Speaker Diarization
Speaker diarization is the task of identifying "who spoke when" in an audio recording, a crucial preprocessing step for many speech applications. Current research focuses on improving accuracy and efficiency, particularly in challenging scenarios like multi-speaker conversations and noisy environments, using techniques such as end-to-end neural networks, spectral clustering, and the integration of audio-visual or semantic information. These advancements are driving progress in areas like meeting transcription, multilingual speech processing, and improving the performance of downstream tasks such as automatic speech recognition.
Papers
The CHiME-7 Challenge: System Description and Performance of NeMo Team's DASR System
Tae Jin Park, He Huang, Ante Jukic, Kunal Dhawan, Krishna C. Puvvada, Nithin Koluguri, Nikolay Karpov, Aleksandr Laptev, Jagadeesh Balam, Boris Ginsburg
Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation
Tae Jin Park, He Huang, Coleman Hooper, Nithin Koluguri, Kunal Dhawan, Ante Jukic, Jagadeesh Balam, Boris Ginsburg
USED: Universal Speaker Extraction and Diarization
Junyi Ao, Mehmet Sinan Yıldırım, Ruijie Tao, Meng Ge, Shuai Wang, Yanmin Qian, Haizhou Li
Improving Speaker Diarization using Semantic Information: Joint Pairwise Constraints Propagation
Luyao Cheng, Siqi Zheng, Qinglin Zhang, Hui Wang, Yafeng Chen, Qian Chen, Shiliang Zhang