.org
… This is prone to errors by misunderstanding and relies on the assistant’s expert knowledge … by X-ray for a short amount of time when contrast agent is administered … we integrated PocketSphinx, a lightweight speech recognition engine based on CMU Sphinx Natural Language …

Data Augmentation Using Healthy Speech for Dysarthric Speech Recognition
B Vachhani, C Bhat, SK Kopparapu – Proc. Interspeech 2018, 2018 – isca-speech.org
… Takiguchi, Y. Ariki, S. Duffner, and C. Garcia, “Dysarthric speech recognition using a convolutive bot- tleneck network … 24] CMU Sphinx:, “The Carnegie … Available: http://cmusphinx.sourceforge. net/, Mar 2018 [25] VoxForge, http://www.voxforge.org/home/downloads, viewed March …

The Smart Data Layer
M Sahlgren, E Ylipää, B Brown, K Helms… – 2018 AAAI Spring …, 2018 – aaai.org
… data. As an example, imagine that we 1https://cloud.google.com/vision/ 2https://github.com/cmusphinx/pocketsphinx 186 Page 3 … player). and embodied agents that appropriately act and enact with users and on their behalf …

Investigating the Effects of Word Substitution Errors on Sentence Embeddings
R Voleti, JM Liss, V Berisha – arXiv preprint arXiv:1811.07021, 2018 – arxiv.org
… Examples include sentiment analysis of product reviews, customer service chatbots, biomedical informatics … Speech Recognition Systems (Microsoft API, Google API And CMU Sphinx),” Int … An integrated dialog simulation technique for evaluating spoken dialog systems,” in Coling …

DNN-HMM based automatic speech recognition for HRI scenarios
J Novoa, J Wuth, JP Escudero, J Fredes… – Proceedings of the …, 2018 – dl.acm.org
… CMU Sphinx engine was also employed in [49], as part of a voice control system for a robotic endoscope holder during minimally invasive … source speech recognizer Sphinx can be tuned to outperform Google cloud-based speech recognition API in a spoken dialog system task …

Hidebehind: Enjoy Voice Input with Voiceprint Unclonability and Anonymity
J Qian, H Du, J Hou, L Chen, T Jung, XY Li – Proceedings of the 16th …, 2018 – dl.acm.org
… Though many existing apps have their own voice input feature such as voice-based virtual assistants, privacy-aware users can choose to tap the … PDA: PDA is a speech database from CMU Sphinx Group [4], which contains 16 speak- ers each speaking over 50 short sentences …

Whistle-blowing ASRs: evaluating the need for more inclusive automatic speech recognition systems
M Moore, H Venkateswara… – Proceedings of the …, 2018 – researchgate.net
… popularization of products like Amazon Alexa®, Google Home®, and Voice Assistants like Siri … Category CMU Sphinx Google % Diff Dysarthric 126% 43% 84% Control 63% 20% 74% %Diff … Panchanathan, S. Chakraborty, and T. McDaniel, “Social in- teraction assistant: A person …

Lip syncing method for realistic expressive 3D face model
IR Ali, H Kolivand, MH Alkawaz – Multimedia Tools and Applications, 2018 – Springer
… advent of computer-aided technologies, animated virtual characters are widely used in movies, games and embodied conversational agents (ECAs) to … easy to extend research on virtual human characters by using Xface Open Source Project and SMIL-Agent Scripting Language …

Speak Up: A Multi-Year Deployment of Games to Motivate Speech Therapy in India
A Nanavati, MB Dias, A Steinfeld – … of the 2018 CHI Conference on …, 2018 – dl.acm.org
… role in the games, making changes that encouraged teachers to build their computer literacy, and adding an embodied agent … However, many conversational agents, games, and visualizations have been developed to sup- port speech therapy for children with disabilities since …

