AT&T Watson


research.att.com/projects/WATSON

References:

See also:

100 Best Speech API Videos | 100 Best Speech-To-Text VideosSpeak4it


An alternative front-end for the AT&T WATSON LV-CSR system D Dimitriadis, E Bocchieri… – Acoustics, Speech and …, 2011 – ieeexplore.ieee.org ABSTRACT In previously published work, we have proposed a novel feature extraction algorithm, based on the Teager-Kaiser energy estimates, that approximates human auditory characteristics and that is more robust to sub-band noise than the mean-square estimates … Cited by 5 Related articles All 5 versions

Speech recognition modeling advances for mobile voice search E Bocchieri, D Caseiro… – Acoustics, Speech and …, 2011 – ieeexplore.ieee.org … The combination of these algorithms, integrated into the AT&T Watson recognizer, yields substantial accuracy im- provements. … 4.3. TECC Front-End The acoustic front-end of the AT&T Watson recognizer [3] is based on the mel-frequency cepstral analysis of speech. … Cited by 10 Related articles All 5 versions

QASR: Spoken Question Answering Using Semantic Role Labeling S Stenchikova, D Hakkani-Tur… – les actes de International …, 2006 – researchgate.net … While using the speech interface, QASR uses AT&T Watson speech recognizer (Goffin et al., 2005) with VoiceXML (VXML ). … 2005. The at&t watson speech rec- ognizer. In Proceedings of the ICASSP, Philadelphia, PA, March. … Cited by 5 Related articles All 5 versions

Your mobile virtual assistant just got smarter! M Gilbert, I Arizmendi, E Bocchieri, D Caseiro… – …, 2011 – researchgate.net … Section 3 provides details of the adaptive learning techniques for acoustic and language modeling used in the AT&T WATSON™ speech engine [2]. Section 4 presents results for supervised and unsupervised adaptation at the mobile device level. … Cited by 5 Related articles All 2 versions

Multilingual web conferencing using speech-to-speech translation. J Chen, S Wen, VKR Sridhar, S Bangalore – INTERSPEECH, 2013 – web2.research.att.com … 2. System Description In order to implement real-time speech translation with text message display, a B2BUA app server was used to act as a SIP Registrar and Soft-Switch was used to connect calls to AT&T WATSON SIP servers. … Related articles All 8 versions

Demonstration of AT&T “Let’s Go”: A production-grade statistical spoken dialog system JD Williams, I Arizmendi… – … Workshop (SLT), 2010 …, 2010 – ieeexplore.ieee.org … The pronunciations used by TTS for most stop names were checked and adjusted when necessary, consulting native Pittsburghers. Recognition was performed with the AT&T WATSON speech recognizer [4]. Two statistical techniques were incorporated. … Cited by 10 Related articles All 7 versions

Multimodal interactive spaces: MagicTV and magicMAP M Worsley, M Johnston – Spoken Language Technology …, 2010 – ieeexplore.ieee.org … The application framework also incorporates tight coupling with the AT&T Watson speech recognizer system [4] and a local Apache webserver for serving the HTML content. … 2005. The AT&T WATSON speech recognizer. In Proceedings of ICASSP. pp. 1033–1036. … Cited by 3 Related articles All 8 versions

Which ASR should I choose for my dialogue system F Morbini, K Audhkhasi, K Sagae, R Artstein… – Proceedings of the 14th …, 2013 – sail.usc.edu … AT&T Watson Watson is the AT&T ASR en- gine available through the AT&T Speech Mashup service.6 It is a cloud based service that can be accessed through HTML POST requests, like the Google Speech API. AT&T Watson … Cited by 10 Related articles All 12 versions

A comparison of speech and GUI input for navigation in complex visualizations on mobile devices R Zhang, S North, E Koutsofios – … of the 12th international conference on …, 2010 – dl.acm.org … 357 Page 2. 2. SYSTEM ARCHITECTURE The system architecture consists of: the Speech Interface, Speech API, Speech Mashup Manager (SMM), AT&T WATSON Automatic Speech Recognition (ASR), and the Visualizer System, as shown in Figure 1. … Cited by 2 Related articles

The AT&t speech API: a study on practical challenges for customized speech to text service. E Gouvêa, A Moreno-Daniel, A Reddy… – INTERSPEECH, 2013 – Citeseer … 7. References [1] V. Goffin, C. Allauzen, E. Bocchieri, DH Tur, A. Ljolje, and S. Parthasarathy, “The AT&T Watson speech recognizer,” in Proc. ICASSP, September 2005. [2] J. Donovan, “AT&T Speech API Gives Developers the Power of AT&T WATSON,” July 2012. [Online]. … Cited by 1 Related articles All 3 versions

Characterizing Mobile Open APIs in Smartphone Apps L Zhang, C Stover, A Lins, C Buckley… – Networking …, 2014 – ieeexplore.ieee.org … The app is developed by Sphero, a company that manufactures voice controlled robotic balls. When the user says a command to the app, the AT&T Speech API is invoked and the spoken voice will be streamed to the AT&T Watson Server. … Cited by 1 Related articles All 3 versions

Imiracle: Multimodal Speech-Enabled Mobile Video Search B Renger, A Basso, D Gibbon, M Johnston, Z Liu… – cs.cmu.edu … The system uses the AT&T WATSON speech recognition [22] and finite-state natural language understanding [4] engines, which are both accessible through the AT&T Speech Mashup Portal [3]. The AT&T MIRACLE engine [1, 2] provides the video search capability. … Related articles All 6 versions

GeoVAQA: a voice activated geographical question answering system J Luque, D Ferrés, J Hernando, JB Mariño… – Actas de las IV …, 2006 – cs.upc.edu … [2] described a speech interface for the AnswerBus2 QA system using a commercial dictation engine (Dragon Naturally Speaking 6.1). [3] presented QASR, a system using semantic role labelling for QA and the AT&T Watson speech recogniser. … Cited by 5 Related articles All 8 versions

A general framework for building natural language understanding modules in voice search J Feng – Acoustics Speech and Signal Processing (ICASSP), …, 2010 – ieeexplore.ieee.org … We instantiated the described framework on a mobile local businesss search task, where the search engine we use is http://www.yellowpages.com/ and the speech recognizer is the AT&T Watson ASR engine [6]. Our training data consists of 18 million web queries to http://www … Cited by 4 Related articles

Webtalk: Towards Automatically Building Spoken Dialog Systems Through Miningwebsites J Feng, D Hakkani-Tur, G Di Fabbrizio… – … , Speech and Signal …, 2006 – ieeexplore.ieee.org … The acoustic model was trained using utterances collected from other deployed spoken dialog services. Both the acoustic and language models are used in speech recognition with the AT&T Watson speech recognizer [8]. 2.3. … Cited by 2 Related articles All 7 versions

VoiSTV: voice-enabled social TV B Renger, J Feng, O Dan, H Chang… – Proceedings of the 20th …, 2011 – dl.acm.org … The underlying speech recogni- tion engine is AT&T Watson [4]. The acoustic and language models of Watson were trained using SMS messages. … The AT&T Watson speech recognizer. In Proceedings of ICASSP, pages 1033–1036, 2005. … Cited by 4 Related articles All 16 versions

Semantic data selection for vertical business voice search G Di Fabbrizio, D Caseiro… – Acoustics, Speech and …, 2011 – ieeexplore.ieee.org … 5 Experiments The AT&T Watson [10] recognizer was used to evaluate the word accuracy of the language models described in Section 4. All experiments used a triphonic HMM acoustic model origi- nally developed for SPEAK4IT. 5618 Page 4. … Related articles All 13 versions

Comparing Open-Source Speech Recognition Toolkits? C Gaida, P Lange, R Petrick, P Proba, A Malatawy… – antikenschlacht.com … On the one hand, there are commercial systems such as AT&T Watson [1], Microsoft Speech Server [2], Google Speech API [3] and Nuance Recognizer [4]. On the other hand, proprietary systems offer little control over the recognizer’s features, and limited native integrability into … Related articles All 9 versions

Can prosody inform sentiment analysis? experiments on short spoken reviews F Mairesse, J Polifroni… – Acoustics, Speech and …, 2012 – ieeexplore.ieee.org … 3,268 textual review summaries. 5. SPEECH RECOGNITION FOR SPOKEN REVIEWS The AT&T Watson [10] speech recognizer was used to automatically convert each spoken review summary to text. Due to the scarcity of … Cited by 7 Related articles All 24 versions

Demonstrating The Incremental Interaction Manager In An End-To-End “Lets Go!” Dialogue System EO Selfridge, PA Heeman, I Arizmendi… – IEEE Workshop on …, 2012 – 131.107.65.14 … of the SIGdial, 2011. [4] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar, “The AT&T WATSON speech recognizer,” in Proc. of ICASSP, 2005, pp. 1033–1036. Cited by 3 Related articles All 7 versions

Vision: mClouds-computing on clouds of mobile devices E Miluzzo, R Cáceres, YF Chen – Proceedings of the third ACM workshop …, 2012 – dl.acm.org … The game-changing application markets (Apple App Store and Google Android Market), ar- tificial intelligence breakthroughs (AT&T Watson [2], Apple Siri, Google voice search), sensing and communication capa- bilities are pushing the envelope for a new class of devices … Cited by 22 Related articles All 4 versions

Feature-rich continuous language models for speech recognition P Mirowski, S Chopra, S Balakrishnan… – … (SLT), 2010 IEEE, 2010 – ieeexplore.ieee.org Page 1. FEATURE-RICH CONTINUOUS LANGUAGE MODELS FOR SPEECH RECOGNITION Piotr Mirowski Courant Institute of Mathematical Sciences New York University 719 Broadway, 12th Floor New York, NY 10034, USA … Cited by 1 Related articles All 6 versions

Multimodal Processing DC Gibbon, Z Liu – Introduction to Video Search Engines, 2008 – Springer … Each sentence has three proper- ties: starting time, ending time, and text. Then the system utilizes the AT&T Watson Automatic Speech Recognition (ASR) tools to align each sentence with the corresponding audio utterance. … Related articles

Web-based real time content processing and monitoring service for digital TV broadcast Z Liu, D Gibbon, B Shahraray – Broadband Multimedia Systems …, 2010 – ieeexplore.ieee.org … In this program title and description inform B. Automatic Speech Recognition The AT&T Watson real-time employed in this work. The continuous-density hidden Markov m modeling and finite state machi language modeling. The recognition efficient search. … Cited by 2 Related articles All 2 versions

Learning a Query Parser for Local Web Search D Feng, J Shanahan, N Murray… – … Computing (ICSC), 2010 …, 2010 – ieeexplore.ieee.org … We therefore design grammars at the phrase level and use CFG composition to cover all variations. Fig. I shows a snippet of our grammars and the CFG composition can be completed using AT&T Watson toolkit [23]. Figure I. A snippet of CFG grammars. As shown in Fig. … Cited by 1 Related articles All 5 versions

