PocketSphinx 2015


Notes:

  • Video to Text (V2T)

Resources:

Wikipedia:

See also:

100 Best CMUSphinx VideosCMUSphinx 2012 | CMUSphinx 2013 | CMUSphinx 2014CMUSphinx 2015


Evaluation of a speech recognition system Pocketsphinx R Hjulström – 2015 – diva-portal.org Abstract Speech recognition is the process of translating an audio signal into text using a computer program. The technique is today widely used in a large variety of areas. Pocketsphinx which is an open source speech recognition system is one of the more … Related articles All 2 versions

A Speech-Based Mobile App for Restaurant Order Recognition and Low-Burden Diet Tracking X Huang, E Agu – International Conference on Smart Health, 2015 – Springer … Since we wanted to leverage these customizations, we adopted Pocketsphinx [6], a mobile implementation of CMU Sphinx for our work. … Without our proposed enhancements, Pocketsphinx had low speech recognition accuracy, with an error rate of about 65.5 % (Fig. … Cited by 1 Related articles All 3 versions

The Cohort and Speechify Libraries for Rapid Construction of Speech Enabled Applications for Android T Kasturi, H Jin, A Pappu, S Lee, B Harrison… – 16th Annual Meeting of …, 2015 – aclweb.org … up with a poor user experience because of inconsistencies in implementing features like: • choice of speech API-Speechify wraps several publicly available speech recogni- tion and speech synthesis APIs, includ- ing the Google Android5 and Pocketsphinx (Huggins-Daines et … Related articles All 9 versions

Multilingual Voice Control for Endoscopic Procedures S Afonso, I Laranjo, J Braga, V Alves… – Internet of Things. User- …, 2015 – Springer … The developed software module was integrated with the MIVbox device, a device for the acquisition, processing and storage of the endoscopic results It uses libraries developed by the PocketSphinx project to recognize a small amount of com- mands. … Related articles

Automatic speech recognition An evaluation of Google Speech M Stenman – 2015 – diva-portal.org … use in robotics. An evaluation of Google Speech, using Google’s speech API, in regards to word error rate and translation speed, as well as a comparison between Google Speech and Pocketsphinx is made. The results show … Related articles All 2 versions

Inventory Counting D Tancharoen, W Thanhikam – dev02.dbpia.co.kr … The system was developed PocketSphinx on an android smart phone result, speech recognition technology the speed of inventory counting. … We implemented the system PocketSphinx [4]. This is an which supports the library for Android system. …

Evaluating spoken dialogue processing for time-offset interaction D Traum, K Georgila, R Artstein, A Leuski – Proceedings of SIGDIAL, 2015 – aclweb.org … For example, the user can select between PocketSphinx and Google ASR engines by checking the appropriate buttons in the Launcher interface. Figure 1 shows the over- all system architecture. We show the data flow through the system as black lines. … Cited by 5 Related articles All 16 versions

Open source german distant speech recognition: Corpus and acoustic model S Radeck-Arneth, B Milde, A Lange, E Gouvêa… – … Conference on Text, …, 2015 – Springer … recordings. We show recognition results with the open source toolkit Kaldi (20.5% WER) and PocketSphinx (39.6% WER) and make a complete open source solution for German distant speech recognition possible. Keywords … Cited by 3 Related articles All 6 versions

Content based Multimedia Retrieval using Automatic Speech Recognition N Purswani, R Ramrakhyani… – International Journal of …, 2015 – search.proquest.com … General Terms. Fast retrieval, content based retrieval, repository of videos. Keywords. CMU Sphinx, PocketSphinx, ffmpeg. 1. INTRODUCTION. In this paper, first the problem has been defined and then an approach has been designed to tackle the problem. … All 5 versions

BahiaRT @Home 2015 Team Description Paper JR de Souza, D Guimaraes, F Pimentel, F Sapucaia… – acso.uneb.br … For recognition, we use the CMU PocketSphinx[15], which features greater flexibility for adaptation and personalization, allowing to adapt the dictionary and acoustic models to the problem of context. … Speech recognition: PocketSphinx library; Boost library. … Related articles All 3 versions

Continuous speech recognizer for low-end embedded devices A Milinkovi?, S Milinkovi? – 2015 4th Mediterranean Conference …, 2015 – ieeexplore.ieee.org … Among them are Sphinx 2 [13], and Sphinx 3 [14], decoders for speech recognition written in C, Sphinx 4 [15], a modified recognizer written in Java, and Pocketsphinx [16], a lightweight recognizer library written in C. … System T1 executed Pocketsphinx and T2 executed our code. … Related articles

Combining different speech recognizers by using CART classifier T Rasymas, V Rudžionis – … AIEEE), 2015 IEEE 3rd Workshop on …, 2015 – ieeexplore.ieee.org … To develop speech recognizers, PocketSphinx toolkit was used. PocketSphinx is a lightweight speech recognition engine, specifically tuned for handheld and mobile devices, though it works equally well on the desktop computers and notebooks. … Related articles