The multimodal speech and visual gesture (mSVG) control model for a practical patrol, search, and rescue aerobot
AO Abioye, SD Prior, GT Thomas, P Saddington… – Annual Conference …, 2018 – Springer
… [11] discovered that HERMES, a humanoid robot assistant, appeared more … Speech is captured via a microphone, processed and recognised using the CMU Sphinx ASR with … Bischoff, R., Graefe, V.: Dependable multimodal communication and interaction with robotic assistants …

Road Navigation System Using Automatic Speech Recognition (ASR) And Natural Language Processing (NLP)
P Withanage, T Liyanage… – 2018 IEEE Region …, 2018 – ieeexplore.ieee.org
… Navigation Dialog Systems have become very popular among Human Machine Interfaces in recent years … from https://www.cnet.com/how-to/5-android-navigation-apps-for-those- who-are-sick-of-google-maps/ [7] Basic concepts of speech recognition – CMUSphinx Open …

The Multimodal Speech and Visual Gesture (mSVG) Control Model for a Practical Patrol, Search, and Rescue Aerobot
P Saddington, SD Ramchurn – … , TAROS 2018, Bristol, UK July 25 …, 2018 – books.google.com
… domains.[11] dis- covered that HERMES, a humanoid robot assistant, appeared more … captured via a microphone, processed and recognised using the CMU Sphinx ASR with … Bischoff, R., Graefe, V.: Dependable multimodal communication and interaction with robotic assistants …

Training Speech Recognition Models on HPC Infrastructure
D Karkada, VA Saletore – 2018 IEEE/ACM Machine Learning in …, 2018 – ieeexplore.ieee.org
… Abstract—Automatic speech recognition is used extensively in speech interfaces and spoken dialogue systems … 2345–2349. [11] P. Lamere, P. Kwok, E. Gouvea, B. Raj, R. Singh, W. Walker, M. Warmuth, and P. Wolf, “The cmu sphinx-4 speech recog- nition system,” in IEEE Intl …

The control system based on extended bci for a robotic wheelchair
TI Voznenko, EV Chepin, GA Urvanov – Procedia computer science, 2018 – Elsevier
… [12] P. Lamere, P. Kwok, E. Gouvea, B. Raj, R. Singh, W. Walker, M. Warmuth, and P. Wolf. The cmu sphinx-4 speech recognition system … [16] GA Urvanov, VV Dan’shin, AA Dyumin, and Chepin EV The system of human interaction as an agent of mobile robotic system …

Approaches to natural language processing in app development
C Djoweini, H Hellberg – 2018 – diva-portal.org
… The recent surge in interest for devices and applications like Amazon’s Alexa home assistant, and Google Home, is testament to this, since they allow the domestic user to interact with software as if it was another person [4] …

Conversational agent as kitchen assistant
B Rystedt, M Zdybek – 2018 – diva-portal.org
… They can also combine skills to make all round conversational assistants … The assistant should have functions such as saving the ingredients of a recipe as a grocery list on … with sup- port for several engines and APIs, online and offline, including CMU Sphinx, Google Speech …

Modeling and Development of a Spoken Natural Language Interface for Autonomous Robot Interaction
AS Brandão, AG Caldeira – … and 2018 Workshop on Robotics in …, 2018 – ieeexplore.ieee.org
… application to better understand and predict the environment where this agent will be … the developed process is an efficient method to start developing agents supposed to … Bohouta, “Comparing speech recognition systems (microsoft api, google api and cmu sphinx),” Journal …

An overview of vulnerabilities of voice controlled systems
Y Gong, C Poellabauer – arXiv preprint arXiv:1803.09156, 2018 – arxiv.org
… In addition, most smartphones are also equipped with smart voice assistants such as Siri, Google Now, and … that are intelligible as a specific command to ASR systems (Google Now and CMU Sphinx), but are … 2] W. Diao, X. Liu, Z. Zhou, and K. Zhang, “Your voice assistant is mine …

A taxonomy of cyber-physical threats and impact in the smart home
R Heartfield, G Loukas, S Budimir, A Bezemskij… – Computers & …, 2018 – Elsevier
… Within the context of the smart home, it is the occupants who make the ultimate decision to install a new wireless security lock, presence sensor or voice-controlled assistant, as privacy and security concerns are carried out according to occupants’ risk attitude Rahmati et al …