Speech recognition with dynamic time warping using MATLAB P Lama, M Namburu – PROJECT REPORT, 2010 – cs.uccs.edu … Some proprietary softwares available in market are AT&T WATSON, HTK (copyrighted by Microsoft), Voice Finger (for Windows Vista and Windows 7), Dragon NaturallySpeaking from Nuance Communications (utilized Hidden Markov Models), e-Speaking (for Windows XP) and … Cited by 10 Related articles

Crowd-sourcing for difficult transcription of speech JD Williams, ID Melamed, T Alonso… – … (ASRU), 2011 IEEE …, 2011 – ieeexplore.ieee.org … further. We next compared crowd-workers to ASR. We built a statistical language model from a large separate set of expert transcriptions, and combined it with a generic acoustic model using AT&T’s WATSON ASR system [12]. On … Cited by 10 Related articles All 12 versions

SEECAT: ASR & Eye-tracking Enabled Computer-Assisted Translation M Garc?a-Mart?nez, K Singla, A Tammewar… – researchgate.net … 3RB: Record Button 4SB: Stop Button 3.1 Automatic Speech Recognition (ASR) In SEECAT, AT&T Watson Toolkit has been trained for ASR in three languages, namely En- glish, Hindi and Spanish. 3.1.1 English and Spanish … Related articles

Collecting multimodal data in the wild M Johnston, P Ehlen – Proceedings of the 2012 ACM international …, 2012 – dl.acm.org … MULTIMODAL SEMANTIC INTERPRETATION SYSTEM MSIS was developed using AT&T’s Watson platform, fostered in part by two advances: a streaming HTTP API that supports cloud-based recognition, and a plug-in development environment that supports complex chains … Related articles

Stability and accuracy in incremental speech recognition EO Selfridge, I Arizmendi, PA Heeman… – Proceedings of the …, 2011 – dl.acm.org … The resulting models were then evaluated on both All and MW utterances. As a baseline for both measures, we compare to AT&T WATSON’s existing confidence score. This score is used in numerous deployed com- mercial applications, so we believe it is a fair baseline. … Cited by 22 Related articles All 17 versions

Integrating Adaptive Beam-forming and Auditory Features for Robust Large Vocabulary Speech Recognition QPL Xie Sun, M Zhu, Q Zhou – 2012 – lilabs.com … [2] A. Stolcke, “Making the most from multiple microphones in meeting recognition,” in ICASSP 2011, 2011. [3] D. Dimitriadis, E. Bocchieri and D. Caseiro, “An alternative front- end for the AT&T Watson LV-CSR system,” in ICASSP 2011, 2011. [4] C. Kim and RM Stern. … Related articles All 3 versions

Speak4it and the Multimodal Semantic Interpretation System. M Johnston, P Ehlen – INTERSPEECH, 2011 – research.att.com … MSIS was developed using AT&T’s Watson platform, fostered in part by two advances: a streaming HTTP API that supports cloud-based recognition, and a plug-in development environment that supports complex chains of diverse processing for signal streams. … Cited by 2 Related articles All 5 versions

AT&T VoiceBuilder: A Cloud-Based Text-to-Speech Voice Builder Tool. YJ Kim, T Okken, A Conkie, G Di Fabbrizio – INTERSPEECH, 2011 – difabbrizio.com … [4] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tür, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar, “The AT&T WATSON Speech Recognizer,” in IEEE International Con- ference on Acoustics, Speech and Signal Processing, 2005. 3328 Cited by 1 Related articles All 10 versions

Exploration of Speech enabled System for English K Sharma, T Suryakanthi, TV Prasad – arXiv preprint arXiv:1304.8013, 2013 – arxiv.org … S. No. Name Description Developed by Year 1 AT&T Watson API AT&T WatsonSM speech recognition technology APIs for developers to incorporate the speech engine’s capabilities into their own products with minimum hassle. … Cited by 1 Related articles All 3 versions

Use of geographical meta-data in ASR language and acoustic models E Bocchieri, D Caseiro – Acoustics Speech and Signal …, 2010 – ieeexplore.ieee.org … These experiments were performed with the AT&T Watson recognizer, with a triphonic HMM, discriminatively trained on 2,000 hours of telephone data, and adapted on the tran- scribed in-domain data of Sections 2.1 and 2.2, respectively for city-state and voice-search ASR. 4.1. … Cited by 4 Related articles All 2 versions

MVA: The Multimodal Virtual Assistant M Johnston, J Chen, P Ehlen, H Jung, J Lieske… – 15th Annual Meeting of …, 2014 – aclweb.org … Vincent Goffin, Cyril Allauzen, Enrico Bocchieri, Dilek Hakkani-Tur, Andrej Ljolje, S. Parthasarathy, Mazim Rahim, Giuseppe Riccardi, and Murat Sar- aclar. 2005. The AT&T WATSON speech recog- nizer. In Proceedings of ICASSP, pages 1033–1036, Philadelphia, PA, USA. … Cited by 1 Related articles All 6 versions

A speech mashup framework for multimodal mobile services G Di Fabbrizio, T Okken, JG Wilpon – Proceedings of the 2009 …, 2009 – dl.acm.org … codecs (for example the Adaptive Multi-Rate5 codec at 12.2kbits/s). Then an HTTP (Hypertext Transfer Proto- col) [7] connection (the transport) is established with the speech mashup manager (the server), which delivers the bit stream to the AT&T WATSON speech recognizer … Cited by 39 Related articles All 6 versions

