Search

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy condition during testing, i.e., the performance is generally sub-optimal when models are tested with unseen noise types that are not involved in the training data; (2) local focus on specific noisy conditions, i.e., models trained using multiple types of noises cannot optimally remove a specific noise type even though the noise type has been involved in the training data. These problems are common in real applications. In this article, we propose a novel denoising autoencoder with a multi-branched encoder (termed DAEME) model to deal with these two problems. In the DAEME model, two stages are involved: training and testing. In the training stage, we build multiple component models to form a multi-branched encoder based on a decision tree (DSDT). The DSDT is built based on prior knowledge of speech and noisy conditions (the speaker, environment, and signal factors are considered in this paper), where each component of the multi-branched encoder performs a particular mapping from noisy to clean speech along the branch in the DSDT. Finally, a decoder is trained on top of the multi-branched encoder. In the testing stage, noisy speech is first processed by each component model. The multiple outputs from these models are then integrated into the decoder to determine the final enhanced speech. Experimental results show that DAEME is superior to several baseline models in terms of objective evaluation metrics, automatic speech recognition results, and quality in subjective human listening tests.

Nonlinear spectral mapping-based models based on supervised learning have successfully applied for speech enhancement. However, as supervised learning approaches, a large amount of labelled data (noisy-clean speech pairs) should be provided to train those models. In addition, their performances for unseen noisy conditions are not guaranteed, which is a common weak point of supervised learning approaches. In this study, we proposed an unsupervised learning approach for speech enhancement, i.e., denoising autoencoder with linear regression decoder (DAELD) model for speech enhancement. The DAELD is trained with noisy speech as both input and target output in a self-supervised learning manner. In addition, with properly setting a shrinkage threshold for internal hidden representations, noise could be removed during the reconstruction from the hidden representations via the linear regression decoder. Speech enhancement experiments were carried out to test the proposed model. Results confirmed that the proposed DAELD could achieve comparable and sometimes even better enhancement performance as compared to the conventional supervised speech enhancement approaches, in both seen and unseen noise environments. Moreover, we observe that higher performances tend to achieve by DAELD when the training data cover more diverse noise types and signal-tonoise-ratio (SNR) levels.

In this study, we compare the speech enhancement performance based on hierarchical extreme learning machine (HELM) with two distinct strategies: masking and mapping. Experimental results of the perceptual evaluation of speech quality (PESQ) show that for both of limited and sufficient amounts of training data, mapping-based HELM tends to be more effective to improve the performance of speech enhancement.

In this paper, we present a simple yet effective deep denoising autoencoder (DDAE) based post-filter (DPF) approach for speech enhancement (SE). The DPF is designed to estimate the spectral difference of clean-noisy speech pair based on the enhanced-noisy speech pair. The difference estimated by the DPF approach is then used to compensate the noisy speech to obtain the final enhanced speech. We integrate the proposed DPF approach with one traditional SE method (minimum mean square error) and one deep-learning-based SE method (DDAE). Experiments on various noise types and signal-to-noise-ratio conditions were carried out to test the integrated systems. Results of three standardized objective evaluation metrics and automatic speech recognition (ASR) tests confirm that integrating the proposed DPF can improve the performance in further reducing spectral distortions and enhancing the speech quality and intelligibility.