An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec
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_ | 1866909090843721728 |
|---|---|
| author | Xu, Linping Jiang, Jiawei Zhang, Dejun Xia, Xianjun Chen, Li Xiao, Yijian Ding, Piao Song, Shenyi Yin, Sixing Sohel, Ferdous |
| author_facet | Xu, Linping Jiang, Jiawei Zhang, Dejun Xia, Xianjun Chen, Li Xiao, Yijian Ding, Piao Song, Shenyi Yin, Sixing Sohel, Ferdous |
| contents | Recently, neural networks have proven to be effective in performing speech coding task at low bitrates. However, under-utilization of intra-frame correlations and the error of quantizer specifically degrade the reconstructed audio quality. To improve the coding quality, we present an end-to-end neural speech codec, namely CBRC (Convolutional and Bidirectional Recurrent neural Codec). An interleaved structure using 1D-CNN and Intra-BRNN is designed to exploit the intra-frame correlations more efficiently. Furthermore, Group-wise and Beam-search Residual Vector Quantizer (GB-RVQ) is used to reduce the quantization noise. CBRC encodes audio every 20ms with no additional latency, which is suitable for real-time communication. Experimental results demonstrate the superiority of the proposed codec when comparing CBRC at 3kbps with Opus at 12kbps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01271 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec Xu, Linping Jiang, Jiawei Zhang, Dejun Xia, Xianjun Chen, Li Xiao, Yijian Ding, Piao Song, Shenyi Yin, Sixing Sohel, Ferdous Audio and Speech Processing Sound Recently, neural networks have proven to be effective in performing speech coding task at low bitrates. However, under-utilization of intra-frame correlations and the error of quantizer specifically degrade the reconstructed audio quality. To improve the coding quality, we present an end-to-end neural speech codec, namely CBRC (Convolutional and Bidirectional Recurrent neural Codec). An interleaved structure using 1D-CNN and Intra-BRNN is designed to exploit the intra-frame correlations more efficiently. Furthermore, Group-wise and Beam-search Residual Vector Quantizer (GB-RVQ) is used to reduce the quantization noise. CBRC encodes audio every 20ms with no additional latency, which is suitable for real-time communication. Experimental results demonstrate the superiority of the proposed codec when comparing CBRC at 3kbps with Opus at 12kbps. |
| title | An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2402.01271 |