PocketSphinx 2016


Notes:

  • Video to Text (V2T)

Resources:

Wikipedia:

See also:

100 Best CMUSphinx VideosCMUSphinx & Dialog Systems 2016


Human-centric point of view for a robot partner: a cooperative project between France and Japan
M Jacquemont, J Woo, J Botzheim… – … on Research and …, 2016 – ieeexplore.ieee.org
… related acoustic model. Then we simply have to specify the three models when calling the listening method of the OpenEars Pocketsphinx controller. OpenEars 2.041 is based on a previous version of Pocket- sphinx. Then it doesn …

Robot Operation via Natural Voice Control
V Lee, C Ly, B Chen – 2016 – pdfs.semanticscholar.org
… We will present a simple proof-of-concept of such an interface. This interface is built through the use of pocketsphinx, an open-source library created by Carnegie Mellon University that works as a speech recognizer. … 4.2 Pocketsphinx …

Speech Control for HTML5 Hypervideo Players.
B Meixner, F Kallmeier – WSICC@ TVX, 2016 – fxpal.com
… PocketSphinx.js The implementation of speech detection and recognition with PocketSphinx. js required more effort compared to the imple- mentation with annyang, because the source code of Pocket- Sphinx.js only comes with an English acoustical model. …

ASR—A real-time speech recognition on portable devices
AS Sharma, R Bhalley – Advances in Computing …, 2016 – ieeexplore.ieee.org
… ASR) for portable devices. The speech recognition is performed offline using PocketSphinx which is the implementation of Carnegie Mellon University’s Sphinx speech recognition engine for portable devices. In this work, machine …

Research of a Mobile ATC Communication Training System
W PAN, J TAN, Q ZHANG… – DEStech Transactions on …, 2016 – dpi-proceedings.com
… As the popularity of the smart phones, a standard mobile ATC communication training system is designed based on IFLYTEK API, GOOGLE SPEECH API and Pocket Sphinx. … And it became an open source project. Pocket Sphinx is an embedded speech recognition system. …

Understanding and Building an Application with STT and TTS
T Pant – Building a Virtual Assistant for Raspberry Pi, 2016 – Springer
… Pocketsphinx is an open source speech decoder developed under the CMU Sphinx Project. … The advantage of using Pocketsphinx is that the speech recognition is performed offline, which means you don’t need an active Internet connection. …

SPEECH TO TEXT CONVERSION FOR CHEMICAL ENTITIES
F Kaleem, S Kanchan, P Kalbhor, A Kakde, S Patil – 2016 – ijirr.com
… To cleanup, here is the list: • Pocketsphinx — lightweight recognizer library written in C. • Sphinxbase — support library required by Pocketsphinx • Sphinx4 — adjustable, modifiable recognizer written in Java • Sphinxtrain — acoustic model training tools …

Speech Control of Measurement Devices
J Špale, C Schweizer – IFAC-PapersOnLine, 2016 – Elsevier
… The chosen solution was realized. Keywords: Speech Recognition, Text-to-Speech (TTS), Pocketsphinx, Nuance NDEV, Speech API, OpenEars, JSGF Grammar, Android, iOS, Qt … Keywords: Speech Recognition, Text-to-Speech (TTS), Pocketsphinx, Nuance NDEV, Speech API, …

Implementation of Android Based Speech Recognition for Indonesian Geography Dictionary
H Hugeng, E Hansel – ULTIMA Computing, 2016 – ejournals.umn.ac.id
… The approach used in recognition is Hidden Markov Model which is contained in the Pocketsphinx library. The phonemes used are Indonesian phonemes’ rule. … Index Terms—speech recognition, Indonesian geography dictionary, Hidden Markov Model, Pocketsphinx, Android. …

Design of a low-cost, open-source, humanoid robot companion for large retail spaces
T Lin, M Baron, B Hallier, M Raiti… – … (SIEDS), 2016 IEEE, 2016 – ieeexplore.ieee.org
… Index Terms – Festival, LabVIEW, HR-OS1, myRIO, PocketSphinx, ROS INTRODUCTION … The PocketSphinx node (top left) is responsible for capturing and transmitting the raw vocal commands from the user and placing its value in the “Raw Vocal Input” topic. …

Enhancing speech recognition in developing language learning systems for low cost Androids
A Jayakumar, M Raghunath… – … in Information and …, 2016 – ieeexplore.ieee.org
… It is a speaker- independent and continuous speech recognition system. Pocket Sphinx requires a dictionary, an acoustic model and a language model to recognize the speech. … Fig. 3. Component level diagram of PocketSphinx …

Speech Based Command and Control System for Mobile Phones: Issues and Challenges
P Mittal, N Singh – Computational Intelligence & …, 2016 – ieeexplore.ieee.org
… PocketSphinx, Sphinx, Google API can be used for developing speech applications. … External noise reduction usually degrades speech recognition accuracy, Pocketsphinx has its own noise reduction module which makes it quite robust to noise. …

Accoustic Modeling for Development of Accented Indian English ASR
P Mandal, G Ojha, A Shukla, SS Agrawal – Artificial Intelligence and …, 2016 – Springer
… A novel approach towards building an Automated Speech Recognition System (ASR) for Indian English using PocketSphinx has been proposed. … PocketSphinx happens to be the first such system and it comes with an open-source license. …

Design and implementation of sql query from spoken words using mobile technology
P Patel – 2016 – ir.inflibnet.ac.in
… 3(1). ISSN: 0976- 5999 [ 7 ] Patel, PN, Patel, JK & Virparia, PV (2014 Mar). Generating Database Query from Spoken Words on Android Smart Phone using Pocketsphinx. … Comparative Study of PocketSphinx and Sphinx with Google’s Speech Recognition API. …

Internet of Things Using Raspberry pi 2
S Awasthi, S Singh, R Soni – 2016 – academicscience.co.in
… Google speech API and Pocket sphinx has been used for speech recognition. … [Has better accuracy, is free for developers, online, and needs no training] Pocket sphinx [can recognise only predefined words, offline, needs training, free to use]. …

