PocketSphinx 2018


Notes:

  • Video to Text (V2T)

Resources:

Wikipedia:

See also:

100 Best CMUSphinx VideosCMUSphinx & Dialog Systems 2018


Spoken English Intelligibility Remediation with PocketSphinx Alignment and Feature Extraction Improves Substantially over the State of the Art
Y Gao, BML Srivastava… – 2018 2nd IEEE Advanced …, 2018 – ieeexplore.ieee.org
W279 use automatic speech recognition to assess spoken English learner pronunciation based on the authentic intelligibility of the learners’ spoken responses determined from support vector machine (SVM) classifier or deep learning neural network model predictions …

Voice Recognition Software on Embedded Devices
P Vojtas, J Stepan, D Sec, R Cimler… – Asian Conference on …, 2018 – Springer
… Keywords. Voice recognition Raspberry Pi Julius PocketSphinx. Download conference paper PDF. 1 Introduction … It has a fork for low performance devices, called Pocket Sphinx. It is discussed in [8, 9]. The software consists of three parts …

A Cloud Middleware Enabling Natural Speech Analysis for IoT Policy Enforcement in Smart Home Environments
R Iqbal, JH Lee, J Hall – … Congress on Internet of Things (ICIOT), 2018 – ieeexplore.ieee.org
… 1) Audio to Text processing: Once a JSON file arrives at the middleware, the byte stream will be extracted and sent to PocketSphinx [11] and Google’s Cloud Speech API [12] to decode the streamed speech data. PocketSphinx is a lightweight offline speech recognition tool …

Speech Recognition System Using Open-Source Speech Engine for Indian Names
NA Kallole, R Prakash – Intelligent Embedded Systems, 2018 – Springer
… Open-source package used is Pocketsphinx for speech recognition and festival for text-to-speech and pronunciation generation … The open-source software called Pocketsphinx is used, which depends on another library named sphinxbase …

Speech to Text and Vice Versa
NK Manaswi – Deep Learning with Applications Using Python, 2018 – Springer
… previously. Examples Using Each API. Let’s go through each API. Using PocketSphinx. PocketSphinx is an open source API used for speech-to-text conversions … desktop. Simply use the command pip install PocketSphinx to install the package …

Speech Recognition using Recurrent Neural Networks
A Amberkar, P Awasarmol… – … on Current Trends …, 2018 – ieeexplore.ieee.org
… Fig. 8. Implementation using pocket-sphinx STT Engine From the above figure, words which we want to use is trained using CMU pocketsphinx online tool and then on any linux based or windows based operating system we can implement the code using proper commands by …

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
… Kaldi is available on SourceForge.The tools compile on the commonly used Unix-like systems and on Microsoft Windows.[5][11] POCKETSPHINX: It uses CMU Sphinx – II as its base … Toolkit Error Rate HDecode v3.4.1 and Julius 19.8 & 23.1 PocketSphinx 21.4 Kaldi 6.5 …

FIND IT An Android application to find misplaced phone of user in the vicinity
B Tekwani, V Bhandiwad… – … on I-SMAC (IoT in Social …, 2018 – ieeexplore.ieee.org
… In this application a version of Sphinx named PocketSphinx is used which is a lightweight speech recognition engine, specifically tuned for … David Huggins-Daines, Mohit Kumar, Arthur Chan, Alan W Black, Mosur Ravishankar and Alex I. Rudnicky in “Pocket Sphinx: A free, real …

Design and Development of Voice Control System for Micro Unmanned Aerial Vehicles
C Thomas, R Bharadwaj, AK Mondal… – 2018 Aviation …, 2018 – arc.aiaa.org
… Pocket sphinx speech prediction can be even increased to a more comfortable level by isolating user speech from background noise and by … 2. D. Huggins-Daines, M. Kumar, A. Chan, AW Black, M. Ravishankar, AI Rudnicky, “Pocketsphinx: A Free, Real-Time Continuous …

Developing a voice-controlled home-assisting system for KTH Live-in Labs
S Maloo – 2018 – diva-portal.org
… Pocketsphinx is an open source speech decoder developed under the 15 … The advantage of using Pocketsphinx is that the speech recognition is performed offline, which means we don’t need an active Internet connection. However, the recognition rate is on the poorer side …

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
… The dataset includes radio news audio files with speech on Russian language, textual files with spoken words, textual files with recognition words from CMU Pocketsphinx and a set of queries with indication of relevant documents …

Design of interactive learning media to pronunciation characters and words English for blind children
MF Wicaksono – IOP Conference Series: Materials Science …, 2018 – iopscience.iop.org
… In question mode, used speech to text method using open source speech recognition Sphinx, where speech recognizer used is Pocketsphinx … The received sound will be converted into text and stored into a variable by utilizing Sphinx and PocketSphinx speech recognizer …

Towards Reactive Acoustic Jamming for Personal Voice Assistants
P Cheng, IE Bagci, J Yan, U Roedig – Proceedings of the 2nd …, 2018 – dl.acm.org
… Central part of a PVA device is the wake word recognition imple- mentation. Corporations such as Apple or Microsoft do not provide details of their implementations; however, open source toolkits such as AlexaPi based on PocketSphinx developed by CMU [5] are available …

Voice Controlled Wheelchair
V Shwetha, V Mani, A Kumaran – International Journal of …, 2018 – eprints.manipal.edu
… withstanding capacity of 50 kg. The software implementation is the implementation of voice recognition on a Ubuntu distribution with the help of the CMU Sphinx Toolkit and the Pocket sphinx library. The coding for the voice …

Interactive mobile robot in a dynamic environment
B Rehman, R Yagfarov, A Klimchik – IFAC-PapersOnLine, 2018 – Elsevier
… A number of languages with different accents are available in pocketshinx to train the acoustic model. Pocketsphinx gave different results for different persons … Pocket- sphinx: A free, real-time continuous speech recognition system for hand-held devices …

Sinhala speech recognition for interactive voice response systems accessed through mobile phones
W Manamperi, D Karunathilake… – 2018 Moratuwa …, 2018 – ieeexplore.ieee.org
… The ASR module is based on HMM, uses SphinxTrain for training the acoustic model and PocketSphinx for decoding … The system gives a WER of 9.35% and 28.62% with the PocketSphinx and the Sphinx-4 decoders respectively …

