Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
A bitstream-based front-end for wireless speech recognition on IS-136 communications system
Autore:
Kim, HK; Cox, RV;
Indirizzi:
AT&T Labs Res, Shannon Lab, Florham Park, NJ 07932 USA AT&T Labs Res Florham Park NJ USA 07932 n Lab, Florham Park, NJ 07932 USA
Titolo Testata:
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING
fascicolo: 5, volume: 9, anno: 2001,
pagine: 558 - 568
SICI:
1063-6676(200107)9:5<558:ABFFWS>2.0.ZU;2-F
Fonte:
ISI
Lingua:
ENG
Soggetto:
QUANTIZED LSP PARAMETERS; ROBUST;
Keywords:
bitstream-based front-end; feature extraction frame erasure concealment; speech coding; speech enhancement; wireless speech recognition;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
35
Recensione:
Indirizzi per estratti:
Indirizzo: Kim, HK AT&T Labs Res, Shannon Lab, 180 Pk Ave, Florham Park, NJ 07932 USAAT&T Labs Res 180 Pk Ave Florham Park NJ USA 07932 k, NJ 07932 USA
Citazione:
H.K. Kim e R.V. Cox, "A bitstream-based front-end for wireless speech recognition on IS-136 communications system", IEEE SPEECH, 9(5), 2001, pp. 558-568

Abstract

In this paper, we propose a feature extraction method for a speech recognizer that operates in digital communication networks. The feature parametersare basically extracted by converting the quantized spectral information of a speech coder into a cepstrum, We also include the voiced/unvoiced information obtained from the bitstream of the speech coder in the recognition feature set, We performed speaker-independent connected digit HMM recognition experiments under clean, background noise, and channel impairment conditions. From these results, we found that the speech recognition system employing the proposed bitstream-based front-end gives superior word and string accuracies over a recognizer constructed from decoded speech signals, Its performance is comparable to that of a wireline recognition system that uses the cepstrum as a feature set. Next, we extended the evaluation of the proposed bitstream-based front-end to large vocabulary speech recognition with a name database, The recognition results proved that the proposed bitstream-based front-end also gives a comparable performance to the conventional wireline front-end.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 10/04/20 alle ore 15:31:46