Multi-Channel Joint Dereverberation and Denoising using Deep Priors
| Autor: | Aditya Raikar, Sourya Basu, Rajesh M. Hegde, Laxmi Pandey |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Beamforming
Reverberation Channel (digital image) Computer science Speech recognition Noise reduction Word error rate 01 natural sciences Speech enhancement 030507 speech-language pathology & audiology 03 medical and health sciences Computer Science::Sound 0103 physical sciences Prior probability 0305 other medical science Joint (audio engineering) 010301 acoustics |
| Zdroj: | 2018 15th IEEE India Council International Conference (INDICON). |
| DOI: | 10.1109/indicon45594.2018.8986979 |
| Popis: | Reverberation and ambient noise present in an audio scene degrades the speech intelligibility and perceptual quality of speech based query applications. The problem of joint speech dereverberation and denoising is challenging when compared to sequential dereverberation and denoising. In this paper this joint problem is solved by a using a model-based optimization technique for dereveberation and a corresponding DNN with deep priors for the denoising part. This joint enhancement algorithm is then applied to every channel in a multi-channel scenario. The processed outputs of every channel are then combined using beamforming method to compute a spatially filtered signal. This method therefore utilities both spectral and beam forming techniques for speech enhancement in a multi channel scenario. Subjective, objective Word error rate evaluations indicate a significant improvement under both noisy and reverberant conditions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|