MaskCycleGAN-based Whisper to Normal Speech Conversion
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_ | 1866914924969590784 |
|---|---|
| author | Gupta, K. Rohith Ramnath, K. Joysingh, S. Johanan Vijayalakshmi, P. Nagarajan, T. |
| author_facet | Gupta, K. Rohith Ramnath, K. Joysingh, S. Johanan Vijayalakshmi, P. Nagarajan, T. |
| contents | Whisper to normal speech conversion is an active area of research. Various architectures based on generative adversarial networks have been proposed in the recent past. Especially, recent study shows that MaskCycleGAN, which is a mask guided, and cyclic consistency keeping, generative adversarial network, performs really well for voice conversion from spectrogram representations. In the current work we present a MaskCycleGAN approach for the conversion of whispered speech to normal speech. We find that tuning the mask parameters, and pre-processing the signal with a voice activity detector provides superior performance when compared to the existing approach. The wTIMIT dataset is used for evaluation. Objective metrics such as PESQ and G-Loss are used to evaluate the converted speech, along with subjective evaluation using mean opinion score. The results show that the proposed approach offers considerable benefits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14797 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MaskCycleGAN-based Whisper to Normal Speech Conversion Gupta, K. Rohith Ramnath, K. Joysingh, S. Johanan Vijayalakshmi, P. Nagarajan, T. Audio and Speech Processing Machine Learning Whisper to normal speech conversion is an active area of research. Various architectures based on generative adversarial networks have been proposed in the recent past. Especially, recent study shows that MaskCycleGAN, which is a mask guided, and cyclic consistency keeping, generative adversarial network, performs really well for voice conversion from spectrogram representations. In the current work we present a MaskCycleGAN approach for the conversion of whispered speech to normal speech. We find that tuning the mask parameters, and pre-processing the signal with a voice activity detector provides superior performance when compared to the existing approach. The wTIMIT dataset is used for evaluation. Objective metrics such as PESQ and G-Loss are used to evaluate the converted speech, along with subjective evaluation using mean opinion score. The results show that the proposed approach offers considerable benefits. |
| title | MaskCycleGAN-based Whisper to Normal Speech Conversion |
| topic | Audio and Speech Processing Machine Learning |
| url | https://arxiv.org/abs/2408.14797 |