Interaction and learning in a humanoid robot magic performance
KJ Morris, J Anderson, MC Lau, J Baltes – 2018 AAAI Spring Symposium …, 2018 – aaai.org
… framework. These com- ponents utilize PocketSphinx for speech recognition, and OpenCV2 for playing card classification. The … 16kHz. Incoming audio is pro- cessed using PocketSphinx in order to generate a hypothesis string. This …

Rapid development of a command and control interface for smart office environments
NS Ramunyisi, J Badenhorst, C Moors… – Proceedings of the …, 2018 – dl.acm.org
… Similarly, the Pocketsphinx decoding parameters that we use are set for the NCHLT models and then kept at exactly the same setting when evaluating data using the Smart Control models … The Speech Node device implements the lightweight Pocket- sphinx decoder …

Speech-Based Drawing Application for Handicapped People
L Klinghammer, MAI Farhan, SR Angsanto… – 2018 – dbpia.co.kr
… market. An application that is fully controllable by speech was developed and successfully implement; albeit, the limitations of current mobile phones and the pocket-sphinx library hindered any ground breaking results. Nonetheless …

Candidate’S Declaration
MH Subaid – 2018 – cse.buet.ac.bd
… Page 14. Chapter 2 Background We used a package named ‘PocketSphinx’ of CMUSphinx for our purpose of speech to text conversion … Sphinx, Sphinx2, Sphinx3, Pocket- Sphinx, etc are the decoders. Different decoders have different properties such as Sphinx works …

Development of Spoken Story Database in Malayalam Language
G Deekshitha, KR Sreelakshmi… – 2018 4th International …, 2018 – ieeexplore.ieee.org
… Pocketsphinx is a light weight recognizer written in C mainly used for building mobile applications … 531 Page 3. library that provides basic common functionality for Sphinx4 and PocketSphinx, whereas Sphinxtrain is the tool for running and building the acoustic model …

Road Navigation System Using Automatic Speech Recognition (ASR) And Natural Language Processing (NLP)
P Withanage, T Liyanage… – 2018 IEEE Region …, 2018 – ieeexplore.ieee.org
… generating the user preferred route, system will first convert the audio streams into text through Automatic Speech Recognizer (ASR) using Pocket Sphinx Library, followed … Pocketsphinx library developed by Carnegie Mellon University which is designed for speed and portability …

SpokeIt: A Co-Created Speech Therapy Experience
JS Duval, E Márquez Segura… – Extended Abstracts of the …, 2018 – dl.acm.org
… Technical Details The offline real-time critical speech recognition system is built using RapidEars, an extension of Carnegie Mellon’s Pocketsphinx [5]. We have modified their system to listen for both correct and incorrect utterances of speech …

A semantic indexing approach of multimedia documents content based partial transcription
I Bendib, MR Laouar – 2018 2nd International Conference on …, 2018 – ieeexplore.ieee.org
… In recognition process, we propose use two APIs both: an online interface Google-API-python-client that uses the Google Cloud Speech API and an offline interface that uses PocketSphinx with the Sphinx recognizer module …

Intelligent Communication between User and Machine Using Deep Neural Network
MK Shah, SM Parikh – mathematicstoday.org
… After this voice navigator – II, SW, SDK has been published for apple Macintosh plus and windows. Now a day in many android apps have been make for this navigator. ? Pocket sphinx: Pocket sphinx tools are identifying 10k words with 20% error rate. This tool engine is …

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
… system. V. DEVELOPMENT OF INTELLIGENT VOICE ASSISTANT FOR A SPECIFIC PROBLEMS OF INTERACTION To work with voice recognition, it is advisable to use existing systems. For example, the PocketSphinx project. In …

Evaluating the impact of pushing voice-driven interaction pipelines to the edge
S Sridhar, ME Tolentino – Proceedings of the 15th ACM International …, 2018 – dl.acm.org
… More speci cally, we used the following components within our pipeline: Speech To Text. We used PocketSphinx [17], a widely known open source project for speech recognition from CMU. Pocket- Sphinx comes with a default language and acoustic model …

Towards a cognitive assistant system for emergency response
SM Preum, S Shu, J Ting, V Lin… – 2018 ACM/IEEE 9th …, 2018 – ieeexplore.ieee.org
… These tools are Google Online API, Microsoft speech API, PocketSphinx, and IBM BlueMix API … The Google cloud API outperforms the other three APIs in terms of both WER and runtime. Scenario Metrics PocketSphinx Google Microsoft IBM …

Hitting Three Birds with One System: A Voice-Based CAPTCHA for the Modern User
M Shah, K Harras – 2018 IEEE International Conference on …, 2018 – ieeexplore.ieee.org
… We use Pocketsphinx [36], via its Python bindings, to transcribe the speech signal that we receive from the user. We realize that several factors, including, accent, background noise, and individual pronunciation styles, can introduce minor errors in legitimate responses …

Robot Magic: A Robust Interactive Humanoid Entertainment Robot
KJ Morris, V Samonin, J Anderson, MC Lau… – … Conference on Industrial …, 2018 – Springer
… Among these blobs, the centroid is calculated, and if the cluster of blobs surpasses the minimum density threshold, we deem the card as found. For speech, raw audio is sampled at 16 mhz and hypothesis strings are then created using the PocketSphinx engine …

Robot Magic: A Robust Interactive Humanoid Entertainment Robot
J Baltes – Recent Trends and Future Technology in Applied …, 2018 – books.google.com
… Among these blobs, the centroid is calculated, and if the cluster of blobs surpasses the minimum density threshold, we deem the card as found. For speech, raw audio is sampled at 16 mhz and hypothesis strings are then created using the PocketSphinx engine …

Sentiment Extraction from Naturalistic Video
V Radhakrishnan, C Joseph… – Procedia computer …, 2018 – Elsevier
… In this experiment, we apply KWS on the text extracted from from audio using CMU’s PocketSphinx library … Another script analyses the audio files generated and converts it into text files using automatic speech recognition (PocketSphinx) …

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 ASR system was based on the version 0.8 of the Pocketsphinx recognizer library [40]. The acoustic models were the pre-trained generic German acoustic models provided by CMU [40] … This ASR was based on the version 0.8 of the Pocketsphinx recognizer library [40] …

Estimation of the Optimal HMM Parameters for Amazigh Speech Recognition System Using CMU-Sphinx
M Telmem, Y Ghanou – Procedia Computer Science, 2018 – Elsevier
… they have a number of packages for different tasks and applications: • Pocketsphinx: Lightweight library of written recognition in C. • Sphinxbase: support for libraries required by Pocketsphinx • Sphinx4: decoder for voice recognition search written in Java • CMUclmtk: Language …

Building an Open Source Automatic Speech Recognition System for Catalan}}
B Külebi, A Öktem – Proc. IberSPEECH 2018, 2018 – isca-speech.org
… ASR system, which has been developed at Carnegie Mellon University over many decades starting from the original Sphinx- I [4] to its more recent and advanced incarnations of Sphinx- 3 [5] and Sphinx-4 [6]. For this work, we specifically used the PocketSphinx package within …

A Natural Language Interaction Based Automatic Operating System for Industrial Robot
Y Lin, H Min, H Zhou, M Chen – International Conference on Intelligent …, 2018 – Springer
… An open source speech recognition system (PocketSphinx) for the embedded platform is used for speech recognition in the system [14] and the multi-language and cross-platform open source speech synthesis system Ekho is employed for speech synthesis [15] …

Safeshareride: Edge-based attack detection in ridesharing services
L Liu, X Zhang, M Qiao, W Shi – 2018 IEEE/ACM Symposium …, 2018 – ieeexplore.ieee.org
… Specifically, we leveraged the speech recognition toolkit, Pocket- Sphinx, which is based on CMUSphinx [18] on Android phones … For speech recognition in SafeShareRide, we implemented PocketSphinx-based app using Google’s speech recogni- tion toolkit on the smartphone …

SpokeIt: building a mobile speech therapy experience
J Duval, Z Rubin, EM Segura, N Friedman… – Proceedings of the 20th …, 2018 – dl.acm.org
… The library we chose is Pocketsphinx, an offline speech recognition system for handheld devices from Carnegie Mellon [19] … OpenEars is a free open-source framework that brings the power of Pocketsphinx to iOS devices in native objective-c language for speed and reliability …

Real-Time Scoring of an Oral Reading Assessment on Mobile Devices
J Cheng – Proc. Interspeech 2018, 2018 – isca-speech.org
… 336–354, 2008. [7] D. Huggins-Daines, M. Kumar, A. Chan, AW Black, M. Rav- ishankar, and AI Rudnicky, “Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices,” in ICASSP, 2006, pp … [11] CMUSphinx, “Pocketsphinx,” Computer Software …

Speech-driven mobile games for speech therapy: User experiences and feasibility
B Ahmed, P Monroe, A Hair, CT Tan… – … journal of speech …, 2018 – Taylor & Francis
… All the speech-controlled games tested in this study incorporated the mobile device version of CMU Sphinx speech recognition framework, PocketSphinx (SourceForge, 2018) … For the iOS games, PocketSphinx was adapted and compiled for use within an iOS environment …

Multimodal Interfaces for Inclusive Learning
M Worsley, D Barel, L Davison, T Large… – … Conference on Artificial …, 2018 – Springer
… C++ is used to capture data from the eye tracker, while Python is used for all other capabilities. Namely, the Python code features the speech recognizer (PocketSphinx [12]) and a rudimentary natural language understanding engine using Spacy and Wordnet …

Comparison of different Acoustic Models for Kannada language using Kaldi Toolkit
T Sahana, N Srilasya, KJ Priya… – … on Advances in …, 2018 – ieeexplore.ieee.org
… The toolkits used for the comparison are HDecode v3.4.1, Julius v4.3 27.2 23.1, pocketsphinx v0.8, sphinx-4 and Kaldi. The comparison showed that Kaldi toolkit outperforms all other toolkits in terms of WER by almost 100 …

Real Time Speech Translation (Universal Translator)
M Syed, G Bohouta – bohouta.com
… Open Source Speech Recognition Systems • The following packages are required for Sphinx 4: • sphinxbase-5prealpha • sphinxtrain-5prealpha • pocketsphinx-5prealpha • The following packages are required for Deep Speech: • TensorFlow • GPU specific package …

Erkam Uzun, Pak Ho “Simon” Chung, Irfan Essa
W Lee – prism.gatech.edu
… For all the provided CAPTCHA responses, we used the CMU Pocketsphinx [17] to con- vert them into text before determining, in real time, whether the response is correct … Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices …

MIRTO: an open-source robotic platform for education
K Androutsopoulos, L Aristodemou, J Boender… – Proceedings of the 3rd …, 2018 – dl.acm.org
… We report below two submissions received in previous years and a third year project that led to a publication. 4.2.1 Voice recognition. This project by a first year student in- volved the use of Carnegie Mellon PocketSphinx4, a lightweight …

Technical Paper of HITCSC for The 8 th International Aerial Robotics Competition
N Wang, Y Hou, N Hao – aerialroboticscompetition.org
… As for the Mike or sound card, which is to be chosen further, is to serve for human-robot interaction by speech recognition technology. Now, the pocketsphinx speech recognizer is being redeveloped to do human-robot interaction …

Quantifying the effects of varying light-visibility and noise-sound levels in practical multimodal speech and visual gesture (mSVG) interaction with aerobots
AO Abioye, SD Prior, GT Thomas… – … on Applied System …, 2018 – ieeexplore.ieee.org
… Some popular audio speech recognition (ASR) toolkits are the Microsoft speech platform SDK, CMU PocketSphinx, and Googles web speech API [7]. In order to develop a speech control method for a UAV, one needs to take into account the average noise level generated by …

Forced Alignment of the Phonologie du Français Contemporain Corpus
G Christodoulides – International Conference on Statistical Language and …, 2018 – Springer
… A quick constrained speech recognition is performed on the overlapping segment, using PocketSphinx [11], in an effort to detect the overlap in the recording, with a better temporal precision than the one given by the transcription …

