Get started
Author

Séverin Baroudi

Specializing Self-Supervised Speech Representations for Speaker Segmentation
2024 · Séverin Baroudi, Thomas Pellegrini, et al. · Interspeech (USB) · 12
PDF
pyannote.audio speaker diarization pipeline at VoxSRC 2023
2023 · Baroudi, Séverin, Bredin, Hervé, et al. · HAL · 7
PDF
TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024
2024 · Joonas Kalda, Tanel Alumae, et al. · Interspeech (USB) · 6
PDF
ToTaTo System Descriptions for the NOTSOFAR1 Challenge
2024 · Joonas Kalda, Tanel Alumae, et al. · International Workshop on Speech Processing in Everyday Environments (CHiME) · 5
PDF
SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
2026 · Sergio Burdisso, Séverin Baroudi, et al. · Conference of the European Chapter of the Association for Computational Linguistics · 4
On the Use of Self-Supervised Representation Learning for Speaker Diarization and Separation
2025 · Séverin Baroudi, Hervé Bredin, et al. · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · 3
PDF
Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization
2026 · Yanis Labrak, David Grünert, et al. · Interspeech (USB) · 2
PDF
DASHA: Diarization-Aware Speech-LLM ASR for Healthcare in Code-Switched Indic Doctor-Patient Conversations
2026 · Baroudi, Séverin, Labrak, Yanis, et al. · arXiv (Cornell University) · 1
PDF
Design choices for PixIT-based speaker-attributed ASR: Team ToTaTo at the NOTSOFAR-1 challenge
2025 · Joonas Kalda, Séverin Baroudi, et al. · Computer Speech & Language · 1
Beyond the Benchmark: Conditioning, Domains and Failure Modes of Qwen3-TTS
2026 · Baroudi, Séverin, Labrak, Yanis, et al. · arXiv (Cornell University)
PDF
SepRQ : Self-Supervised Speech Mixture Representation Learning via Mask-Free, Multi-Scale Source Separation
2026 · Baroudi, Séverin, Bredin, Hervé, et al. · arXiv (Cornell University)
PDF
Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition
2026 · Baroudi, Séverin, Labrak, Yanis, et al. · arXiv (Cornell University)
PDF
GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
2026 · Botté, Gaspard, Baroudi, Séverin, et al. · arXiv (Cornell University)
PDF
Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR
2026 · Thibault Bañeras-Roux, Sergio Burdisso, et al. · Interspeech (USB)
PDF
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
2026 · Labrak, Yanis, Sanchez-Cortes, Dairazalia, et al. · arXiv (Cornell University)
PDF
Encodage de la sémantique et du locuteur dans les représentations sémantiques de la parole
2026 · Maryem Bouziane, Séverin Baroudi, et al. · Journées d'Études sur la Parole (JEP)
PDF
SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
2026 · Association for Computational Linguistics 2026, Baroudi, Séverin, et al. · Underline Science Inc.
SDialog : a python toolkit for end-to-end agent building, user simulation, dialog generation, and evaluation
2025 · Burdisso, Sergio, Baroudi, Séverin, et al. · arXiv (Cornell University)
PDF
Enhancing Pixit: Robust Methods for Real-World Speech Separation and Applications
2025 · Joonas Kalda, Séverin Baroudi, et al. · SSRN Electronic Journal
Works count: 19
Citation count: 41
H-index: 4
I10-index: 1
Year
Topic
Type