Exploring multi-channel features for denoising-autoencoder-based speech enhancement

We consider the problem of robust automatic speech recognition (ASR) in the context of the CHiME-3 Challenge. The proposed system combines three contributions. First, we propose a deep neural network (DNN) based multichannel speech enhancement technique, where the speech and noise spectra are estimated using a DNN based regressor and the spatial parameters are derived in an expectation-maximization (EM) like fashion. Second, a conditional restricted Boltzmann machine (CRBM) model is trained using the obtained enhanced speech and used to generate simulated training and development datasets. The goal is to increase the similarity between simulated and real data, so as to increase the benefit of multicondition training. Finally, we make some changes to the ASR backend. Our system ranked 4th among 25 entries.

Combined speech enhancement and auditory modelling for robust distributed speech recognition

Recent work on multichannel end-to-end automatic speech recognition (ASR) has shown that multichannel speech enhancement and speech recognition functions can be integrated into a deep neural network (DNN)-based system, and promising experimental results have been shown using the CHiME-4 and AMI corpora. In other recent DNN-based hidden Markov model (DNN-HMM) hybrid architectures, the effectiveness of speaker adaptation has been well established. Motivated by these results, we propose a multi-path adaptation scheme for end-to-end multichannel ASR, which combines the unprocessed noisy speech features with a speech-enhanced pathway to improve upon previous end-to-end ASR approaches. Experimental results using CHiME-4 show that (1) our proposed multi-path adaptation scheme improves ASR performance and (2) adapting the encoder network is more effective than adapting the neural beamformer, attention mechanism, or decoder network.

A complex-valued multichannel speech enhancement learning algorithm for optimal tradeoff between noise reduction and speech distortion

Accurate and effective voice activity detection (VAD) is a fundamental step for robust speech or speaker recognition. In this study, we proposed a hierarchical framework approach for VAD and speech enhancement. The modified Wiener filter (MWF) approach is utilized for noise reduction in the speech enhancement block. For the feature selection and voting block, several discriminating features were employed in a voting paradigm for the consideration of reliability and discriminative power. Effectiveness of the proposed approach is compared and evaluated to other VAD techniques by using two well-known databases, namely, TIMIT database and NOISEX-92 database. Experimental results show that the proposed method performs well under a variety of noisy conditions.

In this paper a multi-channel speech enhancement framework for distant speech acquisition in noisy and reverberant environments for Non-negative Matrix Factorization (NMF)-based Automatic Speech Recognition (ASR) is proposed. The system is evaluated for its use in an assistive vocal interface for physically impaired and speech-impaired users. The framework utilises the Spatially Pre-processed Speech Distortion Weighted Multichannel Wiener Filter (SP-SDW-MWF) in combination with a postfilter to reduce noise and reverberation. Additionally, the estimation uncertainty of the speech enhancement framework is propagated through the Mel-Frequency Cepstrum Coefficients (MFCC) feature extraction to allow for feature compensation in a later stage. Results indicate that a) using a trade-off parameter between noise reduction and speech distortion has a positive effect on the recognition performance with respect to the well-known GSC and MWF and b) the addition of a postfilter and the feature compensation increases performance with respect to several baselines for a non-pathological and pathological speaker. Index Terms: multi-channel speech enhancement, speech recognition, uncertainty of estimation, dysarthric speech

Speech is easily interfered by external environment in reality, which results in the loss of important features. Deep learning has become a popular speech enhancement method because of its superior potential in solving nonlinear mapping problems for complex features. However, the deficiency of traditional deep learning methods is the weak learning capability of important information from previous time steps and long-term event dependencies between the time-series data. To overcome this problem, we propose a novel speech enhancement method based on the fused features of deep neural networks (DNNs) and gated recurrent unit (GRU). The proposed method uses GRU to reduce the number of parameters of DNNs and acquire the context information of the speech, which improves the enhanced speech quality and intelligibility. Firstly, DNN with multiple hidden layers is used to learn the mapping relationship between the logarithmic power spectrum (LPS) features of noisy speech and clean speech. Secondly, the LPS feature of the deep neural network is fused with the noisy speech as the input of GRU network to compensate the missing context information. Finally, GRU network is performed to learn the mapping relationship between LPS features and log power spectrum features of clean speech spectrum. The proposed model is experimentally compared with traditional speech enhancement models, including DNN, CNN, LSTM and GRU. Experimental results demonstrate that the PESQ, SSNR and STOI of the proposed algorithm are improved by 30.72%, 39.84% and 5.53%, respectively, compared with the noise signal under the condition of matched noise. Under the condition of unmatched noise, the PESQ and STOI of the algorithm are improved by 23.8% and 37.36%, respectively. The advantage of the proposed method is that it uses the key information of features to suppress noise in both matched and unmatched noise cases and the proposed method outperforms other common methods in speech enhancement.

