This paper presents a weakly-supervised multichannel neural speech separation method for distant speech recognition (DSR) of real conversational speech mixtures. A blind source …
ZQ Wang - arXiv preprint arXiv:2402.00820, 2024 - arxiv.org
In reverberant conditions with a single speaker, each far-field microphone records a reverberant version of the same speaker signal at a different location. In over-determined …
In this work, we are interested in learning a model to separate sources that cannot be recorded in isolation, such as parts of a machine that must run simultaneously in order for …
This paper describes an efficient unsupervised learning method for a neural source separation model that utilizes a probabilistic generative model of observed multichannel …
H Munakata, Y Bando, R Takeda… - IEEE Signal …, 2023 - ieeexplore.ieee.org
This paper presents an unsupervised multichannel method that can separate moving sound sources based on an amortized variational inference (AVI) of joint separation and …
L Li, H Kameoka, S Makino - IEEE/ACM Transactions on Audio …, 2022 - ieeexplore.ieee.org
This article proposes a new source model and training scheme to improve the accuracy and speed of the multichannel variational autoencoder (MVAE) method. The MVAE method is a …
Y Bando, T Nakamura, S Watanabe - arXiv preprint arXiv:2406.08396, 2024 - arxiv.org
This paper presents a neural method for distant speech recognition (DSR) that jointly separates and diarizes speech mixtures without supervision by isolated signals. A standard …
E Karamatlı, S Kırbız - IEEE Signal Processing Letters, 2022 - ieeexplore.ieee.org
We introduce two unsupervised source separation methods, which involve self-supervised training from single-channel two-source speech mixtures. Our first method, mixture …