Speaker Hand-Offs in Collaborative Human-Agent Oral Presentations
P Murali, L Ring, H Trinh, R Asadi… – Proceedings of the 18th …, 2018 – dl.acm.org
… 25. D. Huggins-Daines, M. Kumar, A. Chan, AW Black, M Ravishankar, & AI Rudnick (2006, May). Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices. In Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings …

Development of Qibla Direction Cane for Blind Using Interactive Voice Command
A Asrin, GI Hapsari, GA Mutiara – 2018 6th International …, 2018 – ieeexplore.ieee.org
… When using Voice Control, there are two systems which function as Speech To Text (STT) and Text To Speech (TTS). The software used is Pocketsphinx (STT) as a software that can interpret human sounds into text and picco (TTS) as software that can convert text to sound. [8] …

Implementation of Google Assistant on Rasberry Pi
S Mischie, L Mâ?iu-Iovan… – … on Electronics and …, 2018 – ieeexplore.ieee.org
… computer. There are some open source software packages that allow speech recognition such as Kaldi [4] or Pocket Sphinx [5]. However, in recent years cloud-based speech recognition systems have been developed a lot …

A voice control system for assistive robotic arms: preliminary usability tests on patients
TB Pulikottil, M Caimmi, MG D’Angelo… – 2018 7th IEEE …, 2018 – ieeexplore.ieee.org
… The system was able to interact with the user through voice commands (CMU Pocketsphinx and GStreamer packages) and augmented Re- ality 3D Vision Glasses (Vuzix Wrap 920AR Glasses) … Available: https://github.com/ Kinovarobotics/kinova-ros [26] “Pocketsphinx,” 2017 …

A novel ego-noise suppression algorithm for acoustic signal enhancement in autonomous systems
A Schmidt, HW Löllmann… – 2018 IEEE International …, 2018 – ieeexplore.ieee.org
… sure speech keyword error rate (WER), using pocketsphinx [30] in the GRID corpus [28], as defined by the CHiME chal- lenge [31] … [30] D. Huggins-Daines et al., “Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices,” in IEEE Trans …

On Continuous Speech Recognition of Indian English
X Jin, K Zhang, X Huang, M Miao – Proceedings of the 2018 International …, 2018 – dl.acm.org
… Researches on speech recognition of Indian English is relatively rare. In 2016, Mandal et al. [2] proposed an acoustic modeling method for the construction of Indian English ASR System using Pocket Sphinx, which is mainly used in SMS sending applications …

Praaline: An Open-Source System for Managing, Annotating, Visualising and Analysing Speech Corpora
G Christodoulides – Proceedings of ACL 2018, System Demonstrations, 2018 – aclweb.org
… phoneti- sation, and an ASR engine. The currently sup- ported ASR engines in Praaline are HTK(Young et al., 2006), PocketSphinx (Walker et al., 2004) and Kaldi (Povey et al., 2011). The annotation framework in Praaline is …

EdgeBench: Benchmarking Edge Computing Platforms
A Das, S Patterson, M Wittie – 2018 IEEE/ACM International …, 2018 – ieeexplore.ieee.org
… We have converted the audio files into 16khz, 16 bit, mono ‘wav’ file format to comply with the requirements of PocketSphinx … [Online; Accessed July 2018]. [14] “CMU Pocketsphinx Python.” https://github.com/ cmusphinx/pocketsphinx-python, 2018 …

Open source platform Digital Personal Assistant
D Usachev, A Khusnutdinov, M Mazzara… – arXiv preprint arXiv …, 2018 – arxiv.org
… In its turn, open source DPAs such as MyCroft, Open Assistant, Jasper and ADRIAN use open source libraries and some of the libraries can be integrated in several assistants, eg library Pocketsphinx is involved in MyCroft, Open Assistant and Jasper [10]–[12] …

Open Source Platform Digital Personal Assistant
A Khusnutdinov, D Usachev, M Mazzara… – 2018 32nd …, 2018 – ieeexplore.ieee.org
… In its turn, open source DPAs such as MyCroft, Open Assistant, Jasper and ADRIAN use open source libraries and some of the libraries can be integrated in several assistants, eg library Pocketsphinx is involved in MyCroft, Open Assistant and Jasper [10]–[12] …

Voice-directed autonomous navigation of a smart-wheelchair
L Chen, S Wang, H Hu, D Gu, I Dukes – Smart Wheelchairs and Brain …, 2018 – Elsevier
… the mobile base; 5. Rinse and repeat. 17.4.2. Other Miscellaneous Software Modules. Recognizer. The recognizer node implements speech recognition using CMU Pocket Sphinx speech recognizer ( CMU, 2017). It reads the …

Efficient and robust deep networks for semantic segmentation
GL Oliveira, C Bollen, W Burgard… – … International Journal of …, 2018 – journals.sagepub.com
This paper explores and investigates deep convolutional neural network architectures to increase the efficiency and robustness of semantic segmentation tasks. T…

Androdid App” Ondher Josthi/Blind Eye” for Blind
N Faisal, M Islam, Z Hossain – 2018 – dspace.daffodilvarsity.edu.bd
… We used Pocket Sphinx android library for offline speech recognition. Another big challenge of this Page 17. ©Daffodil International University 8 … Page 28. ©Daffodil International University 19 6. Pocket sphinx library for offline speech recognition, machine learning is used in this …

Web-based Mobile Robot Control and Monitoring
DLH Ma, N Zhou – cs.binghamton.edu
… Bot. The feature of controlling the TurtleBot through speech commands is enabled by using the CMU Sphinx speech recognition system (Lamere et al., 2003), which has a simple wrapper for ROS users called pocketsphinx …

CognitiveEMS: A Cognitive Assistant System for Emergency Medical Services
S Preum, S Shu, M Hotaki, R Williams, J Stankovic… – researchgate.net
… Another research [16] analyzes several automatic speech recognizers (ASRs) in terms of their suitability for use in different dialogue systems. They consider PocketSphinx [17], Apple Dictation, Google Cloud Speech API, AT&T Watson, and Otosense-Kaldi …

Evaluating on-device ASR on Field Recordings from an Interactive Reading Companion
A Loukina, N Madnani, BB Klebanov… – 2018 IEEE Spoken …, 2018 – ieeexplore.ieee.org
… Only two system met this requirement: PocketSphinx [11] and KeenASR which uses Kaldi [18] … 1–12. Routledge, New York, 2016. [11] D. Huggins-Daines, Mohit Kumar, Arthur Chan, AW Black, Mosur Ravishankar, and AI Rudnicky, “Pocket- sphinx: A Free, Real-Time …

Low-power architectures for automatic speech recognition
H Tabani – 2018 – upcommons.upc.edu
… Firstly, we provide a performance and energy characterization of Pocketsphinx, a popular toolset for ASR that targets mobile devices … 46 2.4.4 Pocketsphinx Architecture . . . . . 47 3 Software Optimizations 49 …

Effect of TTS Generated Audio on OOV Detection and Word Error Rate in ASR for Low-resource Languages
S Murthy, D Sitaram, S Sitaram – Proc. Interspeech 2018, 2018 – isca-speech.org
… The Lexicon for the word model contains pronunciations of the words in training set and are represented as phonemes. The phone-set comprises of 48 phonemes, including SIL for silence. We use CMU PocketSphinx ASR toolkit1 and Language Mod- eling Toolkit. 2.2 …

Multilingual Low-Resourced Prototype System for Voice-Controlled Intelligent Building Applications
A Caranica, L Georgescu, A Vulpe, H Cucu – World Conference on …, 2018 – Springer
… It was developed using the C programming language, on the basis of the continuous speech decoder PocketSphinx API. The development kit connects both a microphone to retrieve the vocal signal and a speaker device to confirm to the user that his command has been made …

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
… captured whole body gestures and had visual markers (for localization and commands) via a Parrot AR Drone 2.0 camera, captured hand gestures via the Leap motion device, and speech command was captured via the ROS implementation of the CMU PocketSphinx library …

Tools and resources for Romanian text-to-speech and speech-to-text applications
T Boros, SD Dumitrescu, V Pais – arXiv preprint arXiv:1802.05583, 2018 – arxiv.org
… and computational re- sources. Given the success of the widely spread and well-known lightweight ASR system PocketSphinx (Huggins-Daines et al., 2006) we only address NLP and TTS with our tools. We do however, introduce …

Analysis of the Computational Complexity of Algorithms for Phonemic Transcription
D Prozorov, A Tatarinova – 2018 IEEE East-West Design & Test …, 2018 – ieeexplore.ieee.org
… 6. Experiment The comparison of algorithms of phonemic transcription mentioned in sections 3 through 5 was performed using a specially developed SDR-system in C # (the system uses the pocketsphinx library) [10]. HMM model implementation using Accord.Net library [11] …

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
… cap- tured whole body gestures and had visual markers (for localization and com- mands) via a Parrot AR Drone 2.0 camera, captured hand gestures via the Leap motion device, and speech command was captured via the ROS imple- mentation of the CMU PocketSphinx library …

The Smart Data Layer
M Sahlgren, E Ylipää, B Brown, K Helms… – 2018 AAAI Spring …, 2018 – aaai.org
… measures to find interest- ing patterns in the data. As an example, imagine that we 1https://cloud.google.com/vision/ 2https://github.com/cmusphinx/pocketsphinx 186 Page 3. use a word embedding technique to learn a concept …

dAIrector: Automatic Story Beat Generation through Knowledge Synthesis
M Eger, KW Mathewson – arXiv preprint arXiv:1811.03423, 2018 – arxiv.org
… For a live performance, this mode is less convenient and therefore we also provide the capabilities for speech input and output, realized through speech-to-text using pocketsphinx [HDKC+06] and text-to-speech using the built-in say operating system command …

Apraxia world: a speech therapy game for children with speech sound disorders
A Hair, P Monroe, B Ahmed, KJ Ballard… – Proceedings of the 17th …, 2018 – dl.acm.org
… of) the NDP3 set. Speech assessment Previous mobile speech therapy applications have used some form of automatic speech recognition (ASR), such as Pocketsphinx [19, 31] or custom approaches [37]. However, ASR on …

Autonomous systems research embedded in teaching
M Spichkova, M Simic – … on Intelligent Interactive Multimedia Systems and …, 2018 – Springer
… 5, students developed corresponding modules on speech, navigation and hand-movements. For the speech recognition, two kinds of processes were used: Commands requiring a prompt reaction (like “stop”): offline speech recogniser Pocketsphinx …

Design of an Autonomous Surveillance Robot Using Simultaneous Localization and Mapping
IH Shanavas, SA Ahmed… – … Conference on Design …, 2018 – ieeexplore.ieee.org
… The parameters and properties of the webcam were fine tuned in its launch files for best performance and video clarity. To provide speech recognition capability,the CMU pocket sphinx speech recognizer is used. The speech input is taken from the webcam’s inbuilt microphone …

Is automatic speech-to-text transcription ready for use in psychological experiments?
K Ziman, AC Heusser, PC Fitzpatrick, CE Field… – Behavior research …, 2018 – Springer
… We have intentionally avoided detailed comparisons between this speech-to-text engine and the other promising speech-to-text engines available today that may have other advantages or disadvantages (eg, Pocketsphinx; Huggins- Daines et al. (2006)) …

DNN-HMM based automatic speech recognition for HRI scenarios
J Novoa, J Wuth, JP Escudero, J Fredes… – Proceedings of the …, 2018 – dl.acm.org
… attributes. In [51], four ASR engines were compared by making use of different grammars: the Google Speech API; the Microsoft Speech APIM; Pocket Sphinx from CMU; and, the NAO-embedded Nuance VoCon 4.7 engine …

Multi channel speech command recognition for humanoid robots
T Walther – 2018 – tams.informatik.uni-hamburg.de
… Julius is mainly developed in Japan and is fully supporting Japanese but is just in development for English. Finally we had to decide between PocketSphinx, the core part of CMUSphinx, or Kaldi. Both matched all needed criteria. We decided us for Kaldi. 2.4.1 Kaldi …

Robonaut 2 and Watson: Cognitive dexterity for future exploration
JM Badger, P Strawser, L Farrell… – 2018 IEEE …, 2018 – ieeexplore.ieee.org
… The classifier node is a 2D image classifier written in Python. It is built on top of the TensorFlow7 3 https://github.com/cmusphinx/sphinxbase 4 https://github.com/cmusphinx/ pocketsphinx 5 http://pointclouds.org/ 6 https://opencv.org/ library …

Humanoid medical assistant and companion robot for patients
M Zukowski, K Matus, D Kamienski… – AIP Conference …, 2018 – aip.scitation.org
… commands via a USB connection to the embedded system controlling drive motors, • bobot_speech – synthesizes speech in multiple languages using the espeak library, • bobot_ears – recognizes known commands using the pocketsphinx library, • bobot_people_recognition …

Verbal Chess using Computer Vision with the Baxter Research Robot
Z Connell, C Desmond, R Cook – 2018 – repository.uwyo.edu
… Prewritten Python and ROS libraries, including pocketsphinx, Baxter’s Inverse Kinematics Service, pyttsx, and OpenCV are employed to enable computer vision, speech recognition, speech output, and arm movements … PocketSphinx License …

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System
E Uzun, SPH Chung, I Essa… – … 2018 Network and …, 2018 – pdfs.semanticscholar.org
… dictionary. We used the open-sourced CMU Pocketsphinx library, Carnegie Mellon University’s Sphinx speech recognition system [44], in our user study app since it provides a lightweight library working on mobile devices. CMU …

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
… Headphones (Bose GmbH, Friedrichsdorf, Germany). For speech recognition we integrated PocketSphinx, a lightweight speech recognition engine based on CMU Sphinx Natural Language Processing library [14]. The library was used …

A vision and speech enabled, customizable, virtual assistant for smart environments
G Iannizzotto, LL Bello, A Nucita… – 2018 11th International …, 2018 – ieeexplore.ieee.org
… There are currently two modules in the Wake Word class, namely, the Snowboy module, integrating the SnowBoy deep neural networks-based software [17], and the PocketSphinx module, based on the homonymous open source software developed by Carnegie Mellon …

An Efficient Mobile-Based Middleware Architecture for Building Robust, High-Performance Apps
OJ Romero, SA Akoju – 2018 IEEE International Conference on …, 2018 – ieeexplore.ieee.org
… ASR inputs. ADROITNESS not only includes an effector for TTS but also provides a extensible API that allows to plug different kind of ASR implementations (eg, Google ASR, Microsoft Bing, CMU Pocket-sphinx, etc.) V. EVALUATION …

Rhonda: the architecture of a multilingual speech-to-speech translation pipeline
JA Louw, A Moodley – 2018 International Conference on …, 2018 – ieeexplore.ieee.org
… broker to other programming languages. Worker implementations have been interfaced with the PocketSphinx [36] ASR engine, a Grammatical framework based MT system and the Speect [33] TTS engine. This string of HLT …

Algorithms for Automatic Accentuation and Transcription of Russian Texts in Speech Recognition Systems
O Yakovenko, I Bondarenko, M Borovikova… – … Conference on Speech …, 2018 – Springer
… ranking. In: EMNLP (2013)Google Scholar. 8. Huggins-daines, D., Kumar, M., Chan, A., Black, AW, Ravishankar, M., Rudnicky, AI: PocketSphinx: a free, real-time continuous speech recognition system for hand-held devices. In …

Swing: Swarm Computing for Mobile Sensing
S Fan, T Salonidis, B Lee – 2018 IEEE 38th International …, 2018 – ieeexplore.ieee.org
Page 1. Swing: Swarm Computing for Mobile Sensing Songchun Fan* Google Mountain View, CA, USA Email: schfan@google.com Theodoros Salonidis IBM TJ Watson Research Center Yorktown Heights, NY, USA Email: tsaloni@us.ibm.com …

TeMoto: Intuitive Multi-Range Telerobotic System with Natural Gestural and Verbal Instruction Interface
R Valner, K Kruusamäe, M Pryor – Robotics, 2018 – mdpi.com
… ROS Navigation [43] generates collision-free paths for the mobile base. Voice commands are converted to text using a speech recognition package Pocketsphinx [44]. The TeMoto Core contains 5 developed modules, implemented as ROS nodes …

Automatic voice control system for UAV-based accessories
F Rezac, J Safarik, E Gresak… – Unmanned Systems …, 2018 – spiedigitallibrary.org
… Libraries use hidden Markov models to improve the recognition results, and a proposed mobile application works with the Pocketsphinx package, which is a lightweight version of the voice recognition tool written in C language.The application itself is written in Java language …

Ambient intelligence framework for real-time speech-to-sign translation
M Otoom, MA Alzubaidi – Assistive Technology, 2018 – Taylor & Francis
… In this work, the CMU Sphinx (2016) software is used as the speech recognition system to translate English speech into an English text stream. Pocketsphinx is a freely available mobile version of the well-known CMU Sphinx software (Lamere et al., 2003) …

Safety First: Conversational Agents for Health Care
T Bickmore, H Trinh, R Asadi, S Olafsson – Studies in Conversational UX …, 2018 – Springer
… deep neural networks (Hinton et al. 2012). Currently, several open source ASR engines such as Pocketsphinx (Huggins-Daines et al. 2006), Kaldi (Povey et al. 2011), and HTK (Woodland et al. 1994) are available, but accurate …

Baseline Acoustic Models for Brazilian Portuguese Using Kaldi Tools}}
C Batista, AL Dias, NCS Neto – Proc. IberSPEECH 2018, 2018 – isca-speech.org
… 375–380. [5] S. Young, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book. Cambridge University Engineering Department, version 3.4, 2006. [6] D. Huggins-Daines, M. Kumar, A. Chan, AW Black, M. Ravis- hankar, and AI Rudnicky, “Pocketsphinx: A free, real-time con …

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
… It can work on standalone hardware with low configurations(like mobile platforms). Page 23. 15 PocketSphinx toolkit is designed to work in offline mode. It uses prebuilt statistical models for speech recognition. It supports multiple languages and can also build a …