A novel approach: Voice enabled interface with intelligent voice response system to navigate mobile devices for visually challenged people RTF Michael, B RajaKumar… – Emerging Trends in …, 2013 – ieeexplore.ieee.org … discussion and active support. REFERENCES [I] V. Gotlin, G. Riccardi C. Allauzen D. Hakkani A. Ljolje S.Parthasarathy M. Rahim, and M. Saraclar., “The at&t Watson speech recognizer,” in ICASSP, 2005. [2] Gerr F., Marcus … Related articles

Multimodal System Based on Electrooculography and Voice Recognition to Control a Robot Arm JA Martínez, A Úbeda, E Iáñez… – … Journal of Advanced …, 2013 – cdn.intechopen.com … Some proprietary softwares available in the market to do speech recognition are (among others): AT&T WATSON (by AT&T Bell Laboratories), HTK (copyrighted by Microsoft), Voice Finger (by Robson Cozendey), Dragon NaturallySpeaking (by Nuance Communications), e … Related articles All 3 versions

Integrating incremental speech recognition and pomdp-based dialogue systems EO Selfridge, I Arizmendi, PA Heeman… – Proceedings of the 13th …, 2012 – dl.acm.org … V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar. 2005. The AT&T WATSON speech recognizer. In Proceedings of ICASSP, pages 1033– 1036. D. Lu, T. Nishimoto, and N. Minematsu. 2011. … Cited by 14 Related articles All 20 versions

Estimating probability of correctness for ASR N-Best lists JD Williams, S Balakrishnan – … of the SIGDIAL 2009 Conference: The …, 2009 – dl.acm.org … http://www.stat.rutgers.edu/ ˜madigan/BMR/. V Goffin, C Allauzen, E Bocchieri, D Hakkani-Tur, A Ljolje, S Parthasarathy, M Rahim, G Riccardi, and M Saraclar. 2005. The AT&T Watson speech recog- nizer. In Proc ICASSP, Philadelphia. JC Platt. 1999. … Cited by 15 Related articles All 19 versions

Large scale content analysis engine D Gibbon, Z Liu – Proceedings of the First ACM workshop on Large-scale …, 2009 – dl.acm.org … The adopted ASR engine is the AT&T Watson real-time speech recognizer [5]. The recognizer is based on continuous-density hidden Markov models (HMM) for acoustic modeling and finite state machine (FSM) networks for language modeling. … Cited by 11 Related articles All 5 versions

Steps in the development of a robotic scrub nurse C Pérez-Vidal, E Carpintero, N Garcia-Aracil… – Robotics and …, 2012 – Elsevier … ViaVoice SDK: some proprietary software available in the market to do speech recognition are (among others): AT&T WATSON (by AT&T Bell Laboratories), HTK (copyrighted by Microsoft), Voice Finger (by Robson Cozendey), Dragon NaturallySpeaking (by Nuance … Cited by 9 Related articles All 4 versions

Efficient client–server based implementations of mobile speech recognition services RC Rose, I Arizmendi – Speech communication, 2006 – Elsevier … client. The infrastructure used for the study included eight 1 GHz Linux ASR servers with each server running four instances of the AT&T Watson ASR decoder and a single 1 GHz Linux DSEM server with 256 Mb of RAM. Fig. … Cited by 3 Related articles All 5 versions

Fast acoustic computations using graphics processors PR Dixon, T Oonishi, S Furui – Acoustics, Speech and Signal …, 2009 – ieeexplore.ieee.org … INTERSPEECH, 2004, pp. 689–692. [5] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Sar- aclar, “The AT&T WATSON speech recognizer,” in Proc. ICASSP, 2005, pp. 1033–1036. … Cited by 47 Related articles All 5 versions

All together now A Hartholt, D Traum, SC Marsella, A Shapiro… – Intelligent Virtual …, 2013 – Springer … There are interfaces for a number of 3rd party Page 9. 376 A. Hartholt et al. ASRs (including PocketSphinx [7], Google ASR and AT&T Watson). The main ren- dering platform of the Toolkit is Unity [35], a proprietary game engine which offers a free version. … Cited by 30 Related articles All 5 versions

Using Graphics Hardware to Accelarate a Large Vocabulary Speech Decoder P Dixon, T Oonishi, S Furui – Using Graphics Hardware to …, 2008 – t2r2.star.titech.ac.jp … In Proc. ASRU, pages 1301–1304, 2007. [4] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar. The AT&T WATSON speech recognizer. In Proc. ICASSP, pages 1033–1036, 2005. … Related articles All 2 versions

Speaker segmentation and adaptation for speech recognition on multiple-speaker audio conference data Z Liu, M Saraclar – Multimedia and Expo, 2007 IEEE …, 2007 – ieeexplore.ieee.org … 6. REFERENCES [1] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi and M. Sar- aclar, “The AT&T WATSON Speech Recognizer ,” in ICASSP 2005, Philadelphia, PA, pp. 1033–1036. … Cited by 6 Related articles All 2 versions

Building Text-To-Speech Voices in the Cloud. A Conkie, T Okken, YJ Kim, G Di Fabbrizio – LREC, 2012 – difabbrizio.com … Vincent Goffin, Cyril Allauzen, Enrico Bocchieri, Dilek Hakkani-Tür, Andrej Ljolje, S. Parthasarathy, Mazin Rahim, Giuseppe Riccardi, and Murat Saraclar. (2005). The AT&T WATSON Speech Recognizer. In ICASSP, Philadelphia, USA. John Kominek and Alan W. Black. (2004). … Cited by 1 Related articles All 9 versions

