E2E-AEC: Implementing an end-to-end neural network learning approach for acoustic echo cancellation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908783490367488 |
|---|---|
| author | Jiang, Yiheng Tian, Biao Wang, Haoxu Zhao, Shengkui Ma, Bin Chen, Daren Li, Xiangang |
| author_facet | Jiang, Yiheng Tian, Biao Wang, Haoxu Zhao, Shengkui Ma, Bin Chen, Daren Li, Xiangang |
| contents | We propose a novel neural network-based end-to-end acoustic echo cancellation (E2E-AEC) method capable of streaming inference, which operates effectively without reliance on traditional linear AEC (LAEC) techniques and time delay estimation. Our approach includes several key strategies: First, we introduce and refine progressive learning to gradually enhance echo suppression. Second, our model employs knowledge transfer by initializing with a pre-trained LAECbased model, harnessing the insights gained from LAEC training. Third, we optimize the attention mechanism with a loss function applied on attention weights to achieve precise time alignment between the reference and microphone signals. Lastly, we incorporate voice activity detection to enhance speech quality and improve echo removal by masking the network output when near-end speech is absent. The effectiveness of our approach is validated through experiments conducted on public datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16774 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | E2E-AEC: Implementing an end-to-end neural network learning approach for acoustic echo cancellation Jiang, Yiheng Tian, Biao Wang, Haoxu Zhao, Shengkui Ma, Bin Chen, Daren Li, Xiangang Sound Audio and Speech Processing We propose a novel neural network-based end-to-end acoustic echo cancellation (E2E-AEC) method capable of streaming inference, which operates effectively without reliance on traditional linear AEC (LAEC) techniques and time delay estimation. Our approach includes several key strategies: First, we introduce and refine progressive learning to gradually enhance echo suppression. Second, our model employs knowledge transfer by initializing with a pre-trained LAECbased model, harnessing the insights gained from LAEC training. Third, we optimize the attention mechanism with a loss function applied on attention weights to achieve precise time alignment between the reference and microphone signals. Lastly, we incorporate voice activity detection to enhance speech quality and improve echo removal by masking the network output when near-end speech is absent. The effectiveness of our approach is validated through experiments conducted on public datasets. |
| title | E2E-AEC: Implementing an end-to-end neural network learning approach for acoustic echo cancellation |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.16774 |