Indonesian Automatic Speech Recognition system using CMUSphinx toolkit and limited dataset
H Prakoso, R Ferdiana… – Electronics and Smart …, 2016 – ieeexplore.ieee.org
… ASR systems in Indonesian that implemented in mobile environment have been done in several research. Medical dictionary ASR with Android-based built by [11] and has an accuracy of 93.3% using PocketSphinx from CMUSphinx toolkit. …

KALDI GOES ANDROID
C Gaida, R Petrick, D Suendermann-Oeft – ehrai.com
… The only existing related work is, to the best of our knowledge, the develop- ment of PocketSphinx [4], a decoder initially designated for embedded platforms and subsequently ported to Android [5]. The choice of the Kaldi toolkit [6] was motivated by the results of comparisons [7 …

A study on motion control of a robotic endoscope holder using speech recognition
K Zinchenko, CY Wu, KT Song – Industrial Technology (ICIT) …, 2016 – ieeexplore.ieee.org
… A set of seven voice commands are used to control 3 degree of freedom(DOF) robotic arm with remote center of motion(RCM). Speech recognition algorithm was implemented on Ubuntu OS using Pocket Sphinx and achieved 90% success rate. …

Hybrid visual servoing design for a continuum robot under visibility constraint and voice commands
CY Wu, KT Song – … Automation and Systems (ICCAS), 2016 16th …, 2016 – ieeexplore.ieee.org
… source software: including Visual Servoing Platform(ViSP) [6], which is a cross-platform solution that allows prototyping and developing applications in visual tracking and visual servoing and Pocketsphinx, which provides access to the CMU Pocket Sphinx speech recognizer [7 …

An Open Voice Command Interface Kit
JA Ansari, A Sathyamurthy… – IEEE Transactions on …, 2016 – ieeexplore.ieee.org
… Software solutions are flexible, reliable, and scal- able. Due to advances in mobile computing and the availabil- ity of Pocketsphinx, an accurate and reliable open-source voice recognition engine, we have developed an open, software-based, voice command interface kit. …

EVALUATING ACOUSTIC, TEXTUAL AND GRAMMAR FEATURES FOR ALCOHOL CLASSIFICATION
F Neutatz, D Schmidt, M Teckenbrock… – suendermann-oeft.de
… In order to apply text classification to real-world applications, speech recognition is re- quired. We used PocketSphinx [9] (v0.7) as speech recognizer and trained two different lan- guage models — one for tuning and one for testing. …

Intelligent intrusion prevention system for households based on system-on-chip computer
MT Rashid, IK Abir, NS Shourove… – … (CCECE), 2016 IEEE …, 2016 – ieeexplore.ieee.org
… name. This process is carried out using a USB webcam’s built-in microphone connected to the Raspberry Pi and Pocketsphinx, a speech recognition software running on the Raspbian operating system of the Raspberry Pi. Until …

Search in Voice Control Systems
AV Savchenko – Search Techniques in Intelligent Classification Systems, 2016 – Springer
… We used the CMU Pocketsphinx 0.8 library with the Russian acoustic model from the ru4sphinx project, 2 in which the grammar contains only stressed vowels. … Here the isolated syllable mode allowed to increase the accuracy to 3–4 % for the Pocketsphinx ASR. …

Joint Behavioural Control of Autonomous Multi-Robot Systems for Lead-Follower Formation to Improve Human-Robot Interaction
MU Nnennaya, EO Akpaibor, AP Borate… – Proceedings of the 9th …, 2016 – dl.acm.org
… However, in this system the UAV is user controlled, which means obstacles are avoided by the human pronounced instructions. 4.2 Speech Recognition Model The process of the speech recognition model employed for the system is the PocketSphinx. …

RoboFEI@ Home 2016 Team Description Paper
AA Masiero, DDR Meneghetti, L Contador… – ais.uni-bonn.de
… Speech recognition is made using the CMU Pocketsphinx [11]. 3.5 Navigation Stack … 11. Huggins-Daines, D., Kumar, M., Chan, A., Black, AW, Ravishankar, M., Rud- nicky, AI: Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices. …

A Portable Automatic PA-TA-KA Syllable Detection System to Derive Biomarkers for Neurological Disorders.
F Tao, L Daudet, C Poellabauer, SL Schneider… – …, 2016 – ecs.utdallas.edu
… These HMMs are built in Pocketsphinx with three states using a left-to-right topology. The GMMs are built with four mixture components. Our acoustic features correspond to Mel Frequency Cep- stral Coefficients (MFCCs), which are extracted with Pocket- sphinx using a 25ms …

N-best list re-ranking using syntactic score: A solution for improving speech recognition accuracy in air traffic control
VN Nguyen, H Holone – Control, Automation and Systems …, 2016 – ieeexplore.ieee.org
… decoder’s confidence score. We integrate the model into the Pocketsphinx speech recognizer and evaluate the model in terms of Word Error Rate (WER) on the well known ATCOSIM and our own ATCSC corpora. The results …

A Power Efficient Scheme for Speech Controlled IoT Applications
VN MILAN – 2016 – researchgate.net
… 7.10 6LoWPAN state communication…………… 28 7.11 Building Blocks of PocketSphinx ASR…………… 29 … 30 7.16 Testing on RPi…………… 30 7.17 PocketSphinx file management…………… 31 …

Reading AssistantTM
Y Won, IJ Levis, H Le, I Lucic, E Simpson – … IN SECOND LANGUAGE … – academia.edu
… Second, an English speech recognition system, which uses PocketSphinx speech recognizer (Walker et al, 2004), is applied to Reading AssistantTM and it helps decide whether the readers, or the language learners, pronounce the given words appropriately. …

Machinilog 2016 Team Description Paper
A Akhter, T Mehmood, H Aslam, B Akram, S Osama – robocup2016.org
… Fig – 4. Gmapping implemented in ROS Page 6. 3.5 Human Robot Interaction HRI is an important aspect of RoboCup@Home where both vocal and visual commands are given to the robots. We used Pocket Sphinx by Carnegie Mellon University [6] for speech recognition. …

