Wavesplit: End-to-End Speech Separation by Speaker Clustering
Top Cited Papers
- 26 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 29 (23299290) , 2840-2849
Abstract
We introduce Wavesplit, an end-to-end source separation system. From a single mixture, the model infers a representation for each source and then estimates each source signal given the inferred representations. The model is trained to jointly perform both tasks from the raw waveform. Wavesplit infers a set of source representations via clustering, which addresses the fundamental permutation problem of separation. For speech separation, our sequence-wide speaker representations provide a more robust separation of long, challenging recordings compared to prior work. Wavesplit redefines the state-of-the-art on clean mixtures of 2 or 3 speakers (WSJ0-2/3mix), as well as in noisy and reverberated settings (WHAM/WHAMR). We also set a new benchmark on the recent LibriMix dataset. Finally, we show that Wavesplit is also applicable to other domains, by separating fetal and maternal heart rates from a single abdominal electrocardiogram.Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- An open-source framework for stress-testing non-invasive foetal ECG extraction algorithmsPhysiological Measurement, 2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Deep Neural Networks for Single-Channel Multi-Talker Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Librispeech: An ASR corpus based on public domain audio books2015
- A review of blind source separation in NMR spectroscopyProgress in Nuclear Magnetic Resonance Spectroscopy, 2014
- The persistent challenge of foetal heart rate monitoringCurrent Opinion in Obstetrics and Gynecology, 2010
- A Non-invasive Methodology for Fetal Monitoring during PregnancyMethods of Information in Medicine, 2010
- Blind Separation of Speech Mixtures via Time-Frequency MaskingIEEE Transactions on Signal Processing, 2004
- Signal estimation from modified short-time Fourier transformIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980