A multimodal analysis of making
M Worsley, P Blikstein – International Journal of Artificial Intelligence in …, 2018 – Springer
… Animated. Teaching Assistant. Minimal … Custom software was developed based on the Carnegie Mellon University (CMU) Sphinx Speech Recognition Toolkit (Lee et al. 1990). Specifically, the source code was modified to leverage the program’s voice activity detection feature …

Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations
PG Shivakumar, P Georgiou – arXiv preprint arXiv:1805.03322, 2018 – arxiv.org
… performed an in-depth analysis of linguistic variability in the context of spoken dialogue systems for children … children’s training data reference transcripts and the second generic English language model from CMU-Sphinx-41 … 1Language model version: cmusphinx-5.0-en-us.lm …

Guido and Am I Robot? A Case Study of Two Robotic Artworks Operating in Public Spaces
P Granjon, A Dutech, P Henaff – 2018 – repository.cardiffmet.ac.uk
… Both the art- works described in the article recognise this gap and the lack of an even remotely satisfactory general artificial intelligence, the intelligence of “autonomous agents that operate much like beings in the world” (Brooks, 2017) …

Interactive Spoken Content Retrieval by Deep Reinforcement Learning
HY Lee, PH Chung, YC Wu, TH Lin… – IEEE/ACM Transactions on …, 2018 – dl.acm.org
… made so far in bor- rowing from the experiences and expertise of spoken dialogue systems … The retrieval and feature extraction modules are corresponding to the language understanding module in dialogue system … On the other hand, in our setting, the agent has to request the …

Accessible Math: Best Practices After 25 Years of Research and Development
S Noble, N Soiffer, S Dooley, E Lozano, D Brown – 2018 – scholarworks.csun.edu
… limiting recognition to that smaller language. Mathifier was based on CMU’s Sphinx 4 speech Page 8 … With the advent of machine learning via deep neural networks, speaker-independent speech input on phones, home assistants, and other devices has become popular …

A heterogeneous mobile cloud computing model for hybrid clouds
S Alonso-Monsalve, F García-Carballeira… – Future Generation …, 2018 – Elsevier
… Mesos consists of a master daemon that manages agent daemons running on each cluster node, and the Mesos framework runs tasks on these agents. This resource manager is only available for infrastructures where the number of agents is known …

Protecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues
Y Gong, C Poellabauer – 2018 27th International Conference on …, 2018 – ieeexplore.ieee.org
… In addition, most smartphones are also equipped with smart voice assistants such as Siri, Google Assistant, and Cortana … successfully generate adversarial sound exam- ples that are intelligible as a specific command to ASR systems (Google Now and CMU Sphinx), but are …

Towards Intelligent Social Robots: From Naive Robots to Robot Sapiens
A Aly, S Griffiths, V Nitsch, K Pastra… – … on Intelligent Robots …, 2018 – hal.archives-ouvertes.fr
… untrained CMUSphinx) … While several models for privacy exist, they have tended to be either abstract definitions applicable to data rather than an agent operating autonomously in the world (such as encryption [1], data synthesis [2], anonymization [3], or opacity [4] mechanisms …

RoboCup@ Home: Summarizing achievements in over eleven years of competition
M Matamoros, V Seib… – … Robot Systems and …, 2018 – ieeexplore.ieee.org
… ASR [23], Nuance VoCon [19], and the Microsoft Speech API [7], [16], being most popular CMU Sphinx [24], [17 … come out, such as why should one acquire a robot while a human assistants are much … C. Müller, Z. Jin, R. Hartanto, P. Ploeger et al., “The b-it-bots robocup@ home …

Dynamic o offading of application services to edge servers using docker swarm and microservices
2018 – ir.lib.uth.gr
… Christos D. Antonopoulos, Assistant Professor … This systems consists of monitoring ”probes” that interact with the application, a ”monitoring agent” that aggregates the data from the probes and a server that stores relevant information in a time-series database …