Let’s DiSCoH: collecting an annotated open corpus with dialogue acts and reward signals for natural language helpdesks G Andreani, G Di Fabbrizio, M Gilbert… – Spoken Language …, 2006 – ieeexplore.ieee.org … 2005. [18] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Sar- aclar, “The AT&T Watson speech recognizer,” in ICASSP 2005 [19] N. Gupta, G. Tur, D. Hakkani-Tur, S. Bangalore, G. Riccardi, and M Rahim, “The AT&T … Cited by 15 Related articles All 6 versions

Discriminative training of multi-state barge-in models A Ljolje, V Goffin – Automatic Speech Recognition & …, 2007 – ieeexplore.ieee.org … 5.2. Testing on Previously Unseen Test Data Once the barge-in models were integrated into the AT&T Watson recognition engine the performance was evaluated on a number of diverse tasks, using recordings that were not used in creating the barge-in models. … Cited by 5 Related articles

Statistical shared plan-based dialog management. AJ Stent, S Bangalore – INTERSPEECH, 2008 – Citeseer … 34, 1991. [13] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar, “The AT&T WATSON Speech Recognizer,” in Proceedings of ICASSP, Philadelphia, PA, 2005. … Cited by 1 Related articles All 6 versions

SpeechForms: From Web to Speech and Back. L Barbosa, D Caseiro, G Di Fabbrizio, A Stent – INTERSPEECH, 2011 – Citeseer … Cambridge, MA: MIT Press, 1998. [26] FM Suchanek, G. Kasneci, and G. Weikum, “Yago: A core of semantic knowledge,” in Proc. WWW, 2007. [27] V. Goffin et al., “The AT&T WATSON speech recognizer,” in Proc. ICASSP, 2005. … Cited by 1 Related articles All 10 versions

Development and suitability of Indian languages speech database for building watson based ASR system D Pandey, T Mondal, SS Agrawal… – … COCOSDA held jointly …, 2013 – ieeexplore.ieee.org … Soc. India,54(1), pp. 41-46, January 2007. [8] http://www.statmt.org/moses/manual/ manual.pdf. [9]http://www1.icsi.berkeley.edu/Speech/docs/sctk- 1.2/sclite.htm [10] http://www.research.att.com/projects/WATSON/ ?fbid=2tgRMa1CfjG. … Cited by 2 Related articles

Audio Processing DC Gibbon, Z Liu – Introduction to Video Search Engines, 2008 – Springer Page 1. 7 Audio Processing 7.1 Introduction Audio plays an important role in our daily life. From speech to music, from FM radios to Podcast services, from lectures to audio books, audio is simply ubiquitous. Through audio, we … Cited by 3 Related articles

On End-to-End QOS Mapping JF cois Huard, AA Lazar – Citeseer … In 94 he was involved in the XUNET project, working on fault management. In 95, he was involved in the development of AT&T WATSON ASR for Windows 95 and NT. Mr. Huard was awarded a Centennial Scholarship of the NSERC of Canada (1990{94). … Related articles All 3 versions

On the Development of Adaptive and User-Centred Interactive Multimodal Interfaces D Griol, Z Callejas, R López-Cózar… – Speech, Image, and …, 2012 – books.google.com … There is also a number of proprietary software forASR, including AT&T WATSON, Windows speech recognition system, IBM ViaVoice, Microsoft Speech API, Nuance Dragon NaturallySpeaking, MacSpeech, Loquendo ASR and Verbio ASR. … Related articles All 5 versions

Learning edit machines for robust multimodal understanding M Johnston, S Bangalore – Acoustics, Speech and Signal …, 2006 – ieeexplore.ieee.org … 20, no. 5, pp. 522–532, 1998. [14] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar, “The at&t watson speech recognizer,” in Proceedings of ICASSP, Philadelphia, PA, 2005. … Cited by 3 Related articles All 4 versions

Investigating deep neural network based transforms of robust audio features for LVCSR E Bocchieri, D Dimitriadis – Acoustics, Speech and Signal …, 2013 – ieeexplore.ieee.org … for mobile voice search,”,in Proc. ICASSP, 2011, pp 4888-4891. [24] D.Dimitriadis, E.Bocchieri and D.Caseiro, “An alternative front-end for the AT&T WATSON LV-CSR system”, in Proc. ICASSP, 2011. [25] D. Dimitriadis and P … Cited by 4 Related articles All 7 versions

What did spot hide?: a question-answering game for preschool children A Tewari, J Canny – Proceedings of the 32nd annual ACM conference on …, 2014 – dl.acm.org Page 1. What did Spot Hide? A Question-Answering Game for Preschool Children Anuj Tewari1,2 & John Canny1 1Computer Science Division and Berkeley Institute of Design, University of California, Berkeley, USA 2GE Global … Related articles All 3 versions

Real-time incremental speech-to-speech translation of dialogs S Bangalore, VK Rangarajan Sridhar, P Kolan… – Proceedings of the …, 2012 – dl.acm.org … patterns. In Proc. of Col- ing ’96. Vincent Goffin, Cyril Allauzen, Enrico Bocchieri, Dilek Hakkani Tur, Andrej Ljolje, and Sarangarajan Parthasarathy. 2004. The AT&T Watson Speech Rec- ognizer. Technical report, September. P … Cited by 18 Related articles All 11 versions

Large-Scale Analysis for Interactive Media Consumption D Gibbon, A Basso, L Begeja, Z Liu… – TV Content Analysis: …, 2012 – books.google.com Page 240. Chapter 8 Large-Scale Analysis for Interactive Media Consumption David Gibbon AT&T Labs Research Andrea Basso AT&T Labs Research Lee Begeja AT&T Labs Research Zhu Liu AT&T Labs Research Bernard … Cited by 3 Related articles All 3 versions

Statistical machine translation through global lexical selection and sentence reconstruction S Bangalore, P Haffner, S Kanthak – Annual Meeting-Association for …, 2007 – aclweb.org … V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar. 2005. The AT&T WATSON Speech Recognizer. In Pro- ceedings of ICASSP, Philadelphia, PA. H. Hassan, M. Hearne, K. Sima’an, and A. Way. 2006. … Cited by 53 Related articles All 14 versions

Encyclopedia of Wireless and Mobile Communications B Falchuk, D Famolari, S Loeb – 2006 – Taylor & Francis Page 1. Encyclopedia of Wireless and Mobile Communications, Second Edition DOI: 10.1081/E-EWMC2-120048719 Copyright © 2013 by Taylor & Francis. All rights reserved. Image – IP Networks Intelligent Mobile Applications … Cited by 3 Related articles All 3 versions

Speech Mashups G Di Fabbrizio, T Okken, J Wilpon – Semantic Mashups, 2013 – Springer … In the former case, it makes the AT&T WATSON SM speech recognition engine [ 19 ] and the AT&T Natural Voices™ text-to-speech synthesis engine [ 6 ] accessible through any network as web services and exposes them through an HTTP-based API. … Cited by 2 Related articles All 3 versions

Role of Pausing in Text-to-Speech Synthesis for Simultaneous Interpretation VKR Sridhar, J Chen, S Bangalore… – Eighth ISCA Workshop on …, 2013 – ssw8.talp.cat … Multidimensional Translation, Saarbrücken, 2005. [8] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tür, A. Ljolje, and S. Parthasarathy, “The AT&T Watson Speech Recognizer,” Tech. Rep., September 2004. [9] VK Rangarajan … Cited by 1 Related articles All 9 versions

Cepstrum-domain model combination based on decomposition of speech and noise using MMSE-LSA for ASR in noisy environments HK Kim, RC Rose – Audio, Speech, and Language Processing, …, 2009 – ieeexplore.ieee.org … As a result, the recognition system had 274 subword HMMs, 831 states, and 6672 mixtures. The AT&T Watson speech recognition engine was used for ASR [28]. Table II shows word error rate (WER) for the baseline front-end according to different SNRs. … Cited by 9 Related articles All 7 versions

Design and implementation of the note-taking style haptic voice recognition for mobile devices S Moon, KC Sim – Proceedings of the 14th ACM international conference …, 2012 – dl.acm.org … Speech API for Android devices2, AT&T’s Watson API3, or wami4. This gives developers the opportunity to easily implement appli- cations that make use of this technology. 2http://developer. android.com/reference/ 3http://www.research.att.com/projects/WATSON/index.html 4http … Related articles All 3 versions

Corpus analysis of simultaneous interpretation data for improving real time speech translation. VKR Sridhar, J Chen, S Bangalore – INTERSPEECH, 2013 – web2.research.att.com … logical Review, vol. 63, no. 2, pp. 81–97, 1956. [13] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tür, A. Ljolje, and S. Parthasarathy, “The AT&T Watson Speech Recognizer,” Tech. Rep., September 2004. [14] FJ Och and … Cited by 3 Related articles All 8 versions

Social Interaction Behavior Improvement System KB Mohamed, FH Hamed, TS Yeek, D Lukose – academia.edu … Vol. 1. CVPR ’05. IEEE Computer Society, 2005, pp. 886–893. [7] V. Goffin et al. “The AT&T WATSON speech recognizer”. In: in Proceed- ings of ICASSP. 2005. [8] TR Gruber et al. “Intelligent Automated Assistant”. Patent US2012- 0016678 (US). Jan. 2012. url: http : / / www . … Related articles

Finite-state transducer-based statistical machine translation using joint probabilities. S Bangalore, S Kanthak, P Haffner – IWSLT, 2006 – Citeseer … 2002. [9] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar, “The AT&T WATSON Speech Recog- nizer,” in Proceedings of ICASSP, Philadelphia, PA, 2005. [10 … Cited by 2 Related articles All 11 versions

Geo-centric language models for local business voice search A Stent, I Zeljkovi?, D Caseiro, J Wilpon – Proceedings of Human …, 2009 – dl.acm.org … For national, top 2000, local area and geo- centric LMs, we build trigram Katz backoff lan- guage models using AT&T’s Watson language mod- eling toolkit (Riccardi et al., 1996). … 2005. The AT&T Watson speech recognizer. In Proceedings ICASSP. … Cited by 11 Related articles All 12 versions

Noisy hidden Markov models for speech recognition K Audhkhasi, O Osoba, B Kosko – Neural Networks (IJCNN), …, 2013 – ieeexplore.ieee.org Page 1. Noisy Hidden Markov Models for Speech Recognition Kartik Audhkhasi, Osonde Osoba, Bart Kosko Abstract—We show that noise can speed training in hid- den Markov models (HMMs). The new Noisy Expectation- Maximization … Cited by 1 Related articles All 2 versions

