ELOQUENCE - Idiap Publications

Update cookies preferences

Name:

ELOQUENCE

Enhancing Speaker Diarization using Correlation-Based Clustering Initialization, Pradeep Rangappa, Amrutha Prasad, Srikanth Madikeri and Petr Motlicek, Idiap-RR-09-2025

attachment

Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering, Pradeep Rangappa, Andrés Carofilis, Jeena Prakash, Shashi Kumar, Sergio Burdisso, Srikanth Madikeri, Esaú Villatoro-Tello, Bidisha Sharma, Petr Motlicek, Kadri Hacioğlu, Shankar Venkatesan, Saurabh Vyas and Andreas Stolcke, in: Proc. Interspeech, 2025

attachment

Latent Space Factorization in LoRA, Shashi Kumar, Yacouba Kaloga, John Mitros, Petr Motlicek and Ina Kodrasi, in: 39th Conference on Neural Information Processing Systems, 2025

attachment

[URL]

Performance Evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward, Shashi Kumar, Iuliia Thorbecke, Sergio Burdisso, Esaú Villatoro-Tello, Manjunath K E, Kadri Hacioğlu, Pradeep Rangappa, Petr Motlicek, Aravind Ganapathiraju and Andreas Stolcke, in: SALMA Workshop, Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hyderabad, India, IEEE, 2025

attachment

[URL]

Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering, Pradeep Rangappa, Juan Zuluaga-Gomez, Srikanth Madikeri, Andrés Carofilis, Jeena Prakash, Sergio Burdisso, Shashi Kumar, Esaú Villatoro-Tello, Nigmatulina Iuliia, Petr Motlicek, Karthik Pandia D S and Aravind Ganapathiraju, in: 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025), 2025

attachment

[DOI]
[URL]

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation, Shashi Kumar, Srikanth Madikeri, Esaú Villatoro-Tello, Sergio Burdisso, Pradeep Rangappa, Andrés Carofilis, Petr Motlicek, Karthik Pandia D S, Shankar Venkatesan, Kadri Hacioğlu and Andreas Stolcke, in: 2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), IEEE, 2025

attachment

XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models, Shashi Kumar, Srikanth Madikeri, Juan Zuluaga-Gomez, Esaú Villatoro-Tello, Iuliia Thorbecke, Petr Motlicek, Manjunath K E and Aravind Ganapathiraju, in: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hyderabad, India, IEEE, 2025

attachment

[DOI]
[URL]

Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction, Sergio Burdisso, Srikanth Madikeri and Petr Motlicek, in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, Florida, USA, pages 5421–5440, Association for Computational Linguistics, 2024

attachment

[URL]

Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers, Shashi Kumar, Srikanth Madikeri, Nigmatulina Iuliia, Esaú Villatoro-Tello, Petr Motlicek, Karthik Pandia D S, S. Pavankumar Dubagunta and Aravind Ganapathiraju, in: Proceedings of the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) 2024, Seoul, Republic of Korea, pages 12592-12596, IEEE, 2024

[DOI]
[URL]

TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR, Shashi Kumar, Srikanth Madikeri, Juan Zuluaga-Gomez, Iuliia Thorbecke, Esaú Villatoro-Tello, Sergio Burdisso, Petr Motlicek, Karthik Pandia D S and Aravind Ganapathiraju, in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 20988–20995, Association for Computational Linguistics (ACL), 2024

attachment

[DOI]
[URL]

processing time: 0.0003 seconds.