TOOLS FOR RESEARCH AND EDUCATION IN SPEECH SCIENCE

The Center for Spoken Language Understanding (CSLU) provides free language resources to researchers and educators in all areas of speech and hearing science. These resources are of great potential value to speech scientists for analyzing speech, for diagnosing and treating speech and language problems, for researching and evaluating language technologies, and for training students in the theory and practice of speech science. This article describes language resources from CSLU, and some of the ways in which these resources can be used. 1. ACCESSIBLE LANGUAGE RESOURCES In 1991, the Center for Spoken Language Understanding received a grant from the National Science Foundation to develop the OGI speech tools—free software for analyzing, displaying and transcribing speech [1]. Since that time, CSLU has been developing and distributing free language resources to interested users in educational and other not-for-profit institutions. The original OGI speech tools have been transformed into the CSLU Toolkit, a comprehensive set of tools and technologies supporting research, development and education in speech and language technologies. In addition to software tools, CSLU has developed a large number of speech corpora to support basic research and development of language technologies and systems. These language resources—software tools and corpora—have been distributed to over 2000 sites in 65 countries, and have supported research reported in over 300 publications. In this article I describe these resources and how they might benefit educators, practitioners and researchers in speech and language science.

[1]  Yonghong Yan,et al.  Accessible technology for interactive systems: a new approach to spoken language research , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[2]  John-Paul Hosom,et al.  A computer-based course in spectrogram reading , 1999 .

[3]  Ronald A. Cole,et al.  A laboratory course for designing and testing spoken dialogue systems , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[4]  Ronald A. Cole,et al.  An interactive environment for speech recognition research , 1992, ICSLP.

[5]  Ronald A. Cole,et al.  Evaluation and integration of neural-network training techniques for continuous digit recognition , 1998, ICSLP.

[6]  Michael Johnston,et al.  PROFER: predictive, robust finite-state parsing for spoken language , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[7]  Ronald A. Cole,et al.  Building 10,000 spoken dialogue systems , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[8]  Yonghong Yan,et al.  Universal speech tools: the CSLU toolkit , 1998, ICSLP.

[9]  Pieter J. E. Vermeulen,et al.  CSLUsh: an extendible research environment , 1997, EUROSPEECH.

[10]  Ronald A. Cole,et al.  Labeler agreement in phonetic labeling of continuous speech , 1994, ICSLP.

[11]  Ronald A. Cole,et al.  Bringing spoken language systems to the classroom , 1997, EUROSPEECH.

[12]  Ronald A. Cole,et al.  Connected digit recognition experiments with the OGI Toolkit's neural network and HMM-based recognizers , 1998, Proceedings 1998 IEEE 4th Workshop Interactive Voice Technology for Telecommunications Applications. IVTTA '98 (Cat. No.98TH8376).

[13]  D. Massaro.  Perceiving talking faces: from speech perception to a behavioral principle , 1999 .

[14]  D. Massaro,et al.  Perceiving Talking Faces , 1995 .

[15]  Ronald A. Cole,et al.  Creating a mexican Spanish version of the CSLU toolkit , 1998, ICSLP.

[16]  R. J. Lickley,et al.  Proceedings of the International Conference on Spoken Language Processing. , 1992 .