Mike–Your Personal Speech Therapist
J RAZA, H ALI – 2018 – 111.68.99.22
Page 1. 03-134142-063 MUHAMMAD JOHAR RAZA 03-134142-034 HUSSAIN ALI KHAN Mike – Your Personal Speech Therapist In partial fulfilment of the requirements for the degree of Bachelor of Science in Computer Science Supervisor: Tahir Iqbal …

Designing Pronunciation Learning Tools: The Case for Interactivity against Over-Engineering
S Robertson, C Munteanu, G Penn – … of the 2018 CHI Conference on …, 2018 – dl.acm.org
… non- native recording. SotA was trained using pilot data and expert labels, described in [39]. Word segments are computed online through Viterbi alignment of the audio data with Pocketsphinx [27]. The heuristic model, called …

Exploring Hands-Free Alternatives for Teleportation in VR
WL Spurgeon – 2018 – scholarworks.unr.edu
… cursor to appear. Voice activation was implemented using an open source speech recognition library called pocketsphinx for Android. To activate the teleportation, we ended up using the phonetically distinct keyword of “Okra”, which was rec …

Deep Learning with Applications Using Python
NK Manaswi, NK Manaswi, S John – 2018 – Springer
… TABLE OF CONTENTS Page 8. vii Examples Using Each API …..135 Using PocketSphinx …..135 Using the Google Speech API …..136 …

Characteristics that influence perceived intelligence in AI design
S Krening, KM Feigh – Proceedings of the Human Factors …, 2018 – journals.sagepub.com
… 2625–2633). Huggins-Daines, D., Kumar, M., Chan, A., Black, AW, Ravishankar, M., & Rudnicky, AI (2006). Pocketsphinx: A free, real-time contin- uous speech recognition system for hand-held devices. In Acoustics, speech and signal processing, 2006 …

A Study on the Deployment of a Service Robot in an Elderly Care Center
D Portugal, P Alvito, E Christodoulou… – International Journal of …, 2018 – Springer
Page 1. International Journal of Social Robotics https://doi.org/10.1007/s12369-018-0492-5 A Study on the Deployment of a Service Robot in an Elderly Care Center David Portugal1 · Paulo Alvito2 · Eleni Christodoulou1 · George Samaras3 · Jorge Dias4,5 …

Algorithms For Accentuation And Phonemic Transcription Of Russian Texts In Speech Recognition Systems
OS Yakovenko, IY Bondarenko, MN Borovikova – dialog-21.ru
… EMNLP, available at: https://static.googleusercontent.com/media/research.google. com/ru//pubs/archive/41392.pdf. 5. D. Huggins-daines, M. Kumar, A. Chan, AW Black, M. Ravishankar , AI Rudnicky (2006): “PocketSphinx: A free …

An algorithm for multi tempo music lyric transcription
H Amoah – 2018 – air.ashesi.edu.gh
… on mobile devices and embedded systems (Tabani, Arnau, Tubella, & González, 2017). This paper seeks to test a performance and energy characterization of Pocketsphinx, a toolset used for ASR (Tabani, Arnau, Tubella, & González, 2017) …

Librob: An Autonomous Assistive Librarian
C Di Veroli, CA Le, T Lemaire, E Makabu, A Nur, V Ooi… – lemaire.io
… the speech recognition package to operate. Pocketsphinx, an offline Speech Recognition package for PYTHON, was also tested, however the accuracy of the speech recognition suffered greatly. In the future, a substantial amount …

Institute of Communications Engineering Staff
M Bossert, R Fischer, W Minker, UC Fiebig… – Journal on Multimodal …, 2018 – uni-ulm.de

A Framework For Understanding And Detecting Harassment In SocialVR
L POWELL – tabilab.cmpe.boun.edu.tr
Page 1. A FRAMEWORK FOR UNDERSTANDING AND DETECTING HARASSMENT IN SOCIALVR LANCE POWELL BO?AZ?Ç? UNIVERSITY 2018 Page 2. A FRAMEWORK FOR UNDERSTANDING AND DETECTING HARASSMENT IN SOCIALVR Thesis submitted to the …

Hello, computer. Approaches to designing speech-based user experiences
S Schultz – 2018 – researcharchive.vuw.ac.nz
Page 1. Hello, computer. Approaches to designing speech-based user experiences. Stefan Schultz Victoria University of Wellington, 2018 A 90-point thesis submitted to Victoria University of Wellington, in partial fulfilment of the requirements for the degree of …

A Human–Robot-Environment Interactive Reasoning Mechanism for Object Sorting Robot
Y Lin, H Min, H Zhou, F Pei – IEEE Transactions on Cognitive …, 2018 – ieeexplore.ieee.org
Page 1. 2379-8920 (c) 2016 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org …

Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices
J Park, Y Boo, I Choi, S Shin, W Sung – Advances in Neural …, 2018 – papers.nips.cc
… IEEE, 2017. [7] David Huggins-Daines, Mohit Kumar, Arthur Chan, Alan W Black, Mosur Ravishankar, and Alexander I Rudnicky. Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices. In …

Instinctive Assistive Indoor Navigation using Distributed Intelligence
M Muztoba, R Voleti, F Karabacak, J Park… – ACM Transactions on …, 2018 – dl.acm.org
… Speech: While natural speech recognition is demanding, a handful of simple voice com- mands can be recognized with less processing power. We use the Pocketsphinx speech recognition system [23] to detect the user’s voice commands for navigation …

Newtonian Action Advice: Integrating Human Verbal Instruction with Reinforcement Learning
S Krening – arXiv preprint arXiv:1804.05821, 2018 – arxiv.org
… Huggins-Daines, D., Kumar, M., Chan, A., Black, AW, Ravishankar, M., and Rudnicky, AI (2006). Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices. In Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings …

Developing a cognitive assistant for the audit plan brainstorming session
Q Li, MA Vasarhelyi – 2018 – rabida.uhu.es
… HUGGINS-DAINES, D.; KUMAR, M.; CHAN, A.; BLACK, AW; RAVISHANKAR, M.; RUDNICKY, AI (2006): “Pocketsphinx: A free, real- time continuous speech recognition system for hand-held devices”, In Acoustics, Speech and Signal Processing, ICASSP Proceedings …