Information-theoretic analysis of efficiency of the phonetic encoding–decoding method in automatic speech recognition
VV Savchenko, AV Savchenko – Journal of Communications Technology …, 2016 – Springer
Page 1. ISSN 1064 2269, Journal of Communications Technology and Electronics, 2016, Vol. 61, No. 4, pp. 430–435. © Pleiades Publishing, Inc., 2016. Original Russian Text © VV Savchenko, AV Savchenko, 2016, published in Radiotekhnika i Elektronika, 2016, Vol. 61, No. …

ASR systems performance evaluation using Word Error Rate method
J Rato, N Costa – waset.org
… Pocketsphinx, which is a voice recognition library that can be integrated in systems like Linux, Windows, MacOS, iOS and Android; Sphinxtrain is a training tool of acoustic model; Sphinxbase is a medium library necessary to Pocketsphinx and Sphinxtrain; Sphinx4 is a …

Pronunciation Error Detection for New Language Learners.
S Robertson, C Munteanu, G Penn – INTERSPEECH, 2016 – pdfs.semanticscholar.org
… In these cases, French acoustic models and pho- netic dictionaries are from l’Université du Maine [16] and de- coding is performed with Pocketsphinx [17]. … For this experiment, Pocketsphinx has been patched to remove this safe- guard. 3.1. …

A self configured and hybrid fusion approach for an electric wheelchair control
FB Taher, NB Amor, M Jallouli – Intelligent Systems (IS), 2016 …, 2016 – ieeexplore.ieee.org
… The PocketSphinx plug-in [22] was used for the voice recognition under the Ubuntu 12.04 operating system. … [22] “Pocketsphinx speech recognition plugin,” https://doc- snapshots.qt.io/qt5-dev/qspeechrecognition-pocketsphinx.htm. …

N-best list re-ranking using semantic relatedness and syntactic score: An approach for improving speech recognition accuracy in air traffic control
VN Nguyen, H Holone – Control, Automation and Systems …, 2016 – ieeexplore.ieee.org
… In previous work [2], we proposed a context-dependent class n-gram language model and built a baseline speech recognition system based on the Pocketsphinx recognizer from the CMU Sphinx framework [3]. We integrated syntactic knowledge into post-processing to assist …

NITTE MEENAKSHI INSTITUTE OF TECHNOLOGY
A BALARAMAN – 2016 – kscst.iisc.ernet.in
… Here , we use the pocketsphinx tool. A version of Sphinx that can be used in embedded systems (eg, based on an ARM processor). PocketSphinx is under active development and incorporates features such as fixed-point arithmetic and eficient algorithms for GMM computation. …

Power efficient implementation of MVA-SI on speech controlled IoT systems
NM Vasavada, DP Sametriya… – Recent Trends in …, 2016 – ieeexplore.ieee.org
… On the other hand, Gateway is implemented using Raspberry Pi 2 as shown in (b) with another 802.15.4 xbee radio. It is equipped with CMU Pocketsphinx ASR engine which enables it to recognize the speech utterance provided to Arduino as an input. …

An affectively aware virtual therapist for depression counseling
L Ring, T Bickmore, P Pedrelli – ACM SIGCHI …, 2016 – chi2016mentalhealth.media.mit.edu
… The speech recognition system uses pocket sphinx [8] to create a grammar-based speech recognizer using US-English acoustic model and dictionary. … Journal of counseling psychology, (1991). [8] Huggins-Daines, D. and Kumar, M. Pocketsphinx: A free, real-time continuous …

Implementing Acoustic-Prosodic Entrainment in a Conversational Avatar.
R Levitan, S Benus, RH Gálvez, A Gravano… – …, 2016 – pdfs.semanticscholar.org
… English The English pilot study used PocketSphinx [33] for automatic speech recognition (ASR), and Cepstral 6, a unit- selection-based TTS. … Spanish The Spanish implementation also used Pocket- Sphinx [33] for ASR, and a MaryTTS HMM voice built with a corpus read by a …

Implementing acoustic-prosodic entrainment in a conversational avatar
F Savoretti, M Trnka, A Weise, J Hirschberg – 2016 – researchgate.net
… English The English pilot study used PocketSphinx [33] for automatic speech recognition (ASR), and Cepstral 6, a unit- selection-based TTS. … Spanish The Spanish implementation also used Pocket- Sphinx [33] for ASR, and a MaryTTS HMM voice built with a corpus read by a …

Developing a Speech-Based Interface for Field Data Collection
KC Becker – 2016 – oaktrust.library.tamu.edu
… The augmented interface was created using PocketSphinx speech recognition and Android text to speech to enable hands-free operation of a small scope of commands. … The speech recognition and speech synthesis softwares used (PocketSphinx and Android Speech …

An approach to file manager design for speech interfaces
V Raveendran, M Pauly, N Paul, S Priya… – Current Trends in …, 2016 – ieeexplore.ieee.org
… Ideally, the system should use the offline speech recognition such as is done using Pocketsphinx [13] to support environments where internet is not available or has poor connectivity. VIII. … Available: https://www.python.org/. [13] CMUSphinx, “Pocketsphinx,” [Online]. …

Voice recognition in the LabTablet electronic laboratory notebook
S Ventura, RC Amorim, JR da Silva… – Proceedings of the Ninth …, 2016 – dl.acm.org
… The CMUSphinx library has several decoders available, one of them is PocketSphinx. … [2] D. Huggins-Daines, M. Kumar, A. Chan, AW Black, M. Ravishankar, A. Rudnicky, et al. Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices. …

LeonRobot Team Description Paper. RoboCup@ home 2016
FJR Lera, V Matellán, FM Rico – ais.uni-bonn.de
… Interactuator Pocket Sphinx Sound_play M oveIt! … 8 Software Description – Development framework: ROS 1. Vision: ork, findobject 2. Dialogue: Pocketsphinx 3. BellRecognition: pyaudio 4. Manipulation: MoveIt, self developements. 5. Navigation: Ros stack, self developements. …