Assessing Performance of Bengali Speech Recognizers Under Real World Conditions using GMM-HMM and DNN based Methods}}
S Khan, M Pal, J Basu, MS Bepari, R Roy – Proc. The 6th Intl. Workshop on … – isca-speech.org
… Connected word ASR application (Agri domain) The real time application is actually a telephony spoken dialog system [21] designed to disseminate regional agricultural commodity market prices and weather information (with forecast) to the target … [13] CMU SPHINX available at …

Automatic Speech Recognition Adaptation for Various Noise Levels
AS Abdulaziz – 2018 – repository.lib.fit.edu
… Josko Zec, Ph.D. Associate Professor, Electrical and Computer Engineering Nezamoddin Nezamoddini-Kachouie, Ph.D. Assistant Professor, Mathematical Sciences Page 4. Abstract … dictation, voice search, personal digital assistant, gaming, living room interaction …

Machines for Living
R Twomey – 2018 – digital.lib.washington.edu
… interactive chatbot and my dialog with the system in Megahal Grandmommy.10 Similarly, an … such “matrix of activity,” and is particularly dense in numbers of human and non-human agents, relationships in motion, and layers of material accretion …

Supporting Human Autonomy in a Robot-Assisted Medication Sorting Task
JR Wilson, NY Lee, A Saechao… – International Journal of …, 2018 – Springer
… Other examples of service robots are iCat [22] and Care-O-bot [18], or gen- eral purpose robots like the PR2 [38] or the Pioneer [34 … A research assistant informed each participant that the robot will be assisting in a task involving placing the medica- tions onto the medication grid …

Speech Reading with Deep Neural Networks
L Billman, J Hullberg – 2018 – diva-portal.org
… The improvement in ASR has led to many applications eg personal assistants, such as Apple’s Siri [11] or Microsoft’s Cortana [12], system controls in vehicles [13], assistance for people with disabilities [14], and many more …

CognitiveEMS: A Cognitive Assistant System for Emergency Medical Services
S Preum, S Shu, M Hotaki, R Williams, J Stankovic… – researchgate.net
… present ANTICO [8], an emergency agent architecture for emergency response managers that … Although both ANTICO and CognitiveEMS are emer- gency response assistant, they target different … recognizers (ASRs) in terms of their suitability for use in different dialogue systems …

Methods for Evaluation of Imperfect Captioning Tools by Deaf or Hard-of-Hearing Users at Different Reading Literacy Levels
L Berke, S Kafle, M Huenerfauth – … of the 2018 CHI Conference on …, 2018 – dl.acm.org
… Our screening criteria included two questions: “Are you Deaf or Hard-of-Hearing?” and “Do you use captions when viewing television?” Participants who answered affirmatively to both met a research assistant (a native ASL signer) to participate in the study in a private office …

Vocalic, Lexical and Prosodic Cues for the INTERSPEECH 2018 Self-Assessed Affect Challenge
C Montacié, MJ Caraty – Proc. Interspeech 2018, 2018 – isca-speech.org
… The semaine database: Annotated multimodal records of emotionally colored conversations between a person and a limited agent”, IEEE Transactions … Y. Sun, D. Huggins-Daines, and M. Seltzer, “The Hieroglyphs: Building Speech Applications Using CMU Sphinx and Relate …

Voice Control in a Real Flight Deck Environment
M Trzos, M Dostl, P Machkov, J Eitlerov – International Workshop on …, 2018 – Springer
… After the grammar was written, we used a tool from CMUSphinx jsgf2fsg to transform the JSGF-based grammar to a finite … Ranzenberger, T., Hacker, Ch., Gallwitz, F.: Integration of a Kaldi speech recognizer into a speech dialog system for automotive infotainment applications …

Automatic temporal ranking of children’s engagement levels using multi-modal cues
J Kim, KP Truong, V Evers – Computer Speech & Language, 2018 – Elsevier
Skip to main content …

