Forward Convolutive Prediction for Frame Online Monaural Speech Dereverberation Based on Kronecker Product Decomposition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908617250177024 |
|---|---|
| author | Zhu, Yujie Jin, Jilu Luo, Xueqin Yang, Wenxing Wang, Zhong-Qiu Huang, Gongping Chen, Jingdong Benesty, Jacob |
| author_facet | Zhu, Yujie Jin, Jilu Luo, Xueqin Yang, Wenxing Wang, Zhong-Qiu Huang, Gongping Chen, Jingdong Benesty, Jacob |
| contents | Dereverberation has long been a crucial research topic in speech processing, aiming to alleviate the adverse effects of reverberation in voice communication and speech interaction systems. Among existing approaches, forward convolutional prediction (FCP) has recently attracted attention. It typically employs a deep neural network to predict the direct-path signal and subsequently estimates a linear prediction filter to suppress residual reverberation. However, a major drawback of this approach is that the required linear prediction filter is often excessively long, leading to considerable computational complexity. To address this, our work proposes a novel FCP method based on Kronecker product (KP) decomposition, in which the long prediction filter is modeled as the KP of two much shorter filters. This decomposition significantly reduces the computational cost. An adaptive algorithm is then provided to iteratively update these shorter filters online. Experimental results show that, compared to conventional methods, our approach achieves competitive dereverberation performance while substantially reducing computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24471 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Forward Convolutive Prediction for Frame Online Monaural Speech Dereverberation Based on Kronecker Product Decomposition Zhu, Yujie Jin, Jilu Luo, Xueqin Yang, Wenxing Wang, Zhong-Qiu Huang, Gongping Chen, Jingdong Benesty, Jacob Audio and Speech Processing Dereverberation has long been a crucial research topic in speech processing, aiming to alleviate the adverse effects of reverberation in voice communication and speech interaction systems. Among existing approaches, forward convolutional prediction (FCP) has recently attracted attention. It typically employs a deep neural network to predict the direct-path signal and subsequently estimates a linear prediction filter to suppress residual reverberation. However, a major drawback of this approach is that the required linear prediction filter is often excessively long, leading to considerable computational complexity. To address this, our work proposes a novel FCP method based on Kronecker product (KP) decomposition, in which the long prediction filter is modeled as the KP of two much shorter filters. This decomposition significantly reduces the computational cost. An adaptive algorithm is then provided to iteratively update these shorter filters online. Experimental results show that, compared to conventional methods, our approach achieves competitive dereverberation performance while substantially reducing computational cost. |
| title | Forward Convolutive Prediction for Frame Online Monaural Speech Dereverberation Based on Kronecker Product Decomposition |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.24471 |