Home Catalogue search

eng

Refine your search:

Search in the Catalogues and Directories






	Sort by
Simple Search

Hits 1 – 14 of 14

1	Robust Continuous Speech Recognition.
	Makhoul, J.; Schwartz, R.
	In: DTIC AND NTIS (1994)
	BASE
	Show details

2	Usable, Real-Time, Interactive Spoken Language Systems
	Makhoul, J.; Bates, M.
	In: DTIC AND NTIS (1994)
	BASE
	Show details

3	Comparative Experiments on Large Vocabulary Speech Recognition
	Schwartz, Richard; Anastasakos, Tasos; Kubala, Francis...
	In: DTIC (1993)
	BASE
	Show details

4	BBN BYBLOS and HARC February 1992 ATIS Benchmark Results
	Kubala, Francis; Barry, Chris; Bates, Madeleine...
	In: DTIC (1992)
	BASE
	Show details

5	Development of a Spoken Language System
	Austin, S.; Ayuso, D.; Barry, C....
	In: DTIC AND NTIS (1992)
	BASE
	Show details

6	Continuous Speech Recognition Using Segmental Neural Nets
	Austin, S.; Makhoul, J.; Schwartz, R....
	In: DTIC (1991)
	BASE
	Show details

7	Byblos Speech Recognition Benchmark Results
	Kubala, F.; Austin, S.; Barry, C....
	In: DTIC (1991)
	BASE
	Show details

8	Toward a Real-Time Spoken Language System Using Commercial Hardware
	Austin, Steve; Peterson, Pat; Placeway, Paul...
	In: DTIC (1990)
	BASE
	Show details

9	Improvements in the BYBLOS Continuous Speech Recognition System
	Schwartz, R.; Austin, S.; Barry, C....
	In: DTIC AND NTIS (1990)
	BASE
	Show details

10	Development of a Spoken Language System
	Makhoul, John
	In: DTIC AND NTIS (1990)
	BASE
	Show details

11	The BBN Spoken Language System
	Boisen, Sean; Chow, Yen-Lu; Haas, Andrww...
	In: DTIC (1989)
	BASE
	Show details

12	Integration of Speech and Natural Language
	Boisen, S.; Chow, Y.; Haas, A....
	In: DTIC AND NTIS (1989)
	BASE
	Show details

13	Combining Multiple Knowledge Sources for Continuous Speech Recognition
	Kimball, O.; Derr, A.; Chow, Y-L.; Schwartz, R.; Barry, C.
	In: DTIC AND NTIS (1989)
	Abstract: The objective of this project has been to develop methods and techniques to coordinate the many sources of knowledge in the decision for a continuous speech recognition system. This effort includes finding methods for effectively combining information from various knowledge sources, and for developing recognition search strategies that find the most likely word sequence, given the input speech. These search strategies must consider a very large number of word-sequence hypotheses in a computationally efficient manner. To develop and demonstrate these techniques, we designed and implemented a complete word recognition system for continuous speech which is capable of incorporating knowledge from several sources, including lexical, phonetic, phonological, and grammatical knowledge. The complete system called BYBLOS, has been shown to achieve the highest recognition accuracy to date on standard government tests using a 1000-word continuous speech corpus.
	Keyword: MARKOV PROCESSES; SPEECH RECOGNITION; *VOICE COMMUNICATIONS; ACCURACY; ADAPTATION; CONTINUOUS SPEECH RECOGNITION; COORDINATES; Cybernetics; DATA BASES; HIDDEN MARKOV MODELS; INPUT; LANGUAGE MODELLING; MATHEMATICAL MODELS; RECOGNITION; SEARCHING; SEQUENCES; SPEAKER ADAPTATION; SPEECH; SPEECH DATABASE; STANDARDIZATION; STRATEGY; TEST METHODS; Voice Communications; WORD RECOGNITION; WORDS(LANGUAGE)
	URL: http://www.dtic.mil/docs/citations/ADA212368 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA212368
	BASE
	Hide details

14	Combining Multiple Knowledge Sources for Speech Recognition
	Schwartz, Richard; Makhoul, John
	In: DTIC AND NTIS (1988)
	BASE
	Show details

© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern