BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation
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_ | 1866914830552662016 |
|---|---|
| author | Zhang, Zihan Xia, Xianjun Huang, Chuanzeng Xiao, Yijian Xie, Lei |
| author_facet | Zhang, Zihan Xia, Xianjun Huang, Chuanzeng Xiao, Yijian Xie, Lei |
| contents | Audio packet loss is an inevitable problem in real-time speech communication. A band-split packet loss concealment network (BS-PLCNet) targeting full-band signals was recently proposed. Although it performs superiorly in the ICASSP 2024 PLC Challenge, BS-PLCNet is a large model with high computational complexity of 8.95G FLOPS. This paper presents its updated version, BS-PLCNet 2, to reduce computational complexity and improve performance further. Specifically, to compensate for the missing future information, in the wide-band module, we design a dual-path encoder structure (with non-causal and causal path) and leverage an intra-model knowledge distillation strategy to distill the future information from the non-causal teacher to the casual student. Moreover, we introduce a lightweight post-processing module after packet loss restoration to recover speech distortions and remove residual noise in the audio signal. With only 40% of original parameters in BS-PLCNet, BS-PLCNet 2 brings 0.18 PLCMOS improvement on the ICASSP 2024 PLC challenge blind set, achieving state-of-the-art performance on this dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05961 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation Zhang, Zihan Xia, Xianjun Huang, Chuanzeng Xiao, Yijian Xie, Lei Audio and Speech Processing Audio packet loss is an inevitable problem in real-time speech communication. A band-split packet loss concealment network (BS-PLCNet) targeting full-band signals was recently proposed. Although it performs superiorly in the ICASSP 2024 PLC Challenge, BS-PLCNet is a large model with high computational complexity of 8.95G FLOPS. This paper presents its updated version, BS-PLCNet 2, to reduce computational complexity and improve performance further. Specifically, to compensate for the missing future information, in the wide-band module, we design a dual-path encoder structure (with non-causal and causal path) and leverage an intra-model knowledge distillation strategy to distill the future information from the non-causal teacher to the casual student. Moreover, we introduce a lightweight post-processing module after packet loss restoration to recover speech distortions and remove residual noise in the audio signal. With only 40% of original parameters in BS-PLCNet, BS-PLCNet 2 brings 0.18 PLCMOS improvement on the ICASSP 2024 PLC challenge blind set, achieving state-of-the-art performance on this dataset. |
| title | BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.05961 |