Evaluation of methods to combine different speech recognizers T Rasymas, V Rudžionis – Computer Science and Information …, 2015 – ieeexplore.ieee.org … 1 Downloaded from https://github.com/mondhs/lt-pocketsphinx- tutorial/tree/master/impl/models/ hmm/lt.cd_cont_200 2 Downloaded from http://sourceforge.net/projects/cmusphinx/files/ Acoustic%20and%20Language%20Models/Russian%20Voxforge 3 Downloaded from http … Cited by 1 Related articles All 4 versions

Speech Scenario Adaptation and Discourse Topic Recognition on Mobile Smart Terminal M Huang, X Li, S Wu, Y Chen – 2015 International Conference …, 2015 – ieeexplore.ieee.org … In order to prove the effectiveness, we design and implement a continuous Chinese speech recognition system on a mobile smart terminal based on PocketSphinx engine. … PocketSphinx has default acoustic models hub4wsj_scc_8k (English) and tdt_sc_8k (Chinese). … Related articles All 2 versions

UChile HomeBreakers 2015 Team Description Paper L Mart?nez, M Pavez, G Olave, M Correa, L Sánchez… – robocup2015.oss-cn-shenzhen. … … Incorporation of HARK library for sound preprocessing before performing recognition, with the PocketSphinx module, in order to locate the voice source, therefore providing robustness against noise. … 11. Method to implement GStreamer with Pocketsphinx. … Cited by 1 Related articles All 2 versions

Easy Deployment of Spoken Dialogue Technology on Smartwatches for Mental Healthcare A Prange, D Sonntag – … Symposium on Pervasive Computing Paradigms for …, 2015 – Springer … models and grammars (for mental healthcare applications). We tested the PocketSphinx version, a lightweight speech recognition engine, specifically tuned for handheld and mobile devices. Results were very promising, and the … Related articles

Design of a home multi-robot system for the elderly and disabled P Benavidez, M Kumar, S Agaian… – System of Systems …, 2015 – ieeexplore.ieee.org … Task Software Additional Information Speech recognition pocketsphinx ros kinect ROS Pocketsphinx Tutorial [23], Pi Robot Tutorial [24] Processing depth images ROS Opencv2 OpenCV API [25, 26] Processing depth point clouds pcl-ros PCL API [27] … Cited by 1 Related articles All 3 versions

Lithuanian Digits Recognition by Using Hybrid Approach by Combining Lithuanian Google Recognizer and Some Foreign Language Recognizers T Rasymas, V Rudžionis – International Conference on Information and …, 2015 – Springer … To develop speech recognizers, PocketSphinx toolkit was used. PocketSphinx is a lightweight speech recognition engine, specifically tuned for handheld and mobile devices, though it works equally well on the desktop computers and notebooks. … Cited by 1 Related articles

An open platform of auditory perception for home service robots HM Do, W Sheng, M Liu – … and Systems (IROS), 2015 IEEE/RSJ …, 2015 – ieeexplore.ieee.org … Speech recognition has been well researched and there are even open source software available, such as Pocketsphinx [5] and Julius [6]. However, sound event recognition is still challenging due to the diversity of the sounds associated with the same event. … Cited by 1 Related articles

Prediction-guided performance-energy trade-off for interactive applications D Lo, T Song, GE Suh – … of the 48th International Symposium on …, 2015 – dl.acm.org Page 1. Prediction-Guided Performance-Energy Trade-off for Interactive Applications Daniel Lo, Taejoon Song, and G. Edward Suh Cornell University Ithaca, NY, USA {dl575, ts693, gs272}@cornell.edu ABSTRACT Many modern … Cited by 3 Related articles All 3 versions

Portable neurological disease assessment using temporal analysis of speech N Yadav, C Poellabauer, L Daudet, T Collins… – Proceedings of the 6th …, 2015 – dl.acm.org … nature. In particular, the lightweight Pocketsphinx implementation was selected to be ported to the mobile devices. … analysis. The output from running Pocketsphinx on the mobile devices was identical to the output generated on a server. … Related articles All 2 versions

Watermelon Project-Team Description Paper RoCKIn @home 2015 FJR Lera, F Casado, V Matellán, F Mart?n – rockincompetition.eu … However, we have changed our Automatic Speech Recognition software. We have changed the PocketSphinx solution to Sphinx solution due to its good performance in offline recognition tests. Now, our dialogue system is made up by three components. … Related articles All 2 versions

Tag cloud visualisation of verbal discussions following speech-to-text R Visser, BOK Intelligentie – 2015 – esc.fnwi.uva.nl … By using CMU Pocketsphinx speech recogniser with American English language and acoustic models, an average word accuracy of approximately 60% and 52% was obtained for respectively native and non-native American speakers. … 11 3.1.1 CMU Pocketsphinx . . . . . … Related articles

Team Homer @UniKoblenz—Approaches and Contributions to the RoboCup @Home Competition V Seib, S Manthe, R Memmesheimer, F Polster… – Robot Soccer World …, 2015 – Springer … Speech Recognition. For speech recognition we integrated and evaluated different approaches. In the past we used PocketSphinx 5 for speech recognition. … 5 Speech recognition system PocketSphinx: http://www.speech.cs.cmu.edu/pocketsphinx/. 6 … Related articles

