DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 24

1
Authors' Responses - Regularities in motion: Apparent, real, and internalized
In: Behavioral and brain sciences. - New York, NY [u.a.] : Cambridge Univ. Press 24 (2001) 4, 757-761
OLC Linguistik
Show details
2
Evolutionary internalized regularities
In: Behavioral and brain sciences. - New York, NY [u.a.] : Cambridge Univ. Press 24 (2001) 4, 626-628
OLC Linguistik
Show details
3
Spatial cues in the cinematic discourse: Selection, function and style in Jurassic Park and Prospero's Books
In: Journal of pragmatics. - Amsterdam [u.a.] : Elsevier 26 (1996) 6, 767-792
OLC Linguistik
Show details
4
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
5
On Using Written Language Training Data for Spoken Language Modeling
In: DTIC (1994)
BASE
Show details
6
Robust Continuous Speech Recognition.
In: DTIC AND NTIS (1994)
BASE
Show details
7
BBN HARC and DELPHI Results on the ATIS Benchmarks - February 1991
In: DTIC (1991)
BASE
Show details
8
Continuous Speech Recognition Using Segmental Neural Nets
In: DTIC (1991)
Abstract: We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in continuous speech recognition. The SNN takes as input all the frames of a phonetic segment and gives as output an estimate of the probability of each of the phonemes, given the input segment. By tak- ing into account all the frames of a phonetic seg- ment simultaneously, the SNN overcomes the well- known conditional-independence limitation of hid- den Markov models (HMM). However, the prob- lem of automatic segmentation with neural nets is a formidable computing task compared to HMMs. Therefore, to take advantage of the training and decoding speed of HMMs, we have developed a novel hybrid SNN/HMM system that combines the advantages of both types of approaches. In this hy- brid system, use is made of the N-best paradigm to generate likely phonetic segmentations, which are then scored by the SNN. The HMM and SNN scores are then combined to optimize performance. In this manner, the recognition accuracy is guaran- teed to be no worse than the HMM system alone.
Keyword: *SPEECH RECOGNITION; HMM(HIDDEN MARKOV MODELS); MARKOV PROCESSES; MATHEMATICAL MODELS; NEURAL NETS; PHONETICS; SEGMENTED; SNN(SEGMENTAL NEURAL NET); Voice Communications
URL: http://www.dtic.mil/docs/citations/ADA460342
http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA460342
BASE
Hide details
9
Byblos Speech Recognition Benchmark Results
In: DTIC (1991)
BASE
Show details
10
Improvements in the BYBLOS Continuous Speech Recognition System
In: DTIC AND NTIS (1990)
BASE
Show details
11
Combining Multiple Knowledge Sources for Continuous Speech Recognition
In: DTIC AND NTIS (1989)
BASE
Show details
12
Statistical Modeling for Continuous Speech Recognition
In: DTIC AND NTIS (1988)
BASE
Show details
13
Robust Coarticulatory Modeling for Continuous Speech Recognition.
In: DTIC AND NTIS (1986)
BASE
Show details
14
Research in Continuous Speech Recognition
In: DTIC AND NTIS (1984)
BASE
Show details
15
Linguistic innateness and its evidence
In: Language in primates (New York, 1983), p. 125-136
MPI für Psycholinguistik
Show details
16
Talk to the animals
In: Language in primates (New York, 1983), p. 137-145
MPI für Psycholinguistik
Show details
17
Research in Continuous Speech Recognition.
In: DTIC AND NTIS (1983)
BASE
Show details
18
Imagery : there's more to it than meets the eye
In: Imagery (Cambridge, Mass., 1981), P.109-130
MPI für Psycholinguistik
Show details
19
Speech Compression and Synthesis.
In: DTIC AND NTIS (1979)
BASE
Show details
20
Speech Compression and Synthesis
In: DTIC AND NTIS (1979)
BASE
Show details

Page: 1 2

Catalogues
0
0
4
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
4
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
16
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern