Real-Time Neural Speech Enhancement Based on Temporal Refinement Network and Channel-Wise Gating Methods

International Journal
2023-01-30 16:43
Authors : Jinyoung Lee, Hong-Goo Kang

Year : 2023

Publisher / Conference : Digital Signal Processing

Volume : 133

Research area : Speech Signal Processing, Speech Enhancement

Presentation/Publication date : 08 December 2022

Presentation : None

Neural speech enhancement systems have seen dramatic improvements in performance recently. However, it is still difficult to create systems that can operate in real-time, with low delay, low complexity, and causality. In this paper, we propose a temporal and channel attention framework for a U-Net-based speech enhancement architecture that uses short analysis frame lengths. Specifically, we propose an attention-based temporal refinement network (TRN) that estimates convolutional features subject to the importance of temporal location. By adding the TRN output to the channel-attentive convolution output, we can further enhance speech-related features even in low-attentive channel outputs. To further improve the representation power of the convolutional features, we also apply a squeeze-and-excitation (SE)-based channel attention mechanism for three different network modules: main convolutional blocks after processing the TRN, skip connections, and residual connections in the bottleneck recurrent neural network (RNN) layer. In particular, a channel-wise gate architecture placed on the skip connections and residual connections reliably controls the data flow, which avoids transferring redundant information to the following stages. We show the effectiveness of the proposed TRN and channel-wise gating methods by visualizing the spectral characteristics of the corresponding features, evaluating overall enhancement performance, and performing ablation studies in various configurations. Our proposed real-time enhancement system outperforms several recent neural enhancement models in terms of quality, model size, and complexity.
전체 344
344 International Journal Zhenyu Piao, Hyungseob Lim, Miseul Kim, Hong-goo Kang "PDF-NET: Pitch-adaptive Dynamic Filter Network for Intra-gender Speaker Verification" in APSIPA ASC, 2023
343 International Conference WooSeok Ko, Seyun Um, Zhenyu Piao, Hong-goo Kang "Consideration of Varying Training Lengths for Short-Duration Speaker Verification" in APSIP ASC, 2023
342 International Journal Hyungchan Yoon, Changhwan Kim, Seyun Um, Hyun-Wook Yoon, Hong-Goo Kang "SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems" in IEEE Signal Processing Letters, vol.30, pp.593-597, 2023
341 International Conference Miseul Kim, Zhenyu Piao, Jihyun Lee, Hong-Goo Kang "BrainTalker: Low-Resource Brain-to-Speech Synthesis with Transfer Learning using Wav2Vec 2.0" in The IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2023
340 International Conference Seyun Um, Jihyun Kim, Jihyun Lee, Hong-Goo Kang "Facetron: A Multi-speaker Face-to-Speech Model based on Cross-Modal Latent Representations" in EUSIPCO, 2023
339 International Conference Hejung Yang, Hong-Goo Kang "Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement" in INTERSPEECH, 2023
338 International Conference Jihyun Kim, Hong-Goo Kang "Contrastive Learning based Deep Latent Masking for Music Source Seperation" in INTERSPEECH, 2023
337 International Conference Woo-Jin Chung, Doyeon Kim, Soo-Whan Chung, Hong-Goo Kang "MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion" in INTERSPEECH, 2023
336 International Conference Hyungchan Yoon, Seyun Um, Changhwan Kim, Hong-Goo Kang "Adversarial Learning of Intermediate Acoustic Feature for End-to-End Lightweight Text-to-Speech" in INTERSPEECH, 2023
335 International Conference Hyungchan Yoon, Changhwan Kim, Eunwoo Song, Hyun-Wook Yoon, Hong-Goo Kang "Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech" in INTERSPEECH, 2023