A language model based approach towards large scale and lightweight language identification systems BML Srivastava, HK Vydana, AK Vuppala… – arXiv preprint arXiv: …, 2015 – arxiv.org … being developed. We employ PocketSphinx[8] as the front-end phone recognizer which uses HMM-based phone decoder from speech signal. A phonetically tied-mixture (PTM) model is used for efficient decoding. It contains … Related articles All 3 versions

An assistive navigation framework for the visually impaired J Xiao, SL Joseph, X Zhang, B Li, X Li… – IEEE Transactions on …, 2015 – ieeexplore.ieee.org … The software is implemented under the robotics oper- ating system [24] in Ubuntu. We use the CMU PocketSphinx speech recognition system [25] as the speech recognition tool and sound_play in the audio_common package [26] to deliver text-to-speech commands. … Cited by 5 Related articles

Applying human computer interaction to individual security using mobile application S Save, M Gala, S Patil… – … , Information & Computing …, 2015 – ieeexplore.ieee.org … The implementation for voice based activation can be tried using PocketSphinx for Android. PocketSphinx is a lightweight speech recognition engine, specifically tuned for handheld and mobile devices, though it works equally well on the desktop. … Related articles All 2 versions

An Episodic Long-Term Memory for Robots: The Bender Case ML Sánchez, M Correa, L Martínez… – Robot Soccer World …, 2015 – Springer … Some episodic information that Bender can acquire is requested through voice commands, for this purpose two open source libraries are used: pocketsphinx for speech recognition [26], and festival for speech synthesis [27]. … Speech recognition system pocketsphinx. … Related articles All 3 versions

Creating a virtual neighbor C Corbin, F Morbini, D Traum – Natural Language Dialog Systems and …, 2015 – Springer … Figure 19.1 shows a screenshot of the Miki character. Users can talk to her face to face, using any toolkit-compatible speech recognizer (Morbini et al. 2013) (we tested with apple dictation and pocketsphinx). Additionally, it is possible to text miki using a chat interface. … Cited by 4 Related articles All 7 versions

Automated Speech Recognition Technology for Dialogue Interaction with Non-Native Interlocutors AV Ivanov, V Ramanarayanan… – 16th Annual Meeting of …, 2015 – aclweb.org … In a recent study compar- ing several popular ASRs such as Kaldi (Povey et al., 2011), Pocketsphinx (Huggins-Daines et al., 2006) and cloud-based APIs from Apple1, Google2 and AT&T3 in terms of their suitability for use in SDSs, In (Morbini et al., 2013) there was found no … Cited by 3 Related articles All 17 versions

Search system for an audio archive A Dudziec – 2015 – diva-portal.org … engine. Pocketsphinx According to CMU, Pocketsphinx is a lightweight version of their speech recogni- tion engine, written in C, that gives as accurate results as Sphinx4, but faster at the expense of less flexibility. First tests … Related articles

Noise Suppression In Automatic Speech Recognition Using Hidden Markov Model S Tola, L Nikolla – system, 2015 – jmest.org … [2] Huggins-Daines D., M. Kumar, A. Chan, A. Black, M. Ravishekar and A. Rudnicky, 2006. Pocketsphinx: A free, real time continuous speech recognition system for hand-held devices, in Proceedings of ICASSP. [3] Joshi, Siddhant, C. and Dr. AN Cheeran, 2014. … Related articles

Statistical Testing Of Segment Homogeneity In Classification Of Piecewise–Regular Objects AV Savchenko, NS Belova – International Journal of Applied …, 2015 – degruyter.com Page 1. Int. J. Appl. Math. Comput. Sci., 2015, Vol. 25, No. 4, 915–925 DOI: 10.1515/amcs-2015- 0065 STATISTICAL TESTING OF SEGMENT HOMOGENEITY IN CLASSIFICATION OF PIECEWISE–REGULAR OBJECTS ANDREY V. SAVCHENKO a,? , NATALYA S. BELOVA b … Cited by 6 Related articles All 10 versions

HRTF-based robust least-squares frequency-invariant beamforming H Barfuss, C Huemmer, G Lamani… – … of Signal Processing …, 2015 – ieeexplore.ieee.org … The ASR engine PocketSphinx [9] was used Page 4. … 2, pp. 497– 500, 1979. [9] D. Huggins-Daines, M. Kumar, A. Chan, A. Black, M. Rav- ishankar, and A. Rudnicky, “Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices,” in IEEE Int. Conf. … Cited by 3 Related articles All 2 versions

A Study of Automatic Speech Recognition in Noisy Classroom Environments for Automated Dialog Analysis N Blanchard, M Brady, AM Olney, M Glaus… – … Conference on Artificial …, 2015 – Springer … classroom contexts. Morbini et al. [14] recently reviewed some of today’s freely available ASR engines. They tested five ASR engines including Google Speech, Pocketsphinx, Apple, AT&T Watson, and Otosense-Kaldi. Tests were … Cited by 3 Related articles All 2 versions

