| other,44-3-H92-1003,bq | in a <term> multi-site common evaluation of | speech | , natural language and spoken language | #18610 We summarize the motivation for this effort, the goals, the implementation of a multi-site data collection paradigm, and the accomplishments of MADCOW in monitoring the collection and distribution of 12,000 utterances of spontaneous speech from five sites for use in a multi-site common evaluation of speech, natural language and spoken language |
| other,15-1-H92-1010,bq | </term><term> LIMSI </term> in the field of <term> | speech | processing </term> , but also in the related | #18632 The paper provides an overview of the research conducted at LIMSI in the field ofspeech processing, but also in the related areas of Human-Machine Communication, including Natural Language Processing, Non Verbal and Multimodal Communication. |
| measure(ment),16-3-H92-1016,bq | modifications combined to reduce the <term> | speech | recognition word and sentence error rates | #18753 Together with the use of a larger training set, these modifications combined to reduce thespeech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on the October '91 test set. |
| tech,17-3-H92-1036,bq | unified approach for the following four <term> | speech | recognition </term> applications , namely | #19116 Because of its adaptive nature, Bayesian learning serves as a unified approach for the following fourspeech recognition applications, namely parameter smoothing, speaker adaptation, speaker group modeling and corrective training. |
| tool,11-1-H92-1074,bq | corpus </term> represents a new <term> DARPA | speech | recognition technology </term> development | #19538 The CSR (Connected Speech Recognition) corpus represents a new DARPA speech recognition technology development initiative to advance the state of the art in CSR. |
| tool,16-2-H92-1074,bq | corpus </term> that has fueled <term> DARPA | speech | recognition technology </term> development | #19570 This corpus essentially supersedes the now old Resource Management (RM) corpus that has fueled DARPA speech recognition technology development for the past 5 years. |
| other,18-3-H92-1074,bq | natural grammar </term> , and <term> spontaneous | speech | </term> . This paper presents an overview | #19599 The new CSR corpus supports research on major new problems including unlimited vocabulary, natural grammar, and spontaneous speech. |
| tech,28-1-H92-1095,bq | <term> language understanding </term> with <term> | speech | recognition </term> , <term> knowledge-based | #19665 Language understanding work at Paramax focuses on applying general-purpose language understanding technology to spoken language understanding, text understanding, and document processing, integrating language understanding withspeech recognition, knowledge-based information retrieval and image understanding. |
| tech,5-1-C94-1030,bq | character recognition </term> and <term> continuous | speech | recognition </term> of a <term> natural language | #20619 In optical character recognition and continuous speech recognition of a natural language, it has been difficult to detect error characters which are wrongly deleted and inserted. |
| other,26-2-H94-1034,bq | <term> likely repair </term> or as <term> fluent | speech | </term> . Other contextual clues , such as | #21332 The tagger is given knowledge about category transitions for speechrepairs, and so is able to mark a transition either as a likely repair or as fluent speech. |