Integrating automatic transcription into the language documentation workflow: Experiments with Na data and the Persephone toolkit
A Michaud, O Adams, TA Cohn, G Neubig… – 2018 – scholarspace.manoa.hawaii.edu
… using transcribed narratives in Na as training data for CMU Sphinx (https://cmusphinx.github. io … work, for the technical reason that it was not handled in the CMU Sphinx toolkit … with a comparable degree of proficiency were available to do the respeaking (as research assistants) …

Developing a voice-controlled home-assisting system for KTH Live-in Labs
S Maloo – 2018 – diva-portal.org
… 15 Page 16. 3.1. SPEECH TO TEXT SERVICES CHAPTER 3. BACKGROUND CMU Sphinx Project … But then again, this technology gives a higher sense of autonomy when the user does not need to press any button to start the assistant …

Inaudible voice commands: the long-range attack and defense
N Roy, S Shen, H Hassanieh… – 15th {USENIX} Symposium …, 2018 – usenix.org
Page 1. This paper is included in the Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI ’18). April 9–11, 2018 • Renton, WA, USA ISBN 978-1-931971-43-0 Open access to the Proceedings of …

Different recipient designs with dialogue partners: An experimental comparison between a Chatbot and a Human communication partner
A Westin – 2018 – diva-portal.org
… The assistants are most often female, which encourage a long heritage of feminizing … Participant understanding, Human/Chatbot understanding and Repetition were answered through a likert scale … on earlier research that showed participants get bored with Chatbots easier than …

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System
E Uzun, SPH Chung, I Essa… – … 2018 Network and …, 2018 – pdfs.semanticscholar.org
… Our analysis for registration is very simple and mostly involves sanity check of the received face and voice sample to make sure they came from a real human being to further avoid bot registration and … CMU Sphinx is the state-of-the art solution among HMM based approaches …

Speech verification for computer assisted pronunciation training
R Ai – 2018 – publikationen.sulb.uni-saarland.de
… The author’s main effort in the project was to realize the first goal, with inspi- ration and support from MARYTTS, which was developed in an earlier project NECA (A Net Environment for Embodied Emotional Conversational Agents), funded by European Union …

Data Visualization and KPI’s Using Speech Recognition
H Wagh – 2018 – search.proquest.com
… It works online as well as offline. Packages that constitute this package are CMU Sphinx, Google Speech Recognition, Google Cloud Speech API, Wit.ai, Microsoft Bing Voice Recognition, Houndify API, IBM Speech to Text, and Snowboy Hotword Detection …

Design for an Art Therapy Robot: An Explorative Review of the Theoretical Foundations for Engaging in Emotional and Creative Painting with a Robot
M Cooney, M Menezes – Multimodal Technologies and Interaction, 2018 – mdpi.com
… Furthermore, in comparison with other technologies such as virtual agents, robots have been reported to elicit stronger perceived emotions, presence, motivation, and engagement [23,24,25,26], and could perform more behaviors, such as seeking out a person to interact …

Creation and Comparison of Language and Acoustic Models Using Kaldi for Noisy and Enhanced Speech Data
YG Thimmaraja, HS Jayanna – International Journal of Intelligent …, 2018 – mecs-press.org
… Fig.1. Block diagram of Kaldi speech recognition toolkit Various speech recognition toolkits are used to build a robust Automatic Speech Recognition (ASR) system. They are, Kaldi, CMU Sphinx, Hidden Markov Model Toolkit (HTK) and Julius etc., [15] …

Hello, computer. Approaches to designing speech-based user experiences
S Schultz – 2018 – researcharchive.vuw.ac.nz
… interaction by voice— ‘speech–based interface’ —or their so-called ‘intel- ligent assistants’ to be an important move into the future of computing … presentation devoted to demonstrat- ing new features for their Assistant platform (Pichai, 2018). Within weeks …