Vaidya: A Spoken Dialog System for Health Domain
P Danda, BML Srivastava, M Shrivastava – Proceedings of the 13th …, 2016 – aclweb.org
… In order to train acous- tic models we used the phonetically tied model provided by Pocketsphinx (Huggins-Daines et al., 2006) as the base model and adapted it using rel- … 2006. Pocketsphinx: A free, real-time continuous speech recognition sys- tem for hand-held devices. …

Vaidya: A Spoken Dialog System for Health Domain
PDBML Srivastava, M Shrivastava – 13th International Conference on …, 2016 – aclweb.org
… language models. In order to train acous- tic models we used the phonetically tied model provided by Pocketsphinx (Huggins-Daines et al., 2006) as the base model and adapted it using rel- evant domain-specific data. We used …

Towards Natural Human Control and Navigation of Autonomous Wheelchairs
S Echefu – 2016 – search.proquest.com
… locations within the map. Pocketsphinx, a speech toolkit, is used to interpret the vocal commands. A language model … locations within the map. Pocketsphinx, a speech toolkit, is used to interpret the vocal commands. A language model …

A multi-modal perception based architecture for a non-intrusive domestic assistant robot
C Mollaret, AA Mekonnen, J Pinquier… – … (HRI), 2016 11th …, 2016 – ieeexplore.ieee.org
… Each specific question/request coming from the user can trigger transitions to different states leading to robotic service provi- sion. It uses the CMU PocketSphinx and Google Speech APIs for speech recognition, and the Google TTS API for synthesis. …

UberManufacturing: A Goal-Driven Collaborative Industrial Manufacturing Marketplace
S Mayer, D Plangger, F Michahelles… – Proceedings of the 6th …, 2016 – dl.acm.org
Page 1. 111 Session IV: NETWORK UberManufacturing A Goal-Driven Collaborative Industrial Manufacturing Marketplace Simon Mayer, Dominic Plangger, Florian Michahelles Siemens Corporate Technology Berkeley, USA simonmayer@siemens.com …

Learning task goals interactively with visual demonstrations
J Kirk, A Mininger, J Laird – Biologically Inspired Cognitive Architectures, 2016 – Elsevier
… The agent can detect and manipulate foam blocks of various shapes, colors, and sizes. The human teacher interacts with the agent through a chat window or using Google’s TextToSpeech services for speech production and CMU PocketSphinx for speech recognition. …

Application requirements for Robotic Nursing Assistants in hospital environments
S Cremer, K Doelling… – SPIE …, 2016 – proceedings.spiedigitallibrary.org
… Pocketsphinx from CMU is an offline, lightweight speech-to-text program and has been integrated with ROS [31]. … [31] Ferguson, M.,“Pocketsphinx,” Open Source Robotics Foundation, 2016, http://wiki.ros.org/pocketsphinx (16 April 2016). …

Technological evaluation of gesture and speech interfaces for enabling dismounted soldier-robot dialogue
RK Kattoju, DJ Barber… – SPIE Defense …, 2016 – proceedings.spiedigitallibrary.org
… Advances in speech detection and recognition through the development of high fidelity microphones11 and speech recognition software, such as the Microsoft Speech Platform SDK, Google API, and CMU pocket sphinx, have enabled the detection, recording and classification …

Implementation of Speech Engineering in Android Application using Chess Game
N Sukmana, LC Astari – IT for Society, 2016 – e-journal.president.ac.id
… made. This application named ‘ChessCo’ made from 3 elements which by using Java for Android and method provided by PocketSphinx as Speech Recognition Library and Java Speech Grammar Format (JSGF). ChessCo …

Integration framework for speech processing with live visualization interfaces
D Brodeur, F Grondin, Y Attabi… – Robot and Human …, 2016 – ieeexplore.ieee.org
… interfaced with ROS, the Robot Operating System [10]. ROS4iOS [11] is also an environment integrating speech recognition (PocketSphinx [12]) and speaker identification (WISS [13]). What is missing from these implementations is …

HRTF-based robust least-squares frequency-invariant polynomial beamforming
H Barfuss, M Mueglich… – … (IWAENC), 2016 IEEE …, 2016 – ieeexplore.ieee.org
… As ASR engine, we employed PocketSphinx [15] with a Hidden Markov Model (HMM)-Gaussian Mixture Model (GMM)-based acoustic model which was trained on clean speech from the GRID corpus [16], using MFCC+?+?? features and cepstral mean normaliza- tion. …

User Communities and the” Dark Energy” of Open Innovation
C DeFeo, J Harding, R Wood – European Conference on …, 2016 – search.proquest.com
… Linux). Open source tools, which are community developed by nature, are increasing in number, variety and complexity: for example, Mr. Broadbent made use of the open source voice recognition software, PocketSphinx. His …

Speed vs. accuracy: Designing an optimal asr system for spontaneous non-native speech in a real-time application
AV Ivanov, PL Lange, D Suendermann-Oeft… – Proc. of the IWSDS …, 2016 – oeft.de
… A recent study comparing several popular ASRs such as Kaldi [24], Pocketsphinx [11] and cloud-based APIs from Apple3, Google and AT&T4 in terms of their suitability for use in SDSs, [21] found no particular consensus on the best ASR, but observed that Kaldi performed well …

In situ CAD capture.
A Sankar, SM Seitz – MobileHCI, 2016 – pdfs.semanticscholar.org
… creation. The voice component of our system relies on Pocketsphinx [11], a free and open source speech recognition system for mobile devices. … suede. We leverage the Pocketsphinx [11] library for voice command recognition. …

A Generative Method for Producing Audio
J King, S Li, P Wang – 2016 – stanford.edu
… We tried two open-source method of completing this task, Sphinx, and Merlin, with the original goal of using the better outcome dataset. Pocketsphinx from the CMU Sphinx toolkit generated a time stamped phoneme text file with a given input. …