The multimodal presentation dashboard M Johnston, P Ehlen, D Gibbon, Z Liu – … of the Workshop on Bridging the …, 2007 – dl.acm.org … Vincent Goffin, Cyril Allauzen, Enrico Bocchieri, Dilek Hakkani-Tür, Andrej Ljolje, Sarangarajan Partha- sarathy, Mazin Rahim, Giuseppe Riccardi, and Murat Saraclar. 2005. The AT&T WATSON speech recog- nizer. In Proceedings of ICASSP. … Cited by 3 Related articles All 13 versions

Deploying Intelligent Mobile Applications: Server or Device? B Falchuk – Mobile Web 2.0: Developing and Delivering Services …, 2010 – books.google.com … device). For example, the AT&T Watson speech recognition service is,“so complex that it is more practical to run the software on cen- tralized servers than to install, manage, and maintain it on countless mobile devices” [15]. … Related articles

Incremental emotion recognition. T Mishra, D Dimitriadis – INTERSPEECH, 2013 – Citeseer … 25, no. 1, pp. 29–44, Jan 2011. [16] D. Dimitriadis, E. Bocchieri, and D. Caseiro, “An Alternative Front-end for the AT&T WATSON LV-CSR System,” in Proc. Int’l Conf Acoustics,Speech, Signal Process. (ICASSP),. IEEE, 2011. … Related articles All 8 versions

A multiplatform speech recognition decoder based on weighted finite-state transducers E Stoimenov, T Schultz – … 2009. ASRU 2009. IEEE Workshop on, 2009 – ieeexplore.ieee.org … [5] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tür, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi and M. Saraclar. “The AT&T Watson Speech Recognizer”, Interspeech ’05, Lisbon, Portugal, 2005. [6] G. Saon, D. Povey, and G. Zweig. … Cited by 1 Related articles All 5 versions

Building multimodal applications with EMMA M Johnston – Proceedings of the 2009 international conference on …, 2009 – dl.acm.org … In Proceedings of ICMI, Boston, USA, 2009. [6] V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar. The AT&T WATSON Speech Recognizer. In Proceedings of ICASSP, Philadelphia, PA, 2005. … Cited by 27 Related articles All 6 versions

Segmentation Strategies for Streaming Speech Translation. VKR Sridhar, J Chen, S Bangalore, A Ljolje… – HLT-NAACL, 2013 – Citeseer Page 1. Proceedings of NAACL-HLT 2013, pages 230–238, Atlanta, Georgia, 9–14 June 2013. cO2013 Association for Computational Linguistics Segmentation Strategies for Streaming Speech Translation Vivek Kumar Rangarajan … Cited by 4 Related articles All 6 versions

Continuously predicting and processing barge-in during a live spoken dialogue task E Selfridge, I Arizmendi, P Heeman… – Proceedings of the …, 2013 – sigdial.org … V. Goffin, C. Allauzen, E. Bocchieri, D. Hakkani-Tur, A. Ljolje, S. Parthasarathy, M. Rahim, G. Riccardi, and M. Saraclar. 2005. The AT&T WATSON speech recognizer. In Proceedings of ICASSP, pages 1033–1036. James G Martin and Winifred Strange. 1968. … Cited by 3 Related articles All 11 versions

The Daemon As Educator: Ubiquitous Access to A Personal Mentor B Rosell, R Sirbu – Journal Of Systemics, Cybernetics and Informatics, 2011 – iiisci.org … machine learning), and dialog management tasks” Figure 2: AT&T WATSON Speech Technologies Chat rooms offer yet another communication pathway for sharing ideas, opinions and knowledge. A team of researchers built … Cited by 3 Related articles All 3 versions

Edit Machines for Robust Multimodal Language Processing. S Bangalore, M Johnston – EACL, 2006 – aclweb.org Page 1. Edit Machines for Robust Multimodal Language Processing Srinivas Bangalore AT&T Labs-Research 180 Park Ave Florham Park, NJ 07932 srini@research.att.com Michael Johnston AT&T Labs-Research 180 Park … Cited by 1 Related articles All 7 versions

Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition PR Dixon, T Oonishi, S Furui – Computer Speech & Language, 2009 – Elsevier In large vocabulary continuous speech recognition (LVCSR) the acoustic model computations often account for the largest processing overhead. Our weighted finite. Cited by 42 Related articles All 9 versions

Robust acoustic and semantic modeling in a telephone-based spoken dialog system. KT Mengistu – 2009 – deutsche-digitale-bibliothek.de Page 1. Robust Acoustic and Semantic Modeling in a Telephone-based Spoken Dialog System Kinfe Tadesse Mengistu (M. Sc.) Der Fakultät für Elektrotechnik und Informationstechnik der Otto-von-Guericke Universität Magdeburg zur Erlangung des akademischen Grades … Cited by 1 Related articles All 4 versions

Enhancement of Conversational Agents by Means of Multimodal Interaction R López-Cózar, Z Callejas, G Espejo… – … Agents and Natural …, 2011 – books.google.com Page 243. 223 Chapter 10 Enhancement of Conversational Agents by Means of Multimodal Interaction Ramón López-Cózar University of Granada, Spain Zoraida Callejas University of Granada, Spain Gonzalo Espejo University … All 5 versions

[BOOK] Hardware implementation of a low power speech recognition system UC Pazhayaveetil – 2007 – books.google.com Page 1. ABSTRACT PAZHAYAVEETIL, ULLAS CHANDRASEKHAR. Hardware Implementation of a Low Power Speech Recognition System. (Under the direction of Dr. Paul Franzon.) Speech is envisioned as becoming an important … Cited by 7 Related articles All 3 versions