Comparison of Forced-Alignment Speech Recognition and Humans for Generating Reference VAD I Kraljevski, ZH Tan, MP Bissiri – Sixteenth Annual Conference of …, 2015 – researchgate.net … 14]. 2.2. ASR system For the forced-alignment segmentation and VAD labeling, the Sphinx/pocketsphinx [15] framework and its Gstreamer [16] realization were employed without using the VAD functionality. Acoustic modeling … Cited by 1 Related articles All 4 versions

The demura.net 2016 Team Description K Demura – demura.net … avoidance, respectively. 3.3 Speech Recognition and Speech Synthesis The authors developed a hybrid speech recognition system. The Pocketsphinx is used for the recognition of the keyword, ie, the robot name. After the … Related articles All 3 versions

Language Model Adaptation For Transcription Of Banking Protocols I Kraljevski, D Hirschfeld – researchgate.net … 3 Speech Recognition System The recognition framework used for acoustic modeling and recognition is Sphinx/pocketsphinx [11]. … “Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices.” Acoustics, Speech and Signal Processing, 2006. … Related articles All 2 versions

Ontology-Based Voice Annotation of Data Streams in Vehicles I Sosunova, A Zaslavsky, T Anagnostopoulos… – Conference on Smart …, 2015 – Springer … After a preliminary analysis 4 open source speech recognition systems have been selected for further study, testing and choosing the most suitable for the current task: CMU Sphinx (Pocketsphinx) [22], Julius [23], Kaldi [24], Simon [25]. … Related articles All 3 versions

ChibiFace: A sensor-rich Android tablet-based interface for industrial robotics B Nurimbetov, A Saudabayev… – 2015 IEEE/SICE …, 2015 – ieeexplore.ieee.org … Verbal communication is an essential aspect of effective human-robot interaction [10, 11]. We implemented voice based industrial robot control by applying PocketSphinx speech recognition library [27] and mapping a set of words to the corresponding set of instructions. … Cited by 2 Related articles

A SLAM Based Semantic Indoor Navigation System for Visually Impaired Users X Zhang, B Li, SL Joseph, J Xiao, Y Sun… – Systems, Man, and …, 2015 – ieeexplore.ieee.org … to extract room numbers. We use the CMU pocketsphinx-speech- recognition [21] as the speech recognition tool, and use the sound_play in audio_common package [22] to deliver text to speech commands. In the experiment … Cited by 1 Related articles

Energy-Efficient Data Processing Through Data Sparsing with Artifacts P Graubner, P Heckmann, B Freisleben – International Conference on …, 2015 – Springer … For recognition, we used Pocketsphinx [ 25 ], an open source speech recognition engine that recognizes words with an expected error of 20 %. Pocketsphinx needs a phase of 3 seconds for calibration, which cannot be used for data sparsing. … Related articles

Qualitative investigation of the display of speech recognition results for communication with deaf people A Piquard-Kipffer, O Mella, J Miranda, D Jouvet… – 6th Workshop on …, 2015 – hal.inria.fr … syllables are correct. Furthermore, the speech recognition engine is built from the PocketSphinx tool [8] and uses as acoustic models, context-dependent phone HMM models with 3 states and 64 Gaussians per state. The acoustic … Cited by 1 Related articles All 10 versions

Android-based intelligent mobile robot for indoor healthcare Y Ma, D Xiao, R Li, R Hang, S Zhao… – … Conference on E- …, 2015 – ieeexplore.ieee.org … utilized. The offline speech recognition based on Android adopts PocketSphinx embedded speech recognition engine, which realizes the accurate recog- nition of speech input of speaker-independent speech within a small scope. … Related articles

Multifunctional user interface implementation details and evaluation J Gelšvartas, R Simutis… – Methods and Models in …, 2015 – ieeexplore.ieee.org … The pseudo code of the MindWave device driver is provided in Fig. 2. We are using open-source package Pocketsphinx for speech recognition [12]. The Speech recognition driver uses the default microphone of the computer to continuously record defined length sound buffers. … Related articles

A New Approach to the Interpretation of Voice Commands AH Kronbauer, V Costa – Proceedings of the 21st Brazilian Symposium …, 2015 – dl.acm.org … Figura 1. Componentes da Infraestrutura. 3 Disponível em: http://support.apple.com/ en-us/ht5449. 4 Disponível em: http://www.speech.cs.cmu.edu/pocketsphinx/. 5 Disponível em: http://sourceforge.net/projects/kaldi/. 218 Page 3. … Related articles

A Blind Navigation System Using RFID for Indoor Environments K Tandon, T Pande, M Adil, G Dubey, A Kumar – ijcsonline.com … 20, no. 3, pp. 267–314, 2005. [5] D. Huggins-Daines, M. Kumar, A. Chan, AW Black, M. Ravishankar, and AI Rudnicky, “PocketSphinx: A free, real-time continuous speech recognition system for hand-held devices,” in Proceedings of ICASSP, Toulouse, France, May 2006. Related articles

