Show simple item record

dc.contributor.authorHochberg, Mike
dc.contributor.authorRenals, Steve
dc.date.accessioned2006-05-26T12:13:20Z
dc.date.available2006-05-26T12:13:20Z
dc.date.issued1999
dc.identifier.citationIEEE Trans. on Speech and Audio Processing, 7:542-553, 1999.en
dc.identifier.urihttp://hdl.handle.net/1842/1185
dc.description.abstractIn this paper, we present a novel, efficient search strategy for large vocabulary continuous speech recognition. The search algorithm, based on a stack decoder framework, utilizes phone-level posterior probability estimates (produced by a connectionist/HMM acoustic model) as a basis for phone deactivation pruning - a highly efficient method of reducing the required computation. The single-pass algorithm is naturally factored into the time-asynchronous processing of the word sequence and the time-synchronous processing of the HMM state sequence. This enables the search to be decoupled from the language model while still maintaining the computational benefits of time-synchronous processing. The incorporation of the language model in the search is discussed and computationally cheap approximations to the full language model are introduced. Experiments were performed on the North American Business News task using a 60,000 word vocabulary and a trigram language model. Results indicate that the computational cost of the search may be reduced by more than a factor of 40 with a relative search error of less than 2% using the techniques discussed in the paper.en
dc.format.extent129971 bytes
dc.format.extent346491 bytes
dc.format.mimetypeapplication/octet-stream
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherIEEEen
dc.titleStart-synchronous search for large vocabulary continuous speech recognition.en
dc.typeArticleen


Files in this item

This item appears in the following Collection(s)

Show simple item record