TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024 - Structuration, Analyse et Modélisation de documents Vidéo et Audio
Conference Papers Year : 2024

TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024

Abstract

This paper describes the submissions of team TalTech-IRIT-LIS to the DISPLACE 2024 challenge. Our team participated in the speaker diarization and language diarization tracks of the challenge. In the speaker diarization track, our best submission was an ensemble of systems based on the pyannote.audio speaker diarization pipeline utilizing powerset training and our recently proposed PixIT method that performs joint diarization and speech separation. We improve upon PixIT by using the separation outputs for speaker embedding extraction. Our ensemble achieved a diarization error rate of 27.1% on the evaluation dataset. In the language diarization track, we fine-tuned a pre-trained Wav2Vec2-BERT language embedding model on in-domain data, and clustered short segments using AHC and VBx, based on similarity scores from LDA/PLDA. This led to a language diarization error rate of 27.6% on the evaluation data. Both results were ranked first in their respective challenge tracks.
Fichier principal
Vignette du fichier
kalda24_interspeech.pdf (258.31 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04683362 , version 1 (02-09-2024)

Identifiers

Cite

Joonas Kalda, Tanel Alumae, Martin Lebourdais, Hervé Bredin, Séverin Baroudi, et al.. TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024. 25th Interspeech Conference (Interspeech 2024), Sep 2024, Kos, Greece. pp.1635--1639, ⟨10.21437/interspeech.2024-2462⟩. ⟨hal-04683362⟩
119 View
24 Download

Altmetric

Share

More