Dominik Klement
@dklement.bsky.social
Speech Researcher @ BUT SPEECH
Visiting student @ CLSP Johns Hopkins University
GitHub: https://github.com/domklement
LinkedIN: https://www.linkedin.com/in/dominik-klement/
Visiting student @ CLSP Johns Hopkins University
GitHub: https://github.com/domklement
LinkedIN: https://www.linkedin.com/in/dominik-klement/
🤝 Collaboration and Feedback Welcome
We’re open to feedback, discussions, and collaborations. Let’s work together to shape the future of ASR and diarization technology!
[14/14]
We’re open to feedback, discussions, and collaborations. Let’s work together to shape the future of ASR and diarization technology!
[14/14]
January 11, 2025 at 7:30 PM
🤝 Collaboration and Feedback Welcome
We’re open to feedback, discussions, and collaborations. Let’s work together to shape the future of ASR and diarization technology!
[14/14]
We’re open to feedback, discussions, and collaborations. Let’s work together to shape the future of ASR and diarization technology!
[14/14]
🌟 Kudos to CHiME-8 NOTSOFAR-1 Organizers
Thanks to Alon Vinnikov, Amir Ivry, Eyal Krupka (Microsoft) for organizing the CHiME-8 NOTSOFAR-1 Challenge, and to the CHiME-8 Steering Committee for their dedication to advancing speech recognition research!
[13/14]
Thanks to Alon Vinnikov, Amir Ivry, Eyal Krupka (Microsoft) for organizing the CHiME-8 NOTSOFAR-1 Challenge, and to the CHiME-8 Steering Committee for their dedication to advancing speech recognition research!
[13/14]
January 11, 2025 at 7:30 PM
🌟 Kudos to CHiME-8 NOTSOFAR-1 Organizers
Thanks to Alon Vinnikov, Amir Ivry, Eyal Krupka (Microsoft) for organizing the CHiME-8 NOTSOFAR-1 Challenge, and to the CHiME-8 Steering Committee for their dedication to advancing speech recognition research!
[13/14]
Thanks to Alon Vinnikov, Amir Ivry, Eyal Krupka (Microsoft) for organizing the CHiME-8 NOTSOFAR-1 Challenge, and to the CHiME-8 Steering Committee for their dedication to advancing speech recognition research!
[13/14]
💻Gradio-powered Demo pccnect.fit.vutbr.cz/gradio-demo - Test our DiCoW model to transcribe your own meetings! The demo is live for 72 hours only, so don’t miss this chance.
[12/14]
[12/14]
Gradio
pccnect.fit.vutbr.cz
January 11, 2025 at 7:30 PM
💻Gradio-powered Demo pccnect.fit.vutbr.cz/gradio-demo - Test our DiCoW model to transcribe your own meetings! The demo is live for 72 hours only, so don’t miss this chance.
[12/14]
[12/14]
🔗DiCoW Inference Demo Pipeline github.com/BUTSpeechFIT...
[11/14]
[11/14]
GitHub - BUTSpeechFIT/DiCoW
Contribute to BUTSpeechFIT/DiCoW development by creating an account on GitHub.
github.com
January 11, 2025 at 7:30 PM
🔗DiCoW Inference Demo Pipeline github.com/BUTSpeechFIT...
[11/14]
[11/14]
🔗Target-Speaker Whisper Source Code github.com/BUTSpeechFIT...
[10/14]
[10/14]
GitHub - BUTSpeechFIT/TS-ASR-Whisper
Contribute to BUTSpeechFIT/TS-ASR-Whisper development by creating an account on GitHub.
github.com
January 11, 2025 at 7:30 PM
🔗Target-Speaker Whisper Source Code github.com/BUTSpeechFIT...
[10/14]
[10/14]
🌟Open-Source Tools and Demos
We’re making our research accessible by open-sourcing training and inference codebases, and providing interactive demos:
🔗DiariZen Source Code github.com/BUTSpeechFIT...
[9/14]
We’re making our research accessible by open-sourcing training and inference codebases, and providing interactive demos:
🔗DiariZen Source Code github.com/BUTSpeechFIT...
[9/14]
GitHub - BUTSpeechFIT/DiariZen: A toolkit for speaker diarization.
A toolkit for speaker diarization. . Contribute to BUTSpeechFIT/DiariZen development by creating an account on GitHub.
github.com
January 11, 2025 at 7:30 PM
🌟Open-Source Tools and Demos
We’re making our research accessible by open-sourcing training and inference codebases, and providing interactive demos:
🔗DiariZen Source Code github.com/BUTSpeechFIT...
[9/14]
We’re making our research accessible by open-sourcing training and inference codebases, and providing interactive demos:
🔗DiariZen Source Code github.com/BUTSpeechFIT...
[9/14]
🌟
4. Leveraging Self-Supervised Learning for Speaker Diarization - Accepted to ICASSP 2025. This paper introduces DiariZen - our state-of-the-art diarization model and toolkit.
arxiv.org/abs/2409.09408
[8/14]
4. Leveraging Self-Supervised Learning for Speaker Diarization - Accepted to ICASSP 2025. This paper introduces DiariZen - our state-of-the-art diarization model and toolkit.
arxiv.org/abs/2409.09408
[8/14]
Leveraging Self-Supervised Learning for Speaker Diarization
End-to-end neural diarization has evolved considerably over the past few years, but data scarcity is still a major obstacle for further improvements. Self-supervised learning methods such as WavLM hav...
arxiv.org
January 11, 2025 at 7:30 PM
🌟
4. Leveraging Self-Supervised Learning for Speaker Diarization - Accepted to ICASSP 2025. This paper introduces DiariZen - our state-of-the-art diarization model and toolkit.
arxiv.org/abs/2409.09408
[8/14]
4. Leveraging Self-Supervised Learning for Speaker Diarization - Accepted to ICASSP 2025. This paper introduces DiariZen - our state-of-the-art diarization model and toolkit.
arxiv.org/abs/2409.09408
[8/14]
🌟
3. BUT/JHU System Description for CHiME-8 NOTSOFAR-1 Challenge - The work earned the 🏆Jury Prize for being one of the most practical, efficient, and novel systems. Our robust diarization-ASR integration is capable of tackling overlapped speech.
isca-archive.org/chime_2024/p...
