Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F24%3APU155583" target="_blank" >RIV/00216305:26230/24:PU155583 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10446130" target="_blank" >https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10446130</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers
Original language description
Traditionally, automatic speech recognition (ASR) and speaker change detection (SCD) systems have been independently trained to generate comprehensive transcripts accompanied by speaker turns. Recently, joint training of ASR and SCD systems, by inserting speaker turn tokens in the ASR training text, has been shown to be successful. In this work, we present a multitask alternative to the joint training approach. Results obtained on the mix-headset audios of AMI corpus show that the proposed multitask training yields an absolute improvement of 1.8% in coverage and purity based F1 score on SCD task without ASR degradation. We also examine the trade-offs between the ASR and SCD performance when trained using multitask criteria. Additionally, we validate the speaker change information in the embedding spaces obtained after different transformer layers of a self-supervised pre-trained model, such as XLSR-53, by integrating an SCD classifier at the output of specific transformer layers. Results r
Czech name
—
Czech description
—

Type
O - Miscellaneous
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)