Joonas Kalda

According to our database, Joonas Kalda authored at least 5 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Design choices for PixIT-based speaker-attributed ASR: Team ToTaTo at the NOTSOFAR-1 challenge.

Joonas Kalda, Séverin Baroudi, Martin Lebourdais, Clément Pagés, Ricard Marxer, Tanel Alumäe, Hervé Bredin

Comput. Speech Lang., 2026

2024

PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings.

Joonas Kalda, Clément Pagés, Ricard Marxer, Tanel Alumäe, Hervé Bredin

Proceedings of the Odyssey 2024: The Speaker and Language Recognition Workshop, 2024

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

Joonas Kalda, Tanel Alumäe, Martin Lebourdais, Hervé Bredin, Séverin Baroudi, Ricard Marxer

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

2023

Automatic Closed Captioning for Estonian Live Broadcasts.

Tanel Alumäe, Joonas Kalda, Külliki Bode, Martin Kaitsa

Proceedings of the 24th Nordic Conference on Computational Linguistics, 2023

2022

Collar-Aware Training for Streaming Speaker Change Detection in Broadcast Speech.

Joonas Kalda, Tanel Alumäe

Proceedings of the Odyssey 2022: The Speaker and Language Recognition Workshop, 28 June, 2022