Working With Useless Machines: A look at our shifting relationship with ubiquity through personal assistants
N Lessio – 2018 – openresearch.ocadu.ca
Page 1. Working With Useless Machines A look at our shifting relationship with ubiquity through personal assistants by: Nadine Lessio A thesis exhibition presented to OCAD University in partial fulfillment of the requirements for the degree of Master of Design in Digital Futures …

Autonomous Selection and Printing of 3D Models for People Who Are Blind
T Götzelmann – ACM Transactions on Accessible Computing …, 2018 – dl.acm.org
… For the application’s audio feedback, the standard .NET speech synthesis library was used. To make the application controllable by voice commands, the popular voice recognition library PocketSphinx [24] was chosen. This …

Automatic Speech Recognition Adaptation for Various Noise Levels
AS Abdulaziz – 2018 – repository.lib.fit.edu
Page 1. Automatic Speech Recognition Adaptation for Various Noise Levels by Azhar Sabah Abdulaziz Bachelor of Science Computer Engineering College of Engineering University of Mosul 2002 Master of Science in Communication …

Machines for Living
R Twomey – 2018 – digital.lib.washington.edu
Page 1. © Copyright 2018 Robert Twomey Page 2. Machines for Living Robert Twomey A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy University of Washington 2018 Reading Committee: Juan Pampin, Chair …

Visually Augmented Audio-Tactile Graphics for Visually Impaired People
T Götzelmann – ACM Transactions on Accessible Computing …, 2018 – dl.acm.org
… The results of queries (eg, to highlight all buildings) were visually augmented by adapting the rendering styles of the map. For the speech interaction, we utilized the CMU PocketSphinx SDK [19] developed for offline speech detection mobile devices …

Audiovisual Metadata Platform (AMP) Planning Project: Progress Report and Next Steps
JW Dunn, JL Hardesty, T Clement, C Lacinak… – 2018 – scholarworks.iu.edu
Page 1. This publication was made possible through a generous grant from The Andrew W. Mellon Foundation. Page 2. AMP Planning Project Report – March 2018 Report Publication Date March 27, 2018 Report Authors Jon …

Dynamic o offading of application services to edge servers using docker swarm and microservices
2018 – ir.lib.uth.gr
Page 1. Dynamic offloading of application services to edge servers using docker swarm and microservices George Georgiou Supervisors Spyros Lalis, Associate Professor Christos D. Antonopoulos, Assistant Professor 2018, Volos Greece …

A Developmental Model of Trust in Humanoid Robots
M Patacchiola – 2018 – pearl.plymouth.ac.uk
Page 1. This copy of the thesis has been supplied on condition that anyone who consults it is understood to recognise that its copyright rests with its author and that no quotation from the thesis and no information derived from …

Realizing Autonomy via Intelligent Hybrid Control: Adaptable Autonomy for Achieving UxV RSTA Team Decision Superiority (also known as Intelligent Multi-UxV …
M Draper, A Rowe, S Douglass, G Calhoun, S Spriggs… – 2018 – apps.dtic.mil
Page 1. AFRL-RH-WP-TR-2018-0005 Realizing Autonomy via Intelligent Adaptive Hybrid Control: Adaptable Autonomy for Achieving UxV RSTA Team Decision Superiority (also known as Intelligent Multi-UxV Planner with Adaptive …

HuMan: an accessible, polymorphic and personalized CAPTCHA interface with preemption feature tailored for persons with visual impairments
KS Kuppusamy, G Aghila – Universal Access in the Information Society, 2018 – Springer
Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is one of the major security components in the provision of fair web access by differentiating human access from…

Human-autonomy teaming interface design considerations for multi-unmanned vehicle control
GL Calhoun, HA Ruff, KJ Behymer… – Theoretical issues in …, 2018 – Taylor & Francis
Page 1. Human-autonomy teaming interface design considerations for multi-unmanned vehicle control GL Calhouna, HA Ruffb, KJ Behymerb and EM Frostc aAir Force Research Laboratory, Dayton, OH, USA; bInfoscitex, Dayton …

A survey of augmented reality: Making technology acceptable in outdoor environments
R Pascoal, B Alturas, A de Almeida… – 2018 13th Iberian …, 2018 – ieeexplore.ieee.org
… pp. 247–255. IEEE (2012) [14] Huggins-Daines, D., Kumar, M., Chan, A., Black, AW, Ravishankar, M., Rudnicky, AI: Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices. In: Acoustics, Speech and Signal Processing, 2006 …

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
Social robots are being designed to help support people’s well-being in domestic and public environments. To address increasing incidences of psychological and emotional difficulties such as loneliness, and a shortage of human healthcare workers, we believe that robots will also …

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 …

Interaction Algorithm Effect on Human Experience with Reinforcement Learning
S Krening, KM Feigh – ACM Transactions on Human-Robot Interaction …, 2018 – dl.acm.org
Page 1. 16 Interaction Algorithm Effect on Human Experience with Reinforcement Learning SAMANTHA KRENING and KAREN M. FEIGH, Georgia Institute of Technology, USA A goal of interactive machine learning (IML) is …

RAVEN: Improving Interactive Latency for the Connected Car
HJ Lee, J Flinn, B Tonshal – … of the 24th Annual International Conference …, 2018 – dl.acm.org
Page 1. RAVEN: Improving Interactive Latency for the Connected Car HyunJong Lee University of Michigan hyunjong@umich.edu Jason Flinn University of Michigan jflinn@umich.edu Basavaraj Tonshal Ford Motor Co. btonshal@ford.com ABSTRACT …

Word assistant app with speech recognition
AK Hannemann – 2018 – upcommons.upc.edu
Page 1. Master’s Thesis Word assistant app with speech recognition Ann-Katrin Hannemann Date of defence: 26th of April 2018 Supervising Professor: Enric Mayol Sarroca Departament d’Enginyeria de Serveis i Sistemes d’Informació …

(Visited 214 times, 1 visits today)