Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.10234 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914033463984128 |
|---|---|
| author | Cui, Can Magron, Paul Sadeghi, Mostafa Vincent, Emmanuel |
| author_facet | Cui, Can Magron, Paul Sadeghi, Mostafa Vincent, Emmanuel |
| contents | Automatic speech recognition (ASR) in multichannel, multi-speaker scenarios remains challenging due to ambient noise, reverberation and overlapping speakers. In this paper, we propose a beamforming approach that processes specific angular sectors based on their spherical polar coordinates before applying an end-to-end multichannel, multi-speaker ASR system. This method is data-independent and training-free. We demonstrate that using a group of beamformed signals improves ASR performance compared to using the same number of raw microphone signals. Moreover, increasing the number of signals used for beamforming further enhances recognition accuracy, leading to a more efficient use of multichannel signals while reducing the overall input load for the ASR system. We conduct experiments on the AMI meeting corpus, where the proposed method reduces word error rate by up to 11% and improves speaker counting accuracy by up to 27% relative compared to a multichannel ASR baseline system that does not exploit beamforming. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10234 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data-independent Beamforming for End-to-end Multichannel Multi-speaker ASR Cui, Can Magron, Paul Sadeghi, Mostafa Vincent, Emmanuel Sound Automatic speech recognition (ASR) in multichannel, multi-speaker scenarios remains challenging due to ambient noise, reverberation and overlapping speakers. In this paper, we propose a beamforming approach that processes specific angular sectors based on their spherical polar coordinates before applying an end-to-end multichannel, multi-speaker ASR system. This method is data-independent and training-free. We demonstrate that using a group of beamformed signals improves ASR performance compared to using the same number of raw microphone signals. Moreover, increasing the number of signals used for beamforming further enhances recognition accuracy, leading to a more efficient use of multichannel signals while reducing the overall input load for the ASR system. We conduct experiments on the AMI meeting corpus, where the proposed method reduces word error rate by up to 11% and improves speaker counting accuracy by up to 27% relative compared to a multichannel ASR baseline system that does not exploit beamforming. |
| title | Data-independent Beamforming for End-to-end Multichannel Multi-speaker ASR |
| topic | Sound |
| url | https://arxiv.org/abs/2509.10234 |