Human–robot interaction review and challenges on task planning and programming
P Tsarouchi, S Makris… – International Journal of …, 2016 – Taylor & Francis
… The speech recognition development was implemented with MS Speech Recognition libraries API, using a noise cancelling micro- phone. Another successful tool for voice commands recog- nition is the Pocketsphinx (http://www.pocketsphinx.org/). …

Application of Russian Language Phonemics to Generate Macedonian Speech Recognition Model Using Sphinx
R Mingov, E Zdravevski, P Lameski – researchgate.net
… model Page 6. 6 R. Mingov, E.Zdravevski, P.Lameski 3.4 Experimental setup To test our adapted acoustic model we created an Android application using the Pocketsphinx library from the CMU Sphinx toolkit. The application …

Dereverberation using a model for the spatial coherence of decaying reverberant sound fields in rectangular rooms
S Nees, A Schwarz, W Kellermann – Audio Engineering Society …, 2016 – aes.org
… In:IEEESignalProcessingLetters16.9 ( Sept . based on Pocketsphinx [ 24 ] , which was trained on clean 2009 ) , pp . 770 773 . speech ( see [ 9 ] for details ) , was also measured . … In : accepted for J . Acoust . M.Ravishankar , andA.I . Rudnicky . PocketSphinx : A Soc . Am . …

A multi-modal perception based assistive robotic system for the elderly
C Mollaret, AA Mekonnen, F Lerasle, I Ferrané… – Computer Vision and …, 2016 – Elsevier
In this paper, we present a multi-modal perception based framework to realize a non-intrusive domestic assistive robotic system. It is non-intrusive in that it.

Natural user interfaces for human-drone multi-modal interaction
RAS Fernández, JL Sanchez-Lopez… – Unmanned Aircraft …, 2016 – ieeexplore.ieee.org
… Voice processing is done using the ROS package imple- mentation of the Pocketsphinx library. The CMU Pocket Sphinx speech recognizer is the general term to describe a group of speech recognition systems based on hidden Markov models (HMM’s) developed at Carnegie …

Acoustic Echo Control for Humanoid Robots Adel El-Rayyes, Heinrich W. Löllmann, Christian Hofmann, Walter Kellermann
A El-Rayyes – robot-ears.eu
… 1:40 min onward. For the evaluation of the speech recog- nition performance, which is essential for robot audition, the Automated Speech Recognition System (ASR) engine PocketSphinx was used [15]. It employs a Hidden …

Language based shared control of a mobile-manipulator robotic assistant for quadriplegics
C Kaur – 2016 – search.proquest.com
… It is an open source speech recognition toolkit written in Java and released under BSD license. In particular, we use PocketSphinx variant for speed and. 18. … PocketSphinx is a light-weight recognizer library written in C and we use it as a plugin via GStreamer in our python code. …

WSN-Based Keen Sensors and Actuator for Force Administration in Smart Structures
B Mahendrakar, G Deepthi – ijracse.com
… It takes as input the au- ditory communication with the user’s speech that come back from the VAD and sends the resultant text to the Ce. Within the planned platform, the ASR module relies on the Pocket Sphinx speech recognition library. …

On the impact of localization errors on HRTF-based robust least-squares beamforming
H Barfuss, W Kellermann – arXiv preprint arXiv:1603.08740, 2016 – arxiv.org
… As ASR engine, we employed PocketSphinx [6] with a Hidden Markov Model (HMM)-Gaussian Mixture Model (GMM)-based acoustic model trained on clean speech from the GRID corpus [7], using MFCC+?+?? features and cepstral mean normalization. …

Prosodic Cues and Answer Type Detection for the Deception Sub-Challenge
C Montacié, MJ Caraty – Interaction, 2016 – pdfs.semanticscholar.org
… 4.1. Automatic speech transcription The transcription of the corpus was obtained by an acoustic- phonetic decoding system using a loop search. The ASR system was based on the version 0.8 of the Pocketsphinx recognizer library [29]. …

Speech Recognition System for Medical Domain
T Dodiya, S Jain – Citeseer
… It has been built entirely on Javaprogramming language. It is flexible and modular, supporting various types of HMM-based acoustic models, language models, and multiple search strategies [7]. CMU Sphinx toolkit has a number of packages like Pocketsphinx, Sphinxbase, …

Detection of Total Syllables and Canonical Syllables in Infant Vocalizations.
AS Warlaumont, HL Ramsdell-Hudock – INTERSPEECH, 2016 – pdfs.semanticscholar.org
… We used PocketSphinx, which has a mode that provides broad phonetic transcriptions of audio input without performing word recog- nition. The procedure is given at http://cmusphinx. sourceforge.net/wiki/phonemerecognition. …

AUT@ Home 2016 Team Description Paper
E Mehrabi, E Babaians, A Ahmadi, A Sheikhjafari… – sar.aut.ac.ir
… Localization using laser scanner is done using standard AMCL [9]. Visual odometry is more complex and is done using Fovis [10] algorithm, but 1 Available at http://wiki.ros.org/pocketsphinx 2 Available at http://www.microsoft.com/ 3 Available at http://developer.android.com/ …

On-device mobile speech recognition
MK Mustafa – 2016 – irep.ntu.ac.uk
… 50 3.2.4 Pocket-Sphinx On-Device Speech Recognition Systems ….. 51 … the Pocketsphinx by CMU [20].However, there are disadvantages and limitations with regards to both implementations; Page 19. Chapter One – Introduction 5 …

Walking Machine 2016 Team Description
LM Caron, S Otis, J Fortin, A Doyle, J Cousineau… – robocup2016.org
… and AMCL SLAM Gmapping Navigation DWA local_planner Arm navigation Moveit and Kinova API Object recognition Object recognition kitchen Face detection People face_detector Face recognition Cob_people_detection Speech recognition Pocketsphinx Speech synthesis …

