aalto1 untyped-item.component.html

Vocal effort compensation for MFCC feature extraction in a shouted versus normal speaker recognition task

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Authors

Jokinen, Emma
Saeidi, Rahim
Kinnunen, Tomi
Alku, Paavo

Major/Subject

Mcode

Degree programme

Language

en

Pages

11

Series

Computer Speech and Language, Volume 53, pp. 1-11

Abstract

In shouting, speakers use increased vocal effort to convey spoken messages over distance or above environmental noise. For automatic speaker recognition systems trained using normal speech, shouting causes a severe vocal effort mismatch between the enrollment and test hence reducing the recognition performance. In this study, two compensation methods are proposed to tackle the mismatch in a shouted versus normal speaker recognition task. These techniques are applied in the feature extraction stage of a speaker recognition system to modify the spectral envelopes of shouts to be closer to those in normal speech. The techniques modify the all-pole power spectrum of the MFCC computation chain with shouted-to-normal compensation filtering that is obtained using a GMM-based statistical mapping. In an evaluation using the state-of-the-art i-vector based recognition system, the proposed techniques provided considerable improvements in identification rates compared to the case when shouted speech spectra were not processed.

Description

Other note

Citation

Jokinen, E, Saeidi, R, Kinnunen, T & Alku, P 2019, 'Vocal effort compensation for MFCC feature extraction in a shouted versus normal speaker recognition task', Computer Speech and Language, vol. 53, pp. 1-11. https://doi.org/10.1016/j.csl.2018.06.002

Endorsement

Review

Supplemented By

Referenced By