DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 24

1
A Hybrid Segmental Neural Net/Hidden Markov Model System for Continuous Speech Recognition
In: Institute of Electrical and Electronics Engineers. IEEE transactions on speech and audio processing. - New York, NY : Inst. 2 (1994) 1, 151-160
OLC Linguistik
Show details
2
On Using Written Language Training Data for Spoken Language Modeling
In: DTIC (1994)
BASE
Show details
3
Robust Continuous Speech Recognition.
In: DTIC AND NTIS (1994)
BASE
Show details
4
Usable, Real-Time, Interactive Spoken Language Systems
In: DTIC AND NTIS (1994)
BASE
Show details
5
Development of a Spoken Language System
In: DTIC AND NTIS (1992)
BASE
Show details
6
BBN HARC and DELPHI Results on the ATIS Benchmarks - February 1991
In: DTIC (1991)
BASE
Show details
7
Continuous Speech Recognition Using Segmental Neural Nets
In: DTIC (1991)
BASE
Show details
8
Byblos Speech Recognition Benchmark Results
In: DTIC (1991)
BASE
Show details
9
Systems
Kimball, O.A. (Mitarb.); Krasner, M.A. (Mitarb.); Kubala, G.F. (Mitarb.)...
In: Readings in speech recognition. - San Mateo, Calif. : Kaufmann (1990), 551-618
BLLDB
Show details
10
Improvements in the BYBLOS Continuous Speech Recognition System
In: DTIC AND NTIS (1990)
Abstract: The objective of this research was to develop accurate mathematical models of speech sounds for the purpose of large-vocabulary continuous speech recognition. The research focussed on three areas: developing better speech models to improve recognition accuracy, exploring new techniques for speaker-independent training, and developing speaker adaptation techniques that allow system use with a minimum of training. The work was performed within the BBN BYBLOS speech recognition system, which is based on the use of phonetic hidden Markov models. As a result of several model improvements, we have succeeded in decreasing the word rate by a factor of four for speaker-dependent and speaker- independent recognition. In speaker-independent recognition, we developed a new training paradigm in which we record speech from only a dozen speakers instead of the traditional approach of recording more than a hundred speakers. The same approach has been shown to be useful for effective speaker adaptation with only two minutes of speech training.
Keyword: *MATHEMATICAL MODELS; ACCURACY; ADAPTATION; BYBLOS SPEECH RECOGNITION; CONTINUOUS SPEECH RECOGNITION; Cybernetics; MARKOV PROCESSES; MODELS; RATES; RECOGNITION; RECORDING SYSTEMS; SOUND; SPEAKER ADAPTATION; SPEAKER INDEPENDENT RECOGNITION; SPEECH; SPEECH RECOGNITION; TRAINING; Voice Communications; WORDS(LANGUAGE)
URL: http://www.dtic.mil/docs/citations/ADA230126
http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA230126
BASE
Hide details
11
Acoustic-phonetic decoding of speech
In: Recent advances in speech understanding and dialog systems (Berlin [etc.], 1988), P.25-50
MPI für Psycholinguistik
Show details
12
Speech Communication
Stevens, Kenneth N.; Allen, Jonathan; Halle, Morris. - : Research Laboratory of Electronics (RLE) at the Massachusetts Institute of Technology (MIT), 1987
BASE
Show details
13
Research in Continuous Speech Recognition
In: DTIC AND NTIS (1984)
BASE
Show details
14
Research in Continuous Speech Recognition.
In: DTIC AND NTIS (1983)
BASE
Show details
15
Medium and low bit rate speech transmission
In: Automatic speech analysis and recognition (Dordrecht, 1982), p. 21-48
MPI für Psycholinguistik
Show details
16
Speech Compression and Synthesis.
In: DTIC AND NTIS (1979)
BASE
Show details
17
Speech Compression and Synthesis
In: DTIC AND NTIS (1979)
BASE
Show details
18
Speech Compression and Synthesis
In: DTIC AND NTIS (1979)
BASE
Show details
19
Speech Compression and Synthesis
In: DTIC AND NTIS (1978)
BASE
Show details
20
Speech Compression and Synthesis
In: DTIC AND NTIS (1978)
BASE
Show details

Page: 1 2

Catalogues
0
0
1
0
0
0
0
Bibliographies
2
0
0
0
0
0
0
0
3
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
18
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern