Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Separation of speech from interfering sounds based on oscillatory correlation
Autore:
Wang, DLL; Brown, GJ;
Indirizzi:
Ohio State Univ, Dept Comp & Informat Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 nformat Sci, Columbus, OH 43210 USA Ohio State Univ, Ctr Cognit Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 Cognit Sci, Columbus, OH 43210 USA Univ Sheffield, Dept Comp Sci, Sheffield S8 0ET, S Yorkshire, England UnivSheffield Sheffield S Yorkshire England S8 0ET S Yorkshire, England
Titolo Testata:
IEEE TRANSACTIONS ON NEURAL NETWORKS
fascicolo: 3, volume: 10, anno: 1999,
pagine: 684 - 697
SICI:
1045-9227(199905)10:3<684:SOSFIS>2.0.ZU;2-G
Fonte:
ISI
Lingua:
ENG
Soggetto:
DIFFERENT FUNDAMENTAL FREQUENCIES; INFERIOR COLLICULUS; NEURAL OSCILLATORS; CONCURRENT VOWELS; COCHLEAR NUCLEUS; AUDITORY-CORTEX; SEGREGATION; MODEL; CAT; INTEGRATION;
Keywords:
auditory scene analysis; harmonicity; oscillatory correlation; speech segregation; stream segregation;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
57
Recensione:
Indirizzi per estratti:
Indirizzo: Wang, DLL Ohio State Univ, Dept Comp & Informat Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 i, Columbus, OH 43210 USA
Citazione:
D.L.L. Wang e G.J. Brown, "Separation of speech from interfering sounds based on oscillatory correlation", IEEE NEURAL, 10(3), 1999, pp. 684-697

Abstract

A multistage neural model is proposed for an auditory scene analysis task-segregating speech from interfering sound sources. The core of the model isa two-layer oscillator network that performs stream segregation on the basis of oscillatory correlation. In the oscillatory correlation framework, a stream is represented by a population of synchronized relaxation oscillators, each of which corresponds to an auditory feature, and different streams are represented by desynchronized oscillator populations. Lateral connections between oscillators encode harmonicity, and proximity in frequency and time. Prior to the oscillator network are a model of the auditory periphery and a stage in which mid-level auditory representations are formed. The model has been systematically evaluated using: a corpus of voiced speech mixedwith interfering sounds, and produces improvements in terms of signal-to-noise ratio for every mixture. The performance of our model is compared withother studies on computational auditory scene analysis. A number of issuesincluding: biological plausibility and real-time implementation are also discussed.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 14/08/20 alle ore 16:07:01