Improved Remixing Process for Domain Adaptation-Based Speech Enhancement by Mitigating Data Imbalance in Signal-to-Noise Ratio
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_ | 1866911927174692864 |
|---|---|
| author | Li, Li Seki, Shogo |
| author_facet | Li, Li Seki, Shogo |
| contents | RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement (DASE) methods that use a teacher model trained in full supervision to generate pseudo-paired data by remixing the outputs of the teacher model. The student model for enhancing real-world recorded signals is trained using the pseudo-paired data without ground truth. Since the noisy signals are recorded in natural environments, the dataset inevitably suffers data imbalance in some acoustic properties, leading to subpar performance for the underrepresented data. The signal-to-noise ratio (SNR), inherently balanced in supervised learning, is a prime example. In this paper, we provide empirical evidence that the SNR of pseudo data has a significant impact on model performance using the dataset of the CHiME-7 UDASE task, highlighting the importance of balanced SNR in DASE. Furthermore, we propose adopting curriculum learning to encompass a broad range of SNRs to boost performance for underrepresented data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13982 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improved Remixing Process for Domain Adaptation-Based Speech Enhancement by Mitigating Data Imbalance in Signal-to-Noise Ratio Li, Li Seki, Shogo Sound Audio and Speech Processing RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement (DASE) methods that use a teacher model trained in full supervision to generate pseudo-paired data by remixing the outputs of the teacher model. The student model for enhancing real-world recorded signals is trained using the pseudo-paired data without ground truth. Since the noisy signals are recorded in natural environments, the dataset inevitably suffers data imbalance in some acoustic properties, leading to subpar performance for the underrepresented data. The signal-to-noise ratio (SNR), inherently balanced in supervised learning, is a prime example. In this paper, we provide empirical evidence that the SNR of pseudo data has a significant impact on model performance using the dataset of the CHiME-7 UDASE task, highlighting the importance of balanced SNR in DASE. Furthermore, we propose adopting curriculum learning to encompass a broad range of SNRs to boost performance for underrepresented data. |
| title | Improved Remixing Process for Domain Adaptation-Based Speech Enhancement by Mitigating Data Imbalance in Signal-to-Noise Ratio |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.13982 |