We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work [1] demonstrates that GANs can effectively suppress additive noise in raw waveform speech signals, improving perceptual quality metrics; however this technique was not justified in the context of ASR. In this work, we conduct a detailed study to measure the effectiveness of GANs in enhancing speech contaminated by both additive and reverberant noise. Motivated by recent advances in image processing [2], we propose operating GANs on log-Mel filterbank spectra instead of waveforms, which requires less computation and is more robust to reverberant noise. While GAN enhancement improves the performance of a clean-trained ASR system on noisy speech, it falls short of the performance achieved by conventional multi-style training (MTR). By appending the GAN-enhanced features to the noisy inputs and retraining, we achieve a 7% WER improvement relative to the MTR system.

Wiener filtering based speech enhancement with Weighted Denoising Auto-encoder and noise classification

The study focuses on acoustic characteristics of cardiac auscultation for recognition of the first sound of heart (S1) and second sound of heart (S2) for cardiovascular disease. DNN (Deep Neural Network) method with Autoencoder was proposed for heart sound recognition along with spectrogram for visual representation performance of S1 and S2 classification. Mel-Frequency Cepstral Coefficients (MFCCs) conversion sequence is carried first from heart sound signals and algorithm of K-means along with Shannon energy is applied to MFCC features for refining the representation, refined features applied to spectrogram through Denoising Autoencoder (DAE) and AE(Autoencoder) for unsupervised learning of DNN to classify S1 and S2. The proposed system is a DNN-based method of spectrogram with DAE and 1-AE can achieve higher accuracy when compared to other classification methods of S1 and S2 heart sounds.KeywordsSpectrogramAutoencoderDNNDenoising autoencoder

Supervised models for speech enhancement are trained using artificially generated mixtures of clean speech and noise signals. However, the synthetic training conditions may not accurately reflect real-world conditions encountered during testing. This discrepancy can result in poor performance when the test domain significantly differs from the synthetic training domain. To tackle this issue, the UDASE task of the 7th CHiME challenge aimed to leverage real-world noisy speech recordings from the test domain for unsupervised domain adaptation of speech enhancement models. Specifically, this test domain corresponds to the CHiME-5 dataset, characterized by real multi-speaker and conversational speech recordings made in noisy and reverberant domestic environments, for which ground-truth clean speech signals are not available. In this paper, we present the objective and subjective evaluations of the systems that were submitted to the CHiME-7 UDASE task, and we provide an analysis of the results. This analysis reveals a limited correlation between subjective ratings and several supervised nonintrusive performance metrics recently proposed for speech enhancement. Conversely, the results suggest that more traditional intrusive objective metrics can be used for in-domain performance evaluation using the reverberant LibriCHiME-5 dataset developed for the challenge. The subjective evaluation indicates that all systems successfully reduced the background noise, but always at the expense of increased distortion. Out of the four speech enhancement methods evaluated subjectively, only one demonstrated an improvement in overall quality compared to the unprocessed noisy speech, highlighting the difficulty of the task. The tools and audio material created for the CHiME-7 UDASE task are shared with the community Key Terms: Speech Enhancement, CHIME-7 Challenge ,Deep Neural Networks, UDASE Task, Audio Restoration, Subjective Evaluation, objective Evaluation

Since the introduction of deep neural network (DNN)-based acoustic model, robust automatic speech recognition using DNN are being in research. Especially in model adaptation, the techniques utilizing auxiliary context features is known to be a promising technique. Recently, we proposed a technique which is called two-stage noise-aware training (TSNAT). The key idea of