A Power Efficient Scheme for Speech Controlled IoT Applications
NM Vasavada, S Belhe – International Journal of Engineering …, 2016 – academia.edu
… Specific Processors, pp. 58-61, June 2011. [15] David Huggins-Daines, Mohit Kumar et al., “Pocketsphinx: A free, Real-time continuous Speech recognition system for hand-held devices”, IEEE ICASSP, pp. 185-188, 2006. [16] Wei …

Taylor series expansion of psychoacoustic corruption function for noise robust speech recognition
B Das, A Panda – Signal Processing (ICSP), 2016 IEEE 13th …, 2016 – ieeexplore.ieee.org
… environments. There are 192 utterances in the core test set. We have used CMU- Sphinx toolkit [14] for training and decoding. We have im- plemented proposed method, Psy-Comp, MCMN and VTS in the pocketsphinx decoder. Test …

Recognizing Voice-Based Requirements to Drive Self-Adaptive Software Systems
X Zhang, Q Yang, J Xing, D Han – Computer Software and …, 2016 – ieeexplore.ieee.org
… Voice recognition technology allows the machine to identify the voice signal. This paper chooses Pocketsphinx as the voice recognition interface [11] because Sphinx is a large vocabulary, speaker independent, real-time continuous voice recognition system. …

COMD: Computation Offloading for Mobile Devices
GV Rashmila, EK Navya – ijets.in
… I collected a data set of pictures containing faces from Google Image. VOICERECOG is an Android port of the speech recognition program PocketSphinx .For simplicity of experiments, I also modified it to use audio files as input. DROIDFISH is an Android port of the chess engine …

Daily-life training and monitoring methodologies for chronic obstructive pulmonary disease patients
G Spina – 2016 – pure.tue.nl
Page 1. Daily-life training and monitoring methodologies for chronic obstructive pulmonary disease patients Spina, G. Published: 02/06/2016 Document Version Publisher’s PDF, also known as Version of Record (includes final page, issue and volume numbers) …

Advanced Spacesuit Informatics Software Design for Power, Avionics and Software Version 2.0
TW Wright – 2016 – ntrs.nasa.gov
… This was implemented using a separate program from Informatics GUI that calls the Pocketsphinx[1616] software library. Pocketsphinx is a lighter weight version of the Sphinx speech recognition engine developed by Carnegie Mellon University. …

Automated Help Aid for Visually Impaired People using Obstacle Detection and GPS Technology: AKSHI
VSS Kaushalya, K Premarathne, HM Shadir, P Krithika… – 2016 – repository.kln.ac.lk
… System AKSHI developed by using Python 3.5.2. Operation System for Raspberry pi 2 model are NOOBS Version 1.9.1, Debian “Jessie”, For Voice Detection and Text –to speech, “Pocketsphinx” , “PyAudio, “Espeak” python Library,MFRC-522 RFID Reader Python Library for …

MMSE estimation of speech power spectral density under speech presence uncertainty for automatic speech recognition
J Liu, Y Zhou, Y Ma, H Liu – Digital Signal Processing (DSP) …, 2016 – ieeexplore.ieee.org
Page 1. MMSE Estimation of Speech Power Spectral Density Under Speech Presence Uncertainty for Automatic Speech Recognition Jingang Liu, Yi Zhou, Yongbao Ma, Hongqing Liu School of Communication and Information …

High-precision telerobot with human-centered variable perspective and scalable gestural interface
K Kruusamäe, M Pryor – Human System Interactions (HSI) …, 2016 – ieeexplore.ieee.org
… Human speech is received by a standard PC microphone and converted to text by CMU Pocketsphinx speech recognizer. For carrying out teleoperated tasks, we utilize a Yaskawa Motoman SIA5D robotic arm. Since the dimensions of SIA5D Fig. …

Prediction-Guided Performance-Energy Trade-off with Continuous Run-Time Adaptation
T Song – 2016 – pdfs.semanticscholar.org
Page 1. PREDICTION-GUIDED PERFORMANCE-ENERGY TRADE-OFF WITH CONTINUOUS RUN-TIME ADAPTATION A Thesis Presented to the Faculty of the Graduate School of Cornell University in Partial Fulfillment of the Requirements for the Degree of Master of Science …

Accent based speech recognition of gujarati language
J Patel – 2016 – ir.inflibnet.ac.in
… ISSN: 0974- 3308 [ 67 ] Patel JK, Patel PN & Virparia PV (Mar 2015). Comparative Study of PocketSphinx and Sphinx with Google’s Speech Recognition API. Fourth National Seminar on Future Trends in Information Technology. Anand Institute of Information Science …

Real-time application for monitoring human daily activity and risk situations in robot-assisted living
M Vieira, DR Faria, U Nunes – Robot 2015: Second Iberian Robotics …, 2016 – Springer
… and y velocity vy. For speech synthesis, we use the sound_play package that given a text input, it will be synthesized into sound output. For speech recognition, we use the pocketsphinx package. This package recognizes a …

Institute of Communications Engineering Staff
M Bossert, R Fischer, W Minker, UC Fiebig… – Journal of Siberian …, 2016 – uni-ulm.de
… 259-265, September 2014 Bibtex. S. Zablotskiy and M. Sidorov Russian Sub-Word Based Speech Recognition Using Pocketsphinx Engine Proceedings of the 11th International Conference on Informatics in Control, Automation and Robotics (ICINCO), Vienna, Austria, Vol. …

ISANA: wearable context-aware indoor assistive navigation with obstacle avoidance for the blind
B Li, JP Munoz, X Rong, J Xiao, Y Tian… – European Conference on …, 2016 – Springer
… Instead, we implemented a Speech-to-Text (STT) module [7] based voice input to help the user interact with the ISANA system. We use the CMU PocketSphinx 3 STT engine to receive the voice commands from the user. The …

Implementing Speech Input and Output
M McTear, Z Callejas, D Griol – The Conversational Interface, 2016 – Springer
… AT&T speech. API. http://?developer.?att.?com/?apis/?speech. CMU PocketSphinx. http://?www.?speech.?cs.?cmu.?edu/?pocketsphinx/?. CMU Sphinx. HMM. http://?cmusphinx.? sourceforge.?net/?. CMU statistical language modeling toolkit. Language modeling. …

