DNN-FREE LOW-LATENCY ADAPTIVE SPEECH ENHANCEMENT BASED ON FRAME-ONLINE BEAMFORMING POWERED BY BLOCK-ONLINE FASTMNMF - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

DNN-FREE LOW-LATENCY ADAPTIVE SPEECH ENHANCEMENT BASED ON FRAME-ONLINE BEAMFORMING POWERED BY BLOCK-ONLINE FASTMNMF

Résumé

This paper describes a practical dual-process speech enhancement system that adapts environment-sensitive frame-online beamforming (front-end) with help from environment-free block-online source separation (back-end). To use minimum variance distortionless response (MVDR) beamforming, one may train a deep neural network (DNN) that estimates timefrequency masks used for computing the covariance matrices of sources (speech and noise). Backpropagation-based runtime adaptation of the DNN was proposed for dealing with the mismatched training-test conditions. Instead, one may try to directly estimate the source covariance matrices with a state-ofthe-art blind source separation method called fast multichannel non-negative matrix factorization (FastMNMF). In practice, however, neither the DNN nor the FastMNMF can be updated in a frame-online manner due to its computationally-expensive iterative nature. Our DNN-free system leverages the posteriors of the latest source spectrograms given by block-online FastMNMF to derive the current source covariance matrices for frame-online beamforming. The evaluation shows that our frame-online system can quickly respond to scene changes caused by interfering speaker movements and outperformed an existing block-online system with DNN-based beamforming by 5.0 points in terms of the word error rate.
Fichier principal
Vignette du fichier
2207.10934.pdf (635.16 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03821095 , version 1 (19-10-2022)

Identifiants

  • HAL Id : hal-03821095 , version 1

Citer

Aditya Arie Nugraha, Kouhei Sekiguchi, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii. DNN-FREE LOW-LATENCY ADAPTIVE SPEECH ENHANCEMENT BASED ON FRAME-ONLINE BEAMFORMING POWERED BY BLOCK-ONLINE FASTMNMF. 17th International Workshop on Acoustic Signal Enhancement (IWAENC 2022), 2022, Bamberg, Germany. ⟨hal-03821095⟩
13 Consultations
102 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More