ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916145759518720 |
|---|---|
| author | Ho, Kuan-Hsun Hung, Jeih-weih Chen, Berlin |
| author_facet | Ho, Kuan-Hsun Hung, Jeih-weih Chen, Berlin |
| contents | Speech separation has recently made significant progress thanks to the fine-grained vision used in time-domain methods. However, several studies have shown that adopting Short-Time Fourier Transform (STFT) for feature extraction could be beneficial when encountering harsher conditions, such as noise or reverberation. Therefore, we propose a magnitude-conditioned time-domain framework, ConSep, to inherit the beneficial characteristics. The experiment shows that ConSep promotes performance in anechoic, noisy, and reverberant settings compared to two celebrated methods, SepFormer and Bi-Sep. Furthermore, we visualize the components of ConSep to strengthen the advantages and cohere with the actualities we have found in preliminary studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01792 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning Ho, Kuan-Hsun Hung, Jeih-weih Chen, Berlin Sound Audio and Speech Processing Speech separation has recently made significant progress thanks to the fine-grained vision used in time-domain methods. However, several studies have shown that adopting Short-Time Fourier Transform (STFT) for feature extraction could be beneficial when encountering harsher conditions, such as noise or reverberation. Therefore, we propose a magnitude-conditioned time-domain framework, ConSep, to inherit the beneficial characteristics. The experiment shows that ConSep promotes performance in anechoic, noisy, and reverberant settings compared to two celebrated methods, SepFormer and Bi-Sep. Furthermore, we visualize the components of ConSep to strengthen the advantages and cohere with the actualities we have found in preliminary studies. |
| title | ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2403.01792 |