Getting Started with Raspberry Pi Zero
R Grimmett – 2016 – books.google.com
… Voice Recognition and Speech – A Voice Activated Robot 123 Communication between the Raspberry Pi Zero and the robot 125 Giving your robot voice commands 129 Using eSpeak to allow your robot to respond with an audible voice 137 Using pocketsphinx to accept your …

Speech only interface approach for personal computing environment
V Raveendran, MR Sanjeev, N Paul… – … (ICETECH), 2016 IEEE …, 2016 – ieeexplore.ieee.org
… For speech recognition, the system supports both online and offline engines. The online engine used is Google’s speech recognition accessed through its API and the offline speech recognition is done using Pocketsphinx [16]. …

Ego-noise reduction using a motor data-guided multichannel dictionary
A Schmidt, A Deleforge… – Intelligent Robots and …, 2016 – ieeexplore.ieee.org
… speech is distorted by the suppression algorithm. Additionally, we measure keyword speech recognition rate (RR), using pocketsphinx [23] in the GRID corpus [21], as defined by the CHiME challenge [24]. A. Proof of concept In a …

Emotive Robotics with I-Zak
H Foresti, G Finch, L Cavalcanti, F Alves, D Lacerda… – ais.uni-bonn.de
… recognition) • Freenect (Kinect drivers) • ROS move base (Positioning and Odometry) • ROS find object 2D (2D / 3D texture recognition) • ROS ppl detection (People detection) • Moveit (ARM Planning) • RTABMap (Mapping and navigation) • Pocketsphinx (Speech recognition …

LucentMaps: 3D printed audiovisual tactile maps for blind and visually impaired people
T Götzelmann – Proceedings of the 18th International ACM …, 2016 – 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 [12] developed for offline speech detection mobile devices. …

Leveraging Multi-modal Analyses and Online Knowledge Base for Video Aboutness Generation
RK Gupta, Y Yinping – International Symposium on Visual Computing, 2016 – Springer
… In: 25th International Conference on Computational Linguistics (COLING) (2014). 6. 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. …

Institute of Information Technology
J Lindner, W Teich, A Linduska, M Mostafa… – Journal of Siberian …, 2016 – uni-ulm.de
… 259-265, September 2014 Bibtex. S. Zablotskiy and M. Sidorov Russian Sub-Word Based Speech Recognition Using Pocketsphinx Engine Proceedings of the 11th International Conference on Informatics in Control, Automation and Robotics (ICINCO), Vienna, Austria, Vol. …

ToBI-Team of Bielefeld The Human-Robot Interaction System for RoboCup@ Home 2016
S Meyer zu Borgsen, T Korthals, S Wachsmuth – 2016 – pub.uni-bielefeld.de
… Recogntition Classificiation Fusion (CLAFU) [12] People Detection strands perception people 12 Behavior Control BonSAI with SCXML Attention Hierachical Robot-Independent Gaze Arbitration 13 Speech Synthesis Mary TTS Speech Recogntition PocketSphinx with context …

Towards Cost-Effective and Performance-Aware Vision Algorithms
D Dai – 2016 – e-collection.library.ethz.ch
Page 1. DISS. ETH NO. 23595 Towards Cost-Effective and Performance-Aware Vision Algorithms A dissertation submitted to ETH ZURICH for the degree of Doctor of Science (Dr. sc. ETH Zürich) presented by Dengxin Dai Master …

Human-in-the-loop control of multi-agent aerial systems
M Orsag, T Haus, D Toli?, A Ivanovic… – Control Conference …, 2016 – ieeexplore.ieee.org
… For each communication channel of the HMI, we have developed a ROS module written in Python or C++. We highlight the usage of OpenCV libraries for GUI widgets, CMU Pocketsphinx toolbox for voice recognition and Pyglet library to produce 3D sounds. …

Development of an intelligent personal assistant for cars
WA Bratt, J Ekdahl – publications.lib.chalmers.se
Page 1. CARAI Development of an intelligent personal assistant for cars Master’s thesis in Algorithms Logic and Languages William Axhav Bratt and Johan Ekdahl Department of Computer Science CHALMERS UNIVERSITY …

Development of a smart glove as a communication tool for people with hearing impairment and speech disorders
S Aguiar, A Erazo, S Romero, E Garcés… – Ecuador Technical …, 2016 – ieeexplore.ieee.org
… Sphinx uses a large quantity of memory: 35 MB for pocket sphinx and 6MB for the Spanish language model, summing a total usage of memory of 41 MB; it has the benefit that it can be implemented in low resource platforms, and for the device, it is the best option due to our lack …

A Robust Speaker Identification Algorithm Based On Atomic Decomposition and Sparse Redundant Dictionary Learning
TJ Bryan Jr – 2016 – search.proquest.com
… 8. Spectrograms are widely used as the front-end processor for Automatic Speech Recognition (ASR). They serve as the engine for generating MFCC features, which is used by the popular open source Sphinx 4 and pocket Sphinx Linux based applications. …

New Dimensions in Testimony Demonstration.
R Artstein, A Gainer, K Georgila, A Leuski… – HLT-NAACL …, 2016 – aclweb.org
… ActiveMQ messaging Acquire Speech PocketSphinx ASR Google Chrome Client NPCEditor VideoPlayer Microphone Google ASR Launcher Logger Figure 2: System architecture: Black lines show the data flow through the system, while gray arrows indicate the control mes …

Using linguistic knowledge for improving automatic speech recognition accuracy in air traffic control
VN Nguyen – 2016 – brage.bibsys.no
… Finally, I build a baseline ASR system based on the Pocketsphinx recognizer from the CMU Sphinx framework, the CMUSphinx US English generic acoustic model and the generic cmudict SPHINX 40 pronunciation dictionary and the three above-mentioned approaches. …

