DRED: Deep REDundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916452161814528 |
|---|---|
| author | Valin, Jean-Marc Büthe, Jan Mustafa, Ahmed Klingbeil, Michael |
| author_facet | Valin, Jean-Marc Büthe, Jan Mustafa, Ahmed Klingbeil, Michael |
| contents | Despite recent advancements in packet loss concealment (PLC) using deep learning techniques, packet loss remains a significant challenge in real-time speech communication. Redundancy has been used in the past to recover the missing information during losses. However, conventional redundancy techniques are limited in the maximum loss duration they can cover and are often unsuitable for burst packet loss. We propose a new approach based on a rate-distortion-optimized variational autoencoder (RDO-VAE), allowing us to optimize a deep speech compression algorithm for the task of encoding large amounts of redundancy at very low bitrate. The proposed Deep REDundancy (DRED) algorithm can transmit up to 50x redundancy using less than 32 kb/s. Results show that DRED outperforms the existing Opus codec redundancy. We also demonstrate its benefits when operating in the context of WebRTC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_04453 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | DRED: Deep REDundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder Valin, Jean-Marc Büthe, Jan Mustafa, Ahmed Klingbeil, Michael Audio and Speech Processing Despite recent advancements in packet loss concealment (PLC) using deep learning techniques, packet loss remains a significant challenge in real-time speech communication. Redundancy has been used in the past to recover the missing information during losses. However, conventional redundancy techniques are limited in the maximum loss duration they can cover and are often unsuitable for burst packet loss. We propose a new approach based on a rate-distortion-optimized variational autoencoder (RDO-VAE), allowing us to optimize a deep speech compression algorithm for the task of encoding large amounts of redundancy at very low bitrate. The proposed Deep REDundancy (DRED) algorithm can transmit up to 50x redundancy using less than 32 kb/s. Results show that DRED outperforms the existing Opus codec redundancy. We also demonstrate its benefits when operating in the context of WebRTC. |
| title | DRED: Deep REDundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2212.04453 |