Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation

• URL: http://arxiv.org/abs/2211.12632v1
• Date: Tue, 22 Nov 2022 23:38:10 GMT
• Title: Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation
• Authors: Vinay Kothapally, John H.L. Hansen
• Abstract summary: We propose a complex-valued T-F attention (TFA) module that models spectral and temporal dependencies. We validate the effectiveness of our proposed complex-valued TFA module with the deep complex convolutional recurrent network (DCCRN) using the REVERB challenge corpus. Experimental findings indicate that integrating our complex-TFA module with DCCRN improves overall speech quality and performance of back-end speech applications.
• Score: 39.64103126881576
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Several speech processing systems have demonstrated considerable performance improvements when deep complex neural networks (DCNN) are coupled with self-attention (SA) networks. However, the majority of DCNN-based studies on speech dereverberation that employ self-attention do not explicitly account for the inter-dependencies between real and imaginary features when computing attention. In this study, we propose a complex-valued T-F attention (TFA) module that models spectral and temporal dependencies by computing two-dimensional attention maps across time and frequency dimensions. We validate the effectiveness of our proposed complex-valued TFA module with the deep complex convolutional recurrent network (DCCRN) using the REVERB challenge corpus. Experimental findings indicate that integrating our complex-TFA module with DCCRN improves overall speech quality and performance of back-end speech applications, such as automatic speech recognition, compared to earlier approaches for self-attention.

Related papers

• Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate [16.4160685571157]
  Recurrent Neural Networks (RNNs) are widely recognized for their proficiency in modeling temporal dependencies. This paper proposes a novel Delayed Memory Unit (DMU) for gated RNNs. The DMU incorporates a delay line structure along with delay gates into vanilla RNN, thereby enhancing temporal interaction and facilitating temporal credit assignment.
  arXiv  Detail & Related papers  (2023-10-23T14:29:48Z)
• Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Tasks [4.132793413136553]
  We introduce Echo-MSA, a nimble module equipped with a variable-length attention mechanism. The proposed design captures the variable length feature of speech and addresses the limitations of fixed-length attention.
  arXiv  Detail & Related papers  (2023-09-14T14:51:51Z)
• Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement [16.701596804113553]
  We explore self-attention in the DPCRN module and design a model called Multi-Loss Convolutional Network with Time-Frequency Attention(MNTFA) for speech enhancement. Compared to DPRNN, axial self-attention greatly reduces the need for memory and computation. We propose a joint training method of a multi-resolution STFT loss and a WavLM loss using a pre-trained WavLM network.
  arXiv  Detail & Related papers  (2023-06-15T08:48:19Z)
• End-to-End Active Speaker Detection [58.7097258722291]
  We propose an end-to-end training network where feature learning and contextual predictions are jointly learned. We also introduce intertemporal graph neural network (iGNN) blocks, which split the message passing according to the main sources of context in the ASD problem. Experiments show that the aggregated features from the iGNN blocks are more suitable for ASD, resulting in state-of-the art performance.
  arXiv  Detail & Related papers  (2022-03-27T08:55:28Z)
• MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterances [94.70787497137854]
  We propose a multi-scale frequency-channel attention (MFA) to characterize speakers at different scales through a novel dual-path design which consists of a convolutional neural network and TDNN. We evaluate the proposed MFA on the VoxCeleb database and observe that the proposed framework with MFA can achieve state-of-the-art performance while reducing parameters and complexity.
  arXiv  Detail & Related papers  (2022-02-03T14:57:05Z)
• SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition [49.42625022146008]
  We present the advantages of applying SRU++ in ASR tasks by comparing with Conformer across multiple ASR benchmarks. Specifically, SRU++ can surpass Conformer on long-form speech input with a large margin, based on our analysis.
  arXiv  Detail & Related papers  (2021-10-11T19:23:50Z)
• MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation [45.90599689005832]
  Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR. We present a self-attentive RNN beamformer to further improve our previous RNN-based beamformer by leveraging on the powerful modeling capability of self-attention.
  arXiv  Detail & Related papers  (2021-04-17T05:02:04Z)
• Capturing Multi-Resolution Context by Dilated Self-Attention [58.69803243323346]
  We propose a combination of restricted self-attention and a dilation mechanism, which we refer to as dilated self-attention. The restricted self-attention allows attention to neighboring frames of the query at a high resolution, and the dilation mechanism summarizes distant information to allow attending to it with a lower resolution. ASR results demonstrate substantial improvements compared to restricted self-attention alone, achieving similar results compared to full-sequence based self-attention with a fraction of the computational costs.
  arXiv  Detail & Related papers  (2021-04-07T02:04:18Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.