Making Sense of Sensors: End-to-End Algorithms and Infrastructure Design from Wearable-Devices to Data Centers
O Tickoo, R Iyer – 2016 – Springer
Page 1. Tickoo · Iyer M aking Sense of Sensors Making Sense of Sensors End-to-End Algorithms and Infrastructure Design from Wearable-Devices to Data Center — Omesh Tickoo Ravi Iyer Page 2. Making Sense of Sensors End-to-End Algorithms and Infrastructure Design from …

A virtual emotional freedom practitioner to deliver physical and emotional therapy
H Ranjbartabar – 2016 – researchonline.mq.edu.au
… Voice activity detection and speech recognition are performed using PocketSphinx (Huggins-Daines et al., 2006). Furthermore, it currently uses 4 statistically trained speech classifiers to record different aspects of user dialogue meaning (DeVault et al., 2014). …

Dialogue enabling speech-to-text user assistive agent system for hearing-impaired person
S Lee, S Kang, DK Han, H Ko – Medical & biological engineering & …, 2016 – Springer
… IEEE Signal Process Lett 11(2):270–273CrossRef. 16. 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. …

Self-reported symptoms of depression and PTSD are associated with reduced vowel space in screening interviews
S Scherer, GM Lucas, J Gratch… – IEEE Transactions …, 2016 – ieeexplore.ieee.org
… For verbal processing, the platform integrates modules to recognize spoken words (eg, using CMU’s PocketSphinx recognizer [46]), analyze the spoken responses [47] and decide on the proper response or question using the Flores dialogue manager [48]. …

Raspberry Pi Networking Cookbook
R Golden – 2016 – books.google.com
Page 1. º – º º Quick answers to common problems Raspberry Pi Networking Cookbook Second Edition Connect your Raspberry Pi to the world with this essential collection of recipes for basic administration and common network …

Building a Virtual Assistant for Raspberry Pi
T Pant – 2016 – Springer
… Pi). The advantage of using Pocketsphinx is that the speech recognition is performed offline, which means you don’t need an active Internet connection. … engine. It does not need an active Internet connection, like Pocketsphinx. …

Vocal combo android application
S Mathukumalli – 2016 – krex.k-state.edu
Page 1. VOCAL COMBO ANDROID APPLICATION by SRAVYA MATHUKUMALLI B.Tech., Andhra University, 2014 A REPORT submitted in partial fulfillment of the requirements for the degree MASTER OF SCIENCE Department …

Listening through a Vibration Motor
N Roy, R Roy Choudhury – Proceedings of the 14th Annual International …, 2016 – dl.acm.org
Page 1. Listening through a Vibration Motor Nirupam Roy, Romit Roy Choudhury University of Illinois at Urbana-Champaign ABSTRACT This paper demonstrates the feasibility of using the vibra- tion motor in mobile devices as a sound sensor, almost like a microphone. …

Supporting Collaboration Between Co-Located Devices for Context Monitoring in a Mobile Environment
K Alanezi – 2016 – search.proquest.com
… A speech recognition application that is based on PocketSphinx [51] to perform speech recognition from a dictionary represents a parallel task. This task is computation-intensive, making it a good candidate for collaboration. …

Advanced Technologies for Human-Computer Interfaces in Mixed Reality
M Marchesi – 2016 – amsdottorato.unibo.it
Page 1. Alma Mater Studiorum Alma Mater Studiorum – Università di Bologna Università di Bologna DOTTORATO DI RICERCA IN Ingegneria Elettronica, delle Telecomunicazioni e Tecnologie dell’Informazione Ciclo XXVIII …

Baymax: Qos awareness and increased utilization for non-preemptive accelerators in warehouse scale computers
Q Chen, H Yang, J Mars, L Tang – ACM SIGPLAN Notices, 2016 – dl.acm.org
Page 1. Baymax: QoS Awareness and Increased Utilization for Non-Preemptive Accelerators in Warehouse Scale Computers Quan Chen?†1 Hailong Yang?‡1 Jason Mars? Lingjia Tang? ?Clarity Lab, University of Michigan …

Sirius Implications for Future Warehouse-Scale Computers
J Hauswald, MA Laurenzano, Y Zhang, C Li… – IEEE Micro, 2016 – ieeexplore.ieee.org
Page 1. ….. SIRIUS IMPLICATIONS FOR FUTURE WAREHOUSE-SCALE COMPUTERS …

Adapting Spoken Dialog Systems Towards Domains and Users
M Sun – 2016 – lti.cs.cmu.edu
Page 1. Adapting Spoken Dialog Systems Towards Domains and Users Ming Sun CMU-LTI-16-006 Language Technologies Institute School of Computer Science Carnegie Mellon University 5000 Forbes Ave., Pittsburgh, PA 15213 www.lti.cs.cmu.edu …

An Intelligent Robot and Augmented Reality Instruction System
CM Reardon – 2016 – trace.tennessee.edu
Page 1. University of Tennessee, Knoxville Trace: Tennessee Research and Creative Exchange Doctoral Dissertations Graduate School 5-2016 An Intelligent Robot and Augmented Reality Instruction System Christopher M …

Towards Energy-Efficient Mobile Sensing: Architectures and Frameworks for Heterogeneous Sensing and Computing
S Fan – 2016 – search.proquest.com
Towards Energy-Efficient Mobile Sensing: Architectures and Frameworks for Heterogeneous Sensing and Computing. Abstract. Modern sensing apps require continuous and intense computation on data streams. Unfortunately …

Designing future warehouse-scale computers for sirius, an end-to-end voice and vision personal assistant
J Hauswald, MA Laurenzano, Y Zhang… – ACM Transactions on …, 2016 – dl.acm.org
Page 1. 2 Designing Future Warehouse-Scale Computers for Sirius, an End-to-End Voice and Vision Personal Assistant JOHANN HAUSWALD, MICHAEL A. LAURENZANO, YUNQI ZHANG, HAILONG YANG, YIPING KANG, CHENG …