The SpeechMap Project

The SpeechMap Project

The STC is working with the USPTO to develop a prior art library pulling together the decades of work in the speech industry and indexing it in ways to faciltiate prior art search.

By using a faceted indexing approach to organizing the materials, SpeechMap can capture not only the content, but also the context by including facets such as the applications of the technology, the research or development group it was done by, and the speech system in which the technique was implemented.

Your Mobile Virtual Assistant Just Got Smarter!

Gilbert, M, Arizmendi I, Bocchieri E, Caseiro D, Goffin V, Ljolje A, Phillips M, Wang C, Wilpon J.  2011.  Your Mobile Virtual Assistant Just Got Smarter!. Twelfth Annual Conference of the International Speech Communication Association.

Contextual information improves oov detection in speech

Parada, C, Dredze M, Filimonov D, Jelinek F.  2010.  Contextual information improves oov detection in speech. Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. :216–224.

Leveraging multiple query logs to improve language models for spoken query recognition

Li, X, Nguyen P, Zweig G, Bohus D.  2009.  Leveraging multiple query logs to improve language models for spoken query recognition. Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on. :3713–3716.

Robust understanding in multimodal interfaces

Bangalore, S, Johnston M.  2009.  Robust understanding in multimodal interfaces. Computational Linguistics. 35:345–397.
Syndicate content