Assisting blind people to avoid obstacles: An wearable obstacle stereo feedback system based on 3D detection B Li, X Zhang, JP Muñoz, J Xiao… – … on Robotics and …, 2015 – ieeexplore.ieee.org … We use the CMU pocketsphinx-speech-recognition [14] as the speech recognition tool, and use the sound_play in audio_common package [15] to deliver text to speech commands. The obstacle avoidance is combining with our navigation system [17]. … Cited by 1 Related articles All 2 versions

An integrated system for voice command recognition and emergency detection based on audio signals E Principi, S Squartini, R Bonfigli, G Ferroni… – Expert Systems with …, 2015 – Elsevier … The acoustic environment is constantly monitored to detect speech signals by means of a Voice Activity Detector (VAD), and a speech recogniser based on PocketSphinx (Huggins-Daines et al., 2006) captures distress calls and voice commands. … Cited by 8 Related articles All 5 versions

Transcription of Telugu TV news using ASR MR Reddy, P Laxminarayana… – Advances in …, 2015 – ieeexplore.ieee.org … CMU SPHINX train tools are used to generate the parameters of the Acoustic characteristics/ models; means, variances, transition probabilities and mixture weights. Continuous and semi-continuous models are generated for sphinx-3 and pocketsphinx decoders respectively. … Related articles

On the importance of subtext in recommender systems P Grasch, A Felfernig – icom, 2015 – degruyter.com … SPEECHREC uses a version of the Simon 2 2 speech recognition system that was modified to include the arousal score calculated by openEAR as described in Section 3.2.2. Simon in turn uses the PocketSphinx decoder of the CMU SPHINX speech recognition framework 3 3 … Cited by 2 Related articles All 4 versions

Human assisted positioning using textual signs B Han, F Qian, MR Ra – Proceedings of the 16th International Workshop …, 2015 – dl.acm.org Page 1. Human Assisted Positioning Using Textual Signs Bo Han? Feng Qian? Moo-Ryong Ra? AT&T Labs – Research, Bedminster, New Jersey, USA {bohan,fengqian,mra}@research.att.com ABSTRACT Location information … Cited by 4 Related articles All 10 versions

Speech Recognition Using Discrete Hidden Markov Model S Suganya, CS Joice – Middle-East Journal of Scientific Research, 2015 – idosi.org … A. Black, M. Ravishekar and A. Rudnicky, DE1 FPGA starter kit and this also can be used to convert 2006. Pocketsphinx: A free, real-time the speech to text. The research work can be extended to continuous speech recognition system for … All 2 versions

[BOOK] Learning Robotics Using Python L Joseph – 2015 – books.google.com … Setting up eSpeak and Festival in Ubuntu 14.04.2 201 Working with speech recognition and synthesis in Windows using Python 202 Installation of the Speech SDK 203 Working with Speech recognition in ROS Indigo and Python 204 Installation of the pocketsphinx package in … Cited by 2 Related articles

Phase-optimized k-svd for signal extraction from underdetermined multichannel sparse mixtures A Deleforge, W Kellermann – 2015 IEEE International …, 2015 – ieeexplore.ieee.org … source separation and localization. 1The speech recognizer pocketsphinx [25] was used to recognize the key- words in the GRID corpus [21], as defined by the CHiME challenge [26]. 358 Page 5. 5. REFERENCES [1] MN Schmidt … Cited by 3 Related articles All 7 versions

i-Vectors in speech processing applications: a survey P Verma, PK Das – International Journal of Speech Technology, 2015 – Springer … http://www.isca-speech.org/archive/interspeech_2013/i13_2282.html. Huggins-Daines, D., Kumar, M., Chan, A., Black, A., Ravishankar, M., & Rudnicky, A. (2006), Pocketsphinx: A free, real-time continuous speech recognition system for hand-held devices. … Related articles All 3 versions

SmartTactMaps: a smartphone-based approach to support blind persons in exploring tactile maps T Götzelmann, K Winkler – Proceedings of the 8th ACM International …, 2015 – dl.acm.org … Answers for responses can either be spatial (relative to the finger position) or non-spatial (eg, general information about the map). By using the free PocketSphinx voice recognition library [13] we processed voice instructions and transformed them into commands. … Cited by 2 Related articles

A multimodal adaptive dialogue manager for depressive and anxiety disorder screening: a Wizard-of-Oz experiment K Tsiakas, L Watts, C Lutterodt… – Proceedings of the 8th …, 2015 – dl.acm.org … The system was implemented in Python. For the face detection, we use the opencv2 library and for speech recognition, we use the Pocketsphinx package for Python. We modified the recognizer in order to capture the user’s voice when the recognizer detects speech. … Related articles All 3 versions

Psychoacoustic model compensation for robust continuous speech recognition in additive noise B Das, A Panda – 2015 IEEE International Symposium on …, 2015 – ieeexplore.ieee.org … We have used CMU-Sphinx toolkit [17] for training and decoding. We have implemented VTS, Psy-Comp, MCMN and MCMVN in the pocketsphinx decoder. Test utterances were corrupted with Babble, F-16 and Hfchannel noise taken from NOISEX- 92 database. … Related articles All 3 versions

