Asymmetric And Trial-dependent Modeling: The Contribution Of LIA To Sdsv Challenge Task 2

Abstract

The SdSv challenge Task 2 provided an opportunity to assess efficiency and robustness of modern text-independent speaker verification systems. But it also made it possible to test new approaches, capable of taking into account the main issues of this challenge (duration, language, ...). This paper describes the contributions of our laboratory to the speaker recognition field. These contributions highlight two other challenges in addition to short-duration and language: the mismatch between enrollment and test data and the one between subsets of the evaluation trial dataset. The proposed approaches experimentally show their relevance and efficiency on the SdSv evaluation, and could be of interest in many real-life applications.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybousquet2024asymmetric

Related papers

• Short-duration Speaker Verification (sdsv) Challenge 2021: The Challenge Evaluation Plan (2019)0.00
• The SVASR System For Text-dependent Speaker Verification (tdsv) AAIC Challenge 2024 (2024)0.00
• Robust Text-dependent Speaker Verification Via Character-level Information Preservation For The Sdsv Challenge 2020 (2020)0.00
• Text-dependent Speaker Verification (tdsv) Challenge 2024: Challenge Evaluation Plan (2024)0.00
• LIA System Description For NIST SRE 2016 (2016)0.00
• Memory-efficient Training For Text-dependent SV With Independent Pre-trained Models (2024)0.00
• Tackling The Score Shift In Cross-lingual Speaker Verification By Exploiting Language Information (2021)3.58
• Application Of ASV For Voice Identification After VC And Duration Predictor Improvement In TTS Models (2024)0.00