Papers

• A list of publications online is available here.

Resources

• The CMU Dictionary for downloading or querying.
• A set of speech coding algorithms.
• The CMU Statistical Language Modeling Toolkit (CMU SLM).
• Error Region Analysis (ERA). Error-responsive feedback for speech recognizers.
• Carnegie Mellon Portable Speech Library
• Papers and recent results available online.
• The CMU mirror of the comp.speech FAQ.
  • Note that this website is defunct: it's here for archival purposes. comp.speech discussions have migrated to other fora. For example you'll find some on Google. There is a Sphinx-related resource at SourceForge, and there are also several groups, e.g., on LinkedIn.
• Grammatical Trigrams and Link Grammar page.
• CMU AI Repository: Speech Recognition and Synthesis section.
• A list of Macintosh speech and sound-related resources maintained locally.

Related pages at CMU

• CMU School of Computer Science (SCS).
• The Robotics Institute (RI).
• Human-Computer Interaction Institute (HCII).
• Information Networking Institute (INI).
• Software Engineering Institute (SEI).

Other Resources

• Usenet
  • comp.speech newsgroup.
  • comp.speech archive
  • FAQ Web sites
    • United States: Carnegie Mellon University.
    • Britain: Cambridge University.
  • comp.speech FAQ.
  • comp.compression FAQ.
  • comp.dsp FAQ.
• Surveys, books, tutorials, etc.
  • Sphinx Manual, Sphinx tips, mainly the trainer, but interesting pointers on how to use the whole system.
  • Journal on Negative Results in Speech Research.
  • Survey of the State of the Art of Human Language Technology, a collection of articles by 97 authors online.
  • How to use speech recognition systems, a useful link from the land Down Under.
  • Cambridge University's HMM Toolkit (HTK).
  • Speech Signal Processing Toolkit (SPTK).
  • HMM-based Speech Synthesis System (HTS).
• Other speech labs & related web sites
  • Lehrstuhl für Informatik VI at RWTH Aachen (H. Ney)
  • The Acoustical Society of America (ASA).
  • Speech at Apple Computer.
  • ATR, Japan.
  • Speech at BBN.
  • ICSI Speech Group at Berkeley.
  • Infopad at Berkeley.
  • The Laboratory for Engineering Man/Machine Systems at Brown University.
  • Speech Vision and Robotics Group (SVR) at Cambridge University Engineering Department (CUED).
  • Cepstral, LLC Voice building, speech synthesis
  • Digital Speech Processing at Arizona State University.
  • Institute of Speech Communication (ICP) in Grenoble, main page in French.
  • The Institute of Electronics, Information and Communication Engineers (IEICE).
  • International Speech Communication Association (ISCA), previously known as ESCA (European SCA).
  • IP Bridges LLC., Open Source VOIP solutions.
  • Center for Language and Speech Processing at Johns Hopkins University.
  • Speech Group at K.U.Leuven, Belgium.
  • KTH Department of Speech Communication and Music Acoustics, Sweden.
  • LIMSI, France.
  • Speech Recognition at LumenVox
  • Music, Mind and Machine Group at the MIT Media Lab.
  • The Spoken Language Systems Group (SLS) at MIT.
  • Microsoft Speech Research Group.
  • National Institute of Standards and Technology's Speech Group (NIST), USA.
  • A Speech Codecs page.
  • Speech Communication, ISCA's Journal.
  • Institute for Signal and Information Processing (ISIP) at Mississippi State University.
  • Center for Spoken Language Understanding (CSLU) at Oregon Graduate Institute (OGI).
  • C. Pallier's psycholinguistic links.
  • Philips Speech Processing.
  • Speech at Purdue University.
  • Research Lab, Inc.
  • Signal Processing Information Base (SPIB) at Rice.
  • CAIP, the Center for Computer Aids for Industrial Productivity, Speech and Language Processing Lab., at Rutgers University.
  • Speech Processing Lab at Shariff University of Technology, Iran.
  • Institute for Language, Speech and Hearing (ILASH) at Sheffield, UK.
  • Speech and Hearing Research Group at Sheffield, UK.
  • Speech Technology and Research at SRI.
  • Center for the Study of Language and Information (CSLI), Stanford.
  • Center for Computer Research in Music and Acoustics (CCRMA), Stanford.
  • Speech Integration Group at Sun Microsystems.
  • Telefónica Investigación y Desarrollo (Spain's Telefónica).
  • Grupo de Tecnología del Habla, GTH (Speech Technology Group) at Universidad Politécnica de Madrid (Technical University at Madrid), Spain.
  • Dept. of Electronics and Information Systems (ELIS) at the Universiteit Gent, in Belgium.
  • ASEL Speech Research Program at the University of Delaware.
  • Speech Processing and Auditory Perception Laboratory, UCLA.
  • UCSC collection of speech starting points at UCSC PSL.
  • Speech Communication Lab at the University of Maryland College Park.
  • Language and Speech at University of Nijmegen, Netherlands.
  • The TRAINS project at the University of Rochester.
  • Speech Analysis and Interpretation Lab at USC Viterbi School of Engineering.
  • Language Technology Research Group and a How-to guide about speech recognition at the University of Sydney, Australia.
  • The Signal, Speech and Language Interpretation Lab (SSLI) at the University of Washington.
  • Vocollect, Inc.
  • Voice Signal Technology
  • Laboratory for Digital Speech and Audio Processing at the Vrije Universiteit Brussel, Belgium.
  • YorkTalk

  
  New Links: (still sorting)

  • Institute for Robotics and Intelligent Systems (IRIS at Precarn Inc.).
  • Multitel-TCTS Lab.
  • Duisburg Universität.
  • Institut de Recherche en Informatique de Toulouse
  • The Australian Speech Science and Technology members.
  • Centre for Intelligent Information Processing Systems.
  • Spoken Language Working Group of the Expert Advisory Group on Language Engineering Standards (EAGLES)
  • Center for PersonKommunikation at the Aalborg University, Denmark.
  • Signal Processing Lab at Griffith University in Australia.