Being aware of the world: Toward using social media to support the blind with navigation SL Joseph, J Xiao, X Zhang, B Chawda… – … on Human-Machine …, 2015 – ieeexplore.ieee.org … extract room numbers. We use the Carnegie Mellon University pocketsphinx-speech- recognition [18] for speech recognition, and sound_play in the audio_common package [19] to deliver text to speech commands. A. Event … Cited by 5 Related articles All 2 versions

An improved switch speech enhancement algorithm for automatic speech recognition Y Ma, Y Zhou, J Liu, J Xia, H Liu – … and Communications (ICCC) …, 2015 – ieeexplore.ieee.org Page 1. An Improved Switch Speech Enhancement Algorithm for Automatic Speech Recognition Yongbao Ma, Yi Zhou, Jingang Liu, Jie Xia, and Hongqing Liu School of Communication and Information Engineering Chongqing … Related articles

[BOOK] Raspberry Pi Robotic Blueprints R Grimmett – 2015 – books.google.com … the RC Car using Raspberry Pi in Python 12 Accessing the RC Car remotely 16 Summary 22 Chapter 2: Adding Raspberry Pi to a Humanoid Robot 23 Giving your robot voice commands 34 Using eSpeak to allow your robot to respond in voice 42 Using pocketsphinx to accept … All 2 versions

[BOOK] Raspberry Pi Robotics Projects R Grimmett – 2015 – books.google.com … Table of Contents Chapter 3: Providing Speech Input and Output 61 Hooking up the hardware to make and input sound 63 Using Espeak to allow our projects to respond in a robotic voice 71 Using PocketSphinx to accept your voice commands 73 Interpreting commands and … Cited by 3 Related articles All 6 versions

SocialRobot: An interactive mobile robot for elderly home care D Portugal, P Alvito, J Dias, G Samaras… – 2015 IEEE/SICE …, 2015 – ieeexplore.ieee.org … word spotting (perception): recognition of a limited set of simple words through speech. Based on the pocketsphinx ROS wrapper. • navigate to (navigation): indoor navigation to a specific place/room in the environment, leveraging the ROS naviga- tion stack. … Cited by 1 Related articles

Robot programming by demonstration with situated spatial language understanding M Forbes, RPN Rao, L Zettlemoyer… – … on Robotics and …, 2015 – ieeexplore.ieee.org … 2) Software: Our software is written within the ROS (Robot Operating System) framework and is open-source.1 It is built as an extension to the open-source PR2 Program- ming by Demonstration package [7]. We use PocketSphinx [13] for speech recognition. … Cited by 6 Related articles All 5 versions

A Voice User Interface for Human-Robot Interaction on a Service Robot M Simonic – ra.cs.uni-tuebingen.de Page 1. UNIVERSITY OF TÜBINGEN Wilhelm Schickard Institute for Informatics The Chair of Cognitive Systems Bachelor Thesis A Voice User Interface for Human-Robot Interaction on a Service Robot Mihael Simonic Supervisors: Prof. Dr. rer. nat. … Related articles All 3 versions

Perceiving user’s intention-for-interaction: A probabilistic multimodal data fusion scheme C Mollaret, AA Mekonnen, I Ferrané… – … on Multimedia and …, 2015 – ieeexplore.ieee.org … Since signal energy is affected by the noise in the environment, the implementa- tion in PocketSphinx does an initial calibration stage so as to best separate signal from stationary noise using a statistical- based noise removal method. … Related articles All 7 versions

On the development of a service robot for social interaction with the elderly D Portugal, P Trindade, E Christodoulou… – … for Active and …, 2015 – ieeexplore.ieee.org … However, it is limited to the two colinear microphones incorporated in the Asus Xtion PRO Live sensor. In order to recognize speech, we make use of PocketSphinx, a lightweight speaker-independent speech recognition engine. … Related articles All 4 versions

Spoke: A framework for building speech-enabled websites P Saylor – 2015 – groups.csail.mit.edu … 22 2.1.1 WAMI ……………23 2.1.2 CMU PocketSphinx…………… 23 … to a backend server. 2.1.2 CMU PocketSphinx … Cited by 3 Related articles All 2 versions

Panorama: A Framework to Support Collaborative Context Monitoring on Co-located Mobile Devices K Alanezi, X Zhou, L Chen, S Mishra – International Conference on Mobile …, 2015 – Springer … A speech recognition application that is based on PocketSphinx [15] to perform speech recognition from a dictionary represents a parallel task. This task is computation-intensive, making it a good candidate for collaboration. … In: MobiSys (2010). 15. CMU PocketSphinx. 16. … Related articles

Video to Text (V2T) in Wide Area Motion Imagery G Chen, D Shen, H Ling – 2015 – DTIC Document Page 1. VIDEO TO TEXT (V2T) IN WIDE AREA MOTION IMAGERY INTELLIGENT FUSION TECHNOLOGY, INC. SEPTEMBER 2015 FINAL TECHNICAL REPORT APPROVED FOR PUBLIC RELEASE; DISTRIBUTION UNLIMITED STINFO COPY … Related articles

Speech-based Recommender Systems P Grasch – grasch.net … Additionally, any successful natural language speech-based interface further has to handle non-speech data such as laughs, coughs, lip smacks, and other kinds of background noise. SpeechRec Simon PocketSphinx Figure 2.1.: Speech processing architecture. … Related articles

Response prompting for intelligent robot instruction of students with intellectual disabilities C Reardon, H Zhang, R Wright… – Robot and Human …, 2015 – ieeexplore.ieee.org … [24] integrated through the ROS action request/service paradigm; speech recognition using CMU PocketSphinx [25]; speech synthesis using eSpeak [26]; and 3D human tracking using NITE [27], all of which are leveraged in this work. … Cited by 1 Related articles All 5 versions

FPGA-Based Hardware Accelerator for Feature Extraction in Automatic Speech Recognition C Choo, YU Chang, IY Moon – Journal of information and communication …, 2015 – kpubs.org … [14] D. Huggins-Daines, M. Kumar, A. Chan, A. Black, M. Ravishankar, and A. Rudnicky, “PocketSphinx: a free, real-time continuous speech recognition system for hand-held devices,” in Proceedings of IEEE International Conference on Acoustics, … Related articles All 3 versions

Enabling visually impaired people to use touch screen phones A Kivaisi – 2015 – open.uct.ac.za … license, which implies legal precautions need to be taken seriously. However, the pocketsphinx library lies under the Berkeley Software Distribution (BSD) license, which is a free, permissive license. Page 16. 15 1.4 Overview of the thesis …

A Review of Interventions with Assistive Technologies for Patients with Cognitive Impairment P Georgakopoulos, M Chatzidimitriou… – … of Research on …, 2015 – books.google.com … Barrena and colleagues have used Google Voice Recognition technology and Carnegie Mellon’s PocketSphinx (Barrena et al, 2012). CONCLUSION There is a wide and diverse field of applica- tions and research issues that are currently being implemented and investigated. … Cited by 1 All 3 versions

Towards the creation of reliable voice control system based on a fuzzy approach AV Savchenko, LV Savchenko – Pattern Recognition Letters, 2015 – Elsevier The key purpose of this paper is to train a voice control system if a small amount of user speech data is available without need for general acoustic model if t. Cited by 4 Related articles All 3 versions

Challenges in Concussion Detection Using Vocal Acoustic Biomarkers C Poellabauer, N Yadav, L Daudet, SL Schneider… – IEEE …, 2015 – ieeexplore.ieee.org Page 1. 2169-3536 (c) 2015 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 … Cited by 1 Related articles All 4 versions

Enabling ubiquitous interaction with smart things H Wirtz, J Rüth, M Serror… – … (SECON), 2015 12th …, 2015 – ieeexplore.ieee.org … For AR GUIs, we use the Qualcomm Vuforia frame- work [25] to augment ST in the smartphone’s camera view. Speech commands are recognized using Pocketsphinx [26], a handheld-optimized version of the popular CMU Sphinx. B. Smart Thing Implementation … Related articles All 3 versions

A floor acoustic sensor for fall classification E Principi, P Olivetti, S Squartini, R Bonfigli… – … Society Convention 138, 2015 – aes.org … A oor acoustic sensor for fall classi cation [ 18 ] D . Huggins – Daines , M . Kumar , A . Chan , A . Black , M . Ravishankar , and A . Rudnicky , \ PocketSphinx : A free , real – time continuous speech recognition system for hand – held de – vices , ” in Proc . of ICASSP , vol . … Cited by 3 Related articles All 2 versions

From rule-based to data-driven lexical entrainment models in spoken dialog systems J Lopes, M Eskenazi, I Trancoso – Computer Speech & Language, 2015 – Elsevier … Let’s Go uses a recognition server that communicates with different recognizer versions (eg: male, female, etc.), running PocketSphinx (Huggins-daines et al., 2006). In Noctívago, the Audimus (Neto et al., 2008) speech recognizer is integrated in a web interface module. … Cited by 4 Related articles All 5 versions

Multi-microphone speech dereverberation and noise reduction using relative early transfer functions O Schwartz, S Gannot… – IEEE/ACM Transactions on …, 2015 – ieeexplore.ieee.org Page 1. 2329-9290 (c) 2013 IEEE. Personal use is permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org/ publications_standards/publications/rights/index.html for more information. This … Cited by 6 Related articles All 7 versions

Zoe: A cloud-less dialog-enabled continuous sensing wearable exploiting heterogeneous computation ND Lane, P Georgiev, C Mascolo, Y Gao – Proceedings of the 13th …, 2015 – dl.acm.org Page 1. ZOE: A Cloud-less Dialog-enabled Continuous Sensing Wearable Exploiting Heterogeneous Computation Nicholas D. Lane†, Petko Georgiev§, Cecilia Mascolo§, Ying Gao‡ †Bell Labs, §University of Cambridge, ‡Intel Research … Cited by 4 Related articles All 10 versions

Coherent-to-diffuse power ratio estimation for dereverberation A Schwarz, W Kellermann – IEEE/ACM Transactions on Audio, …, 2015 – ieeexplore.ieee.org Page 1. 2329-9290 (c) 2015 IEEE. Personal use is permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org/ publications_standards/publications/rights/index.html for more information. This … Cited by 18 Related articles All 5 versions

Minimum data generation for Telugu speech recognition KVN Sunitha, A Sharada – International Journal of Speech Technology, 2015 – Springer Related articles All 3 versions

Architecture and representation for handling dialogues in human-robot interactions E Retamino, S Nair, A Vijayalingam… – 2015 Asia-Pacific …, 2015 – ieeexplore.ieee.org … The main source of misunderstanding during the interaction 4http://www.speech.cs.cmu.edu/ pocketsphinx/ 5https://www.cereproc.com Proceedings of APSIPA Annual Summit and Conference 2015 16-19 December 2015 978-988-14768-0-7©2015 APSIPA … Related articles All 2 versions

Data-Intensive Mobile Cloud Computing JHJ Ahnn – Energy, 2015 – escholarship.org Page 1. … Related articles All 2 versions

Malleable Contextual Partitioning and Computational Dreaming GS Brar – 2015 – vtechworks.lib.vt.edu Page 1. Malleable Contextual Partitioning and Computational Dreaming Gurkanwal Singh Brar Thesis submitted to the faculty of the Virginia Polytechnic Institute and State University in partial fulfillment of the requirements for the degree of … Related articles

Concept and functional structure of a service robot LA Pineda, A Rodríguez, G Fuentes… – International …, 2015 – search.proquest.com … Laser. Player. Voice recognition. RODE VideoMic, M-Audio Fast Track. Interface. JACK, PocketSphinx. Voice synthesizer. Infinity 3.5-Inch Two-Way Built-in Loudspeakers. PulseAudio, Festival TTS. Object Manipulation. In-house Built Robotic. Arm and Gripper Dynamixel RoboPlus … Cited by 4 Related articles All 9 versions

Talking Books: the development of an interactive, educational, digital application E Drescher – 2015 – aut.researchgateway.ac.nz Page 1. ! 1! ! Talking!Books:! The!Development!of!an!Interactive,!Educational,! Digital!Application! ! ! ! ! Emile!Drescher! ! ! ! ! This!exegesis!is!submitted!to!the! Auckland!University!of!Technology!in!partial!fulfilment! of!the … All 2 versions

Listening through a Vibration Motor N Roy, RR Choudhury – synrg.csl.illinois.edu 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. … Related articles

Building a grid-point cloud-semantic map based on graph for the navigation of intelligent wheelchair C Zhao, H Hu, D Gu – Automation and Computing (ICAC), 2015 …, 2015 – ieeexplore.ieee.org … Ml, 2007, pp. 3472–3478. [27] D. Huggins-Daines, M. Kumar, A. Chan, A. Black, M. Ravishankar, and A. Rudnicky, “Pocketsphinx: A Free, Real-Time Continuous Speech Recognition System for Hand-Held Devices,” 2006 IEEE International Conference on Acoustics Speech … Related articles All 4 versions

An empirical investigation to examine the usability issues of using adaptive, adaptable, and mixed-initiative approaches in in-teractive systems M Alshumari – 2015 – dora.dmu.ac.uk Page 1. I Online English Vocabulary Learning on Different Systems for Non-English Speakers Alshumari Mansour PhD 2015 Page 2. II Online English Vocabulary Learning on Different Systems for Non-English Speakers An … Related articles All 4 versions

Exploiting resources from closely-related languages for automatic speech recognition in low-resource languages from Malaysia S Juan, S Flora – 2015 – theses.fr Page 1. TH `ESE Pour obtenir le grade de DOCTEUR DE L’UNIVERSIT ´E DE GRENOBLE Sp écialit é : Informatique Arrêté ministérial : Pr ésent ée par Sarah Flora SAMSON JUAN Th`ese dirigée par Laurent BESACIER préparée … Related articles All 2 versions

A Hybrid Approach for Speech Enhancement Using MoG Model and Neural Network Phoneme Classifier SE Chazan, J Goldberger, S Gannot – arXiv preprint arXiv:1510.07315, 2015 – arxiv.org Page 1. 1 A Hybrid Approach for Speech Enhancement Using MoG Model and Neural Network Phoneme Classifier Shlomo E. Chazan, Jacob Goldberger and Sharon Gannot Senior Member, IEEE, Faculty of Engineering, Bar-Ilan University, Ramat-Gan, 5290002, Israel … Cited by 1 Related articles All 2 versions

Towards Integrated Acoustic Models for Speech Synthesis PK Muthukumar – 2015 – cs.cmu.edu Page 1. Towards Integrated Acoustic Models for Speech Synthesis Prasanna Kumar Muthukumar CMU-LTI-15-019 Language Technologies Institute, School of Computer Science, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213. www.lti.cs.cmu.edu … Related articles All 4 versions