Recognition of Spectrally Distorted Speech after MP3 Compression

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00220039" target="_blank" >RIV/68407700:21230/14:00220039 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Recognition of Spectrally Distorted Speech after MP3 Compression

Popis výsledku v původním jazyce

The deployment of automatic speech recognition (ASR) systems into real-life are often met with difficulties of diverse acoustic conditions. This diversity is what forces the necessity to build the systems as robust to ensure their reliable performance regardless of the conditions. The usage of MP3 compression represents one of such conditions, when the property of lossy encoding degrades the quality of extracted features and therefore the recognition. The research of optimized settings for MP3 recognition has been conducted by various authors and different solutions have been proposed. This work presents the analysis of optimized setup which was focused on blocks of feature extraction and acoustic modeling. The work summarizes the effects of methods proposed the author and other authors, all tested to determine the potential contribution of each method separately as well as in unison.

Název v anglickém jazyce

Recognition of Spectrally Distorted Speech after MP3 Compression

Popis výsledku anglicky

The deployment of automatic speech recognition (ASR) systems into real-life are often met with difficulties of diverse acoustic conditions. This diversity is what forces the necessity to build the systems as robust to ensure their reliable performance regardless of the conditions. The usage of MP3 compression represents one of such conditions, when the property of lossy encoding degrades the quality of extracted features and therefore the recognition. The research of optimized settings for MP3 recognition has been conducted by various authors and different solutions have been proposed. This work presents the analysis of optimized setup which was focused on blocks of feature extraction and acoustic modeling. The work summarizes the effects of methods proposed the author and other authors, all tested to determine the potential contribution of each method separately as well as in unison.

Druh

O - Ostatní výsledky

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