The Business of Speech Technologies J Wilpon, ME Gilbert, J Cohen – Springer Handbook of Speech Processing, 2008 – Springer Logo Springer. Search Options: … Related articles All 2 versions

Finite-state models for speech-based search on mobile devices T Mishra, S Bangalore – Natural Language Engineering, 2011 – Cambridge Univ Press Page 1. Natural Language Engineering 17 (2): 243–264. c Cambridge University Press 2011 doi:10.1017/S1351324911000040 243 Finite-state models for speech-based search on mobile devices TANIYA MISHRA and SRINIVAS … Cited by 1 Related articles All 9 versions

[BOOK] Speech recognition co-processor D Chandra – 2007 – books.google.com Page 1. ABSTRACT CHANDRA, DHRUBA. Speech Recognition Co-processor. (Under the direction of Professor Paul D. Franzon.) With computing trend moving towards ubiquitous computing propelled by the advances in embedded … Cited by 3 Related articles All 3 versions

Bootstrapping spoken dialogue systems by exploiting reusable libraries G Di Fabbrizio, G Tur, D Hakkani-Tür… – Natural Language …, 2008 – Cambridge Univ Press … language characteristics. 3.1 Automatic speech recognition Robust speech recognition is a critical component of a spoken dialogue system. In this work, we use AT&T’s Watson Speech Recognition Engine (Goffin et al. 2005), which … Cited by 5 Related articles All 11 versions

Focusing on novelty: a crawling strategy to build diverse language models L Barbosa, S Bangalore – Proceedings of the 20th ACM international …, 2011 – dl.acm.org Page 1. Focusing on Novelty: A Crawling Strategy to Build Diverse Language Models Luciano Barbosa AT&T Labs – Research 180 Park Ave Florham Park, NJ 07932 lbarbosa@research.att.com Srinivas Bangalore AT&T Labs … Cited by 1 Related articles All 6 versions

Military Applications: Human Factors Aspects of Speech-Based Systems JM Noyes, E Haas – Speech Technology, 2010 – Springer … ICASSP 2000, vol. 3, 1277–1280. 18. Goffin, V., Allauzen, C., Bocchieri, E., Hakkani-Tür, D., Ljolje, A., Parthasarathy, S., Rahim, M., Riccardi, G., Saraclar, M. (2005). The AT&T Watson speech recogniser. In: Proc. IEEE Int. Conf. … Related articles All 4 versions

WFST enabled solutions to ASR problems: Beyond HMM decoding B Hoffmeister, G Heigold, D Rybach… – Audio, Speech, and …, 2012 – ieeexplore.ieee.org Page 1. Copyright (c) 2011 IEEE. Personal use is permitted. For any other purposes, permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Cited by 3 Related articles All 5 versions

Index-based incremental language model for scalable directory assistance A Moreno-Daniel, J Wilpon, BH Juang – Speech Communication, 2012 – Elsevier As the ubiquitous access to vast and remote information sources from portable devices becomes commonplace, the need from users to perform searches in keyboard-u. Cited by 1 Related articles All 3 versions

Glossary and Subject Index B Endres-Niggemeyer – Semantic Mashups: Intelligent Reuse of Web …, 2013 – Springer Page 348. Glossary and Subject Index Brigitte Endres-Niggemeyer Glossary and Subject Index Use The glossary lists and explains technical terms used in the book. It works as a sub- ject index, but it comes up with short descriptions … All 2 versions

Discriminative machine translation using global lexical selection S Venkatapathy, S Bangalore – ACM Transactions on Asian Language …, 2009 – dl.acm.org Page 1. 8 Discriminative Machine Translation Using Global Lexical Selection SRIRAM VENKATAPATHY IIIT-Hyderabad and SRINIVAS BANGALORE AT&T Labs-Research Statistical phrase-based machine translation models crucially rely on word alignments. … Cited by 9 Related articles

Auditory interfaces SC Peres, V Best, D Brock… – HCI Beyond the GUI: …, 2008 – books.google.com Page 167. 5 CHAPTER Auditory Interfaces S. Camille Peres, Virginia Best, Derek Brock, Barbara Shinn-Cunningham, Christopher Frauenberger, Thomas Hermann, John G. Neuhoff, Louise Valgerður Nickerson, Tony Stockman … Cited by 12 Related articles All 10 versions

Robust understanding in multimodal interfaces S Bangalore, M Johnston – Computational Linguistics, 2009 – MIT Press Page 1. Robust Understanding in Multimodal Interfaces Srinivas Bangalore ? AT&T Labs – Research Michael Johnston ?? AT&T Labs – Research Multimodal grammars provide an effective mechanism for quickly creating integration … Cited by 22 Related articles All 13 versions

Prosody and speaker state: Paralinguistics, pragmatics, and proficiency JJ Liscombe – 2007 – researchgate.net Page 1. Prosody and Speaker State: Paralinguistics, Pragmatics, and Proficiency Jackson J. Liscombe Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Graduate School of Arts and Sciences COLUMBIA UNIVERSITY 2007 Page 2. … Cited by 18 Related articles All 10 versions

[BOOK] Multimodal interaction with mobile devices: fusing a broad spectrum of modality combinations R Wasinger – 2006 – books.google.com Page 1. DISKI 305 Multi modal Interaction with Mobile Devices: Fusing a Broad Spectrum of Modality Combinations Rainer Wasinger (jj) infix Page 2. Page 3. DISKI 305 This One TfiAA-FI II-7ATF Page 4. DISKI Dissertationen … Cited by 24 Related articles All 6 versions