Analysis of impact of emotions on target speech extraction and speech separation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU146144" target="_blank" >RIV/00216305:26230/22:PU146144 - isvavai.cz</a>

Result on the web

<a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9914718" target="_blank" >https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9914718</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IWAENC53105.2022.9914718" target="_blank" >10.1109/IWAENC53105.2022.9914718</a>

Result language

angličtina

Original language name

Analysis of impact of emotions on target speech extraction and speech separation

Original language description

Recently, the performance of blind speech separation (BSS) and target speech extraction (TSE) has greatly progressed. Most works, however, focus on relatively well-controlled conditions using, e.g., read speech. The performance may degrade in more realistic situations. One of the factors causing such degradation may be intrinsic speaker variability, such as emotions, occurring commonly in realistic speech. In this paper, we investigate the influence of emotions on TSE and BSS. We create a new test dataset of emotional mixtures for the evaluation of TSE and BSS. This dataset combines LibriSpeech and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS). Through controlled experiments, we can analyze the impact of different emotions on the performance of BSS and TSE.We observe that BSS is relatively robust to emotions, while TSE, which requires identifying and extracting the speech of a target speaker, is much more sensitive to emotions. On comparative speaker verification experiments we show that identifying the target speaker may be particularly challenging when dealing with emotional speech. Using our findings, we outline potential future directions that could improve the robustness of BSS and TSE systems toward emotional speech.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/LTAIN19087" target="_blank" >LTAIN19087: Multi-linguality in speech technologies</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2022

Confidentiality

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

Article name in the collection

Proceedings of The 17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022)

ISBN

978-1-6654-6867-1

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

1-5

Publisher name

IEEE Signal Processing Society

Place of publication

Bamberg

Event location

Bamberg

Event date

Sep 5, 2022

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—