See No Evil, Hear No Evil: Audio-Visual-Textual Cyberbullying Detection
D Soni, VK Singh – Proceedings of the ACM on Human-Computer …, 2018 – dl.acm.org
… in literature include delayed actions, informing users of hidden consequences, links to educational material, use of normative agents, and flagging … We use CMUSphinx [86] to extract the speech in the audio, and pyAudioAnalysis [31] to segment the audio and measure valence …

Refinement of HMM model parameters for punjabi automatic speech recognition (PASR) system
V Kadyan, A Mantri, RK Aggarwal – IETE Journal of Research, 2018 – Taylor & Francis
Page 1. Refinement of HMM Model Parameters for Punjabi Automatic Speech Recognition (PASR) System Virender Kadyan1, Archana Mantri2 and RK Aggarwal3 1Department of Computer Science & Engineering, Chitkara …

Machine Learning for Inspired, Structured, Lyrical Music Composition
PM Bodily – 2018 – scholarsarchive.byu.edu
Page 1. Brigham Young University BYU ScholarsArchive All Theses and Dissertations 2018-07-01 Machine Learning for Inspired, Structured, Lyrical Music Composition Paul Mark Bodily Brigham Young University Follow this …

Practical Hidden Voice Attacks against Speech and Speaker Recognition Systems
H Abdullah, W Garcia, C Peeters, P Traynor… – ndss-symposium.org
… In particular, the increasing use of constrained/headless devices (eg, mobile phones, digital home assistants) has led to their widespread deployment … An adversary wants to execute an unauthorized command on a VPS (eg, Amazon Alexa, Google Home Assistant, or any voice …

FoggyCache: Cross-Device Approximate Computation Reuse
P Guo, B Hu, R Li, W Hu – Proceedings of the 24th Annual International …, 2018 – dl.acm.org
… speech recognition based assistance is now common on smartphones (eg, Siri, Cortana) and in homes (eg, Alexa and Google Assistant) … Learning-based workloads (eg, recognition, clas- si cation, and AI agent) and graphics rendering [55] both exhibit such resilience, and …

Comparison Between Cloud-based and Offline Speech Recognition Systems
E Gazeti? – 2018 – mediatum.ub.tum.de
… Assistant tools like Google Now from Google, Cortana from Microsoft, Watson from IBM, Siri from Cortana are advertising their SR systems more than ever in the technology division. But users are not always satisfied with the privacy and security of cloud-based SR systems …

Frame-Based Representation for Event Detection on Twitter
Y Qin, Y Zhang, M Zhang, D Zheng – IEICE TRANSACTIONS on …, 2018 – search.ieice.org
… AgrEvt is the number of events whose labels are agreed by † http://cmusphinx. sourceforge.net/2013/01/ a-new-english-language-model-release/ Table 4 Experimental results of bursty feature selection methods on de- velop set …

Generating Text Summaries for the Facebook Data Breach with Prototyping on the 2017 Solar Eclipse
L Hamilton, E Robb, A Fitzpatrick, A Goel, R Nandigam – 2018 – vtechworks.lib.vt.edu
… neural network. To bridge the two networks, they use reinforcement learning, with a sentence-level reward policy based on ROGUE score. The ‘agent’ being trained by the reinforcement learning is the extractive summarizer. This model …

Intelligent Situation Awareness and Navigation Aid for Visually Impaired Persons
B Li – 2018 – search.proquest.com
Page 1. Intelligent Situation Awareness and Navigation Aid for Visually Impaired Persons by Bing Li A dissertation submitted to the Graduate Faculty in Electrical Engineering in partial ful- fillment of the requirements for the degree …

Concept-Based Embeddings for Natural Language Processing
Y Ma, E Cambria – arXiv preprint arXiv:1807.05519, 2018 – arxiv.org
… Named entities are typically belonging to several semantic classes defined according to the particular interest of down- stream applications. For example, a flight booking assistant system might re- quire recognizing the location names corresponding to departure and arrival …

(Visited 104 times, 1 visits today)