Cross Domain Optimization for Speech Enhancement: Parallel or Cascade?
- 26 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 4328-4341
Abstract
This paper introduces five novel deep-learning architectures for speech enhancement. Existing methods typically use time-domain, time-frequency representations, or a hybrid approach. Recognizing the unique contributions of each domain to feature extraction and model design, this study investigates the integration of waveform and complex spectrogram models through cross-domain fusion to enhance speech feature learning and noise reduction, thereby improving speech quality. We examine both cascading and parallel configurations of waveform and complex spectrogram models to assess their effectiveness in speech enhancement. Additionally, we employ an orthogonal projection-based error decomposition technique and manage the inputs of individual sub-models to analyze factors affecting speech quality. The network is trained by optimizing three specific loss functions applied across all sub-models. Our experiments, using the DNS Challenge (ICASSP 2021) dataset, reveal that the proposed models surpass existing benchmarks in speech enhancement, offering superior speech quality and intelligibility. These results highlight the efficacy of our cross-domain fusion strategyKeywords
This publication has 39 references indexed in Scilit:
- TSTNN: Two-Stage Transformer Based Neural Network for Speech Enhancement in the Time Domain2021
- Fullsubnet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement2021
- ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network2021
- ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks2020
- Complex Spectral Mapping with a Convolutional Recurrent Network for Monaural Speech Enhancement2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks2015
- On Ideal Binary Mask As the Computational Goal of Auditory Scene Analysis2006
- Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs2002
- Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systemsSpeech Communication, 1993