[7/14]
3. BUT/JHU System Description for CHiME-8 NOTSOFAR-1 Challenge - The work earned the 🏆Jury Prize for being one of the most practical, efficient, and novel systems. Our robust diarization-ASR integration is capable of tackling overlapped speech.
isca-archive.org/chime_2024/p...
[7/14]
ISCA Archive - BUT/JHU System Description for CHiME-8 NOTSOFAR-1 Challenge
isca-archive.org
January 11, 2025 at 7:30 PM
🌟
3. BUT/JHU System Description for CHiME-8 NOTSOFAR-1 Challenge - The work earned the 🏆Jury Prize for being one of the most practical, efficient, and novel systems. Our robust diarization-ASR integration is capable of tackling overlapped speech.
isca-archive.org/chime_2024/p...
[7/14]
3. BUT/JHU System Description for CHiME-8 NOTSOFAR-1 Challenge - The work earned the 🏆Jury Prize for being one of the most practical, efficient, and novel systems. Our robust diarization-ASR integration is capable of tackling overlapped speech.
isca-archive.org/chime_2024/p...
[7/14]
🌟
2. Target Speaker ASR with Whisper arxiv.org/abs/2409.09543 - Accepted to ICASSP 2025. This work enhances the Whisper ASR model for target-speaker recognition, demonstrating its applicability in complex acoustic scenarios.
[6/14]
2. Target Speaker ASR with Whisper arxiv.org/abs/2409.09543 - Accepted to ICASSP 2025. This work enhances the Whisper ASR model for target-speaker recognition, demonstrating its applicability in complex acoustic scenarios.
[6/14]
Target Speaker ASR with Whisper
We propose a novel approach to enable the use of large, single speaker ASR models, such as Whisper, for target speaker ASR. The key insight of this method is that it is much easier to model relative d...
arxiv.org
January 11, 2025 at 7:30 PM
🌟
2. Target Speaker ASR with Whisper arxiv.org/abs/2409.09543 - Accepted to ICASSP 2025. This work enhances the Whisper ASR model for target-speaker recognition, demonstrating its applicability in complex acoustic scenarios.
[6/14]
2. Target Speaker ASR with Whisper arxiv.org/abs/2409.09543 - Accepted to ICASSP 2025. This work enhances the Whisper ASR model for target-speaker recognition, demonstrating its applicability in complex acoustic scenarios.
[6/14]
By directly conditioning the ASR model on diarization outputs, we simplify the workflow for multi-speaker and target-speaker scenarios. Importantly, DiCoW maintains Whisper’s performance on single-speaker transcription, ensuring robustness across diverse use cases.
[5/14]
[5/14]
January 11, 2025 at 7:30 PM
By directly conditioning the ASR model on diarization outputs, we simplify the workflow for multi-speaker and target-speaker scenarios. Importantly, DiCoW maintains Whisper’s performance on single-speaker transcription, ensuring robustness across diverse use cases.
[5/14]
[5/14]
🌟Recent Papers
1. DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition - Submitted to CSL. Our diarization-conditioned approach that eliminates the need for speaker enrollment or source separation.
arxiv.org/abs/2501.00114
[4/14]
1. DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition - Submitted to CSL. Our diarization-conditioned approach that eliminates the need for speaker enrollment or source separation.
arxiv.org/abs/2501.00114
[4/14]
DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition
Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fail to generalize to u...
arxiv.org
January 11, 2025 at 7:30 PM
🌟Recent Papers
1. DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition - Submitted to CSL. Our diarization-conditioned approach that eliminates the need for speaker enrollment or source separation.
arxiv.org/abs/2501.00114
[4/14]
1. DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition - Submitted to CSL. Our diarization-conditioned approach that eliminates the need for speaker enrollment or source separation.
arxiv.org/abs/2501.00114
[4/14]
- Versatile and Robust: Despite all improvements, our systems retain high performance on single-speaker transcription tasks, ensuring broad applicability across use cases.
[3/14]
[3/14]
January 11, 2025 at 7:30 PM
- Versatile and Robust: Despite all improvements, our systems retain high performance on single-speaker transcription tasks, ensuring broad applicability across use cases.
[3/14]
[3/14]
🌟Key Innovations
- Simplifying Multi-Speaker ASR: Our models directly use diarization outputs as conditioning signals, bypassing the need for enrollment data or complex source separation techniques.
[2/14]
- Simplifying Multi-Speaker ASR: Our models directly use diarization outputs as conditioning signals, bypassing the need for enrollment data or complex source separation techniques.
[2/14]
January 11, 2025 at 7:30 PM
🌟Key Innovations
- Simplifying Multi-Speaker ASR: Our models directly use diarization outputs as conditioning signals, bypassing the need for enrollment data or complex source separation techniques.
[2/14]
- Simplifying Multi-Speaker ASR: Our models directly use diarization outputs as conditioning signals, bypassing the need for enrollment data or complex source separation techniques.
[2/14]