The optimization of PLP feature extraction for LVCSR recognition of MP3 data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00219788" target="_blank" >RIV/68407700:21230/14:00219788 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

The optimization of PLP feature extraction for LVCSR recognition of MP3 data

Popis výsledku v původním jazyce

This paper analyses the contribution of optimized PLP feature extraction setup and application of feature normalization to improve the performance of automatic speech recognition system for data compressed by MP3 algorithm. The experimental study performed on loop-digit recognition and large vocabulary continues speech recognition task showed that proper setup can negate the effect of lower compression rates which can achieve results comparable with higher rates. The second finding is that the normalization techniques contribute significantly to overall performance, specially for shorter windows/shifts and lower compression rates. The acoustic models trained on 160kbits/s, 32kbits/s and 16kbits/s data performed at 34.17%, 41.88% and 36.4% WER respectively on LVCSR task. In comparison the noncompressed acoustic models performed at 28.56% WER.

Název v anglickém jazyce

The optimization of PLP feature extraction for LVCSR recognition of MP3 data

Popis výsledku anglicky

This paper analyses the contribution of optimized PLP feature extraction setup and application of feature normalization to improve the performance of automatic speech recognition system for data compressed by MP3 algorithm. The experimental study performed on loop-digit recognition and large vocabulary continues speech recognition task showed that proper setup can negate the effect of lower compression rates which can achieve results comparable with higher rates. The second finding is that the normalization techniques contribute significantly to overall performance, specially for shorter windows/shifts and lower compression rates. The acoustic models trained on 160kbits/s, 32kbits/s and 16kbits/s data performed at 34.17%, 41.88% and 36.4% WER respectively on LVCSR task. In comparison the noncompressed acoustic models performed at 28.56% WER.

Druh

D - Stať ve sborníku

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

19th International Conference on Applied Electronics 2014

ISBN

978-80-261-0276-2

ISSN

1803-7232

e-ISSN

—

Počet stran výsledku

4

Strana od-do

55-58

Název nakladatele

University of West Bohemia

Místo vydání

Pilsen

Místo konání akce

Pilsen

Datum konání akce

9. 10. 2014

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

000343819700013