Robust recognition of strongly distorted speech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00313559" target="_blank" >RIV/68407700:21230/17:00313559 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Robust recognition of strongly distorted speech

Popis výsledku v původním jazyce

This thesis is focused on the compensation methods for strongly distorted speech working at the level of front-end processing and acoustic modelling, whose aim is to compensate the degradation introduced by a distant microphone, noisy environments and a lossy compression. The techniques for noisy and distant speech recognition studied in this thesis were focused on front-end noise suppression techniques, feature normalization techniques, acoustic model adaptations and discriminative training. The experiments have proved, that extended spectral subtraction can bring significant improvement even for the state-of-the-art systems in public environments with a strong noise and for a far-distance microphone recordings. The evaluation of compressed speech recognition examined the degrading effects of lossy compression on fundamental frequency, formants and smoothed LPC spectrum and for standard MFCC and PLP features used for ASR. The low-pass filtering and the areas of very low energy in a spectrogram were identified as the two main reasons of degradation. The practical experiments evaluated the contributions of specific feature extraction setups, combinations of normalization and compensation techniques, supervised and unsupervised adaptation and discriminative training methods and finally the matched training. The largest contributions were gained from the application of adaptation techniques, subspace GMM and discriminative training. A novel algorithm named Spectrally selective dithering (SSD) was proposed within this thesis, which compensated the effect of spectral valleys. The contribution of said algorithm was verified for both GMM-HMM and DNN-HMM speech recognition systems.

Název v anglickém jazyce

Robust recognition of strongly distorted speech

Popis výsledku anglicky

This thesis is focused on the compensation methods for strongly distorted speech working at the level of front-end processing and acoustic modelling, whose aim is to compensate the degradation introduced by a distant microphone, noisy environments and a lossy compression. The techniques for noisy and distant speech recognition studied in this thesis were focused on front-end noise suppression techniques, feature normalization techniques, acoustic model adaptations and discriminative training. The experiments have proved, that extended spectral subtraction can bring significant improvement even for the state-of-the-art systems in public environments with a strong noise and for a far-distance microphone recordings. The evaluation of compressed speech recognition examined the degrading effects of lossy compression on fundamental frequency, formants and smoothed LPC spectrum and for standard MFCC and PLP features used for ASR. The low-pass filtering and the areas of very low energy in a spectrogram were identified as the two main reasons of degradation. The practical experiments evaluated the contributions of specific feature extraction setups, combinations of normalization and compensation techniques, supervised and unsupervised adaptation and discriminative training methods and finally the matched training. The largest contributions were gained from the application of adaptation techniques, subspace GMM and discriminative training. A novel algorithm named Spectrally selective dithering (SSD) was proposed within this thesis, which compensated the effect of spectral valleys. The contribution of said algorithm was verified for both GMM-HMM and DNN-HMM speech recognition systems.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

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