Search Results for author: Jenthe Thienpondt

Found 10 papers, 0 papers with code

Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization

no code implementations15 May 2024 Jenthe Thienpondt, Kris Demuynck

Current speaker diarization systems rely on an external voice activity detection model prior to speaker embedding extraction on the detected speech segments.

Action Detection Activity Detection +3

ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings

no code implementations16 Jan 2024 Jenthe Thienpondt, Kris Demuynck

In this paper, we present ECAPA2, a novel hybrid neural network architecture and training strategy to produce robust speaker embeddings.

Speaker Verification

Margin-Mixup: A Method for Robust Speaker Verification in Multi-Speaker Audio

no code implementations7 Apr 2023 Jenthe Thienpondt, Nilesh Madhu, Kris Demuynck

Most speaker verification systems are designed with the assumption of a single speaker being present in a given audio segment.

Speaker Verification

Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping

no code implementations19 Jun 2022 Jenthe Thienpondt, Kris Demuynck

This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting domain mismatch when decoding children's speech with systems trained on adult data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Tackling the Score Shift in Cross-Lingual Speaker Verification by Exploiting Language Information

no code implementations18 Oct 2021 Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck

This paper contains a post-challenge performance analysis on cross-lingual speaker verification of the IDLab submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21).

Language Identification Speaker Recognition +1

The IDLAB VoxCeleb Speaker Recognition Challenge 2021 System Description

no code implementations9 Sep 2021 Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck

The final system fusion with two ECAPA CNN-TDNNs and three SE-ResNets enhanced with frequency positional information achieved a third place on the VoxSRC-21 leaderboard for both track 1 and 2 with a minDCF of 0. 1291 and 0. 1313 respectively.

Speaker Recognition Speaker Verification

Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker Verification

no code implementations6 Apr 2021 Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck

These learnable feature map biases along the frequency axis offer this architecture a straightforward way to exploit frequency positional information.

Speaker Verification Task 2

Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization

no code implementations15 Jul 2020 Jenthe Thienpondt, Brecht Desplanques, Kris Demuynck

In this paper we describe the top-scoring IDLab submission for the text-independent task of the Short-duration Speaker Verification (SdSV) Challenge 2020.

Language Modelling Speaker Verification

Cannot find the paper you are looking for? You can Submit a new open access paper.