Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.14268 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913276492775424 |
|---|---|
| author | Lee, PeiYing Guo, HauYun Chen, Berlin |
| author_facet | Lee, PeiYing Guo, HauYun Chen, Berlin |
| contents | End-to-End Neural Diarization with Encoder-Decoder based Attractor (EEND-EDA) is an end-to-end neural model for automatic speaker segmentation and labeling. It achieves the capability to handle flexible number of speakers by estimating the number of attractors. EEND-EDA, however, struggles to accurately capture local speaker dynamics. This work proposes an auxiliary loss that aims to guide the Transformer encoders at the lower layer of EEND-EDA model to enhance the effect of self-attention modules using speaker activity information. The results evaluated on public dataset Mini LibriSpeech, demonstrates the effectiveness of the work, reducing Diarization Error Rate from 30.95% to 28.17%. We will release the source code on GitHub to allow further research and reproducibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14268 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Speech-Aware Neural Diarization with Encoder-Decoder Attractor Guided by Attention Constraints Lee, PeiYing Guo, HauYun Chen, Berlin Audio and Speech Processing Sound End-to-End Neural Diarization with Encoder-Decoder based Attractor (EEND-EDA) is an end-to-end neural model for automatic speaker segmentation and labeling. It achieves the capability to handle flexible number of speakers by estimating the number of attractors. EEND-EDA, however, struggles to accurately capture local speaker dynamics. This work proposes an auxiliary loss that aims to guide the Transformer encoders at the lower layer of EEND-EDA model to enhance the effect of self-attention modules using speaker activity information. The results evaluated on public dataset Mini LibriSpeech, demonstrates the effectiveness of the work, reducing Diarization Error Rate from 30.95% to 28.17%. We will release the source code on GitHub to allow further research and reproducibility. |
| title | Speech-Aware Neural Diarization with Encoder-Decoder Attractor Guided by Attention Constraints |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2403.14268 |