UNSSOR: unsupervised neural speech separation by leveraging over-determined training mixtures
ZQ Wang, S Watanabe - Advances in Neural Information …, 2024 - proceedings.neurips.cc
In reverberant conditions with multiple concurrent speakers, each microphone acquires a
mixture signal of multiple speakers at a different location. In over-determined conditions …
mixture signal of multiple speakers at a different location. In over-determined conditions …
Task-Aware Unified Source Separation
Several attempts have been made to handle multiple source separation tasks such as
speech enhancement, speech separation, sound event separation, music source separation …
speech enhancement, speech separation, sound event separation, music source separation …
SuperME: Supervised and Mixture-to-Mixture Co-Learning for Speech Enhancement and Robust ASR
ZQ Wang - arXiv preprint arXiv:2403.10271, 2024 - arxiv.org
The current dominant approach for neural speech enhancement is based on supervised
learning by using simulated training data. The trained models, however, often exhibit limited …
learning by using simulated training data. The trained models, however, often exhibit limited …
A Unified Approach to Speaker Separation and Target Speaker Extraction Using Encoder-Decoder Based Attractors
SR Chetupalli, EAP Habets - 2024 18th International Workshop …, 2024 - ieeexplore.ieee.org
Blind speaker separation (SS) and target speaker extraction (TSE) deal with the extraction of
speaker signals from mixtures containing multiple speakers. We propose a unified approach …
speaker signals from mixtures containing multiple speakers. We propose a unified approach …