Advanced Acoustic Modelling Techniques in MP3 Speech Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00230829" target="_blank" >RIV/68407700:21230/15:00230829 - isvavai.cz</a>

Výsledek na webu

<a href="http://asmp.eurasipjournals.com/content/2015/1/20" target="_blank" >http://asmp.eurasipjournals.com/content/2015/1/20</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1186/s13636-015-0064-7" target="_blank" >10.1186/s13636-015-0064-7</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Advanced Acoustic Modelling Techniques in MP3 Speech Recognition

Popis výsledku v původním jazyce

The automatic recognition of MP3 compressed speech presents a challenge to the current systems due to the lossy nature of compression which causes irreversible degradation of the speech wave. This article evaluates the performance of a recognition systemoptimized for MP3 compressed speech with current state-of-the-art acoustic modelling techniques and one specific front-end compensation method. The article concentrates on acoustic model adaptation, discriminative training and additional dithering as aprominent means of compensating for the described distortion in the task of phoneme and large vocabulary continuous speech recognition (LVCSR). The experiments presented on the phoneme task show a dramatic increase of the recognition error for unvoiced speech units as a direct result of compression. The application of acoustic model adaptation has proved to yield the highest relative contribution while the gain of discriminative training diminished with decreasing bit-rate. The applicati

Název v anglickém jazyce

Advanced Acoustic Modelling Techniques in MP3 Speech Recognition

Popis výsledku anglicky

The automatic recognition of MP3 compressed speech presents a challenge to the current systems due to the lossy nature of compression which causes irreversible degradation of the speech wave. This article evaluates the performance of a recognition systemoptimized for MP3 compressed speech with current state-of-the-art acoustic modelling techniques and one specific front-end compensation method. The article concentrates on acoustic model adaptation, discriminative training and additional dithering as aprominent means of compensating for the described distortion in the task of phoneme and large vocabulary continuous speech recognition (LVCSR). The experiments presented on the phoneme task show a dramatic increase of the recognition error for unvoiced speech units as a direct result of compression. The application of acoustic model adaptation has proved to yield the highest relative contribution while the gain of discriminative training diminished with decreasing bit-rate. The applicati

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název periodika

EURASIP Journal on Audio Speech and Music Processing

ISSN

1687-4722

e-ISSN

—

Svazek periodika

2015:20

Číslo periodika v rámci svazku

July

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

7

Strana od-do

—

Kód UT WoS článku

000358610600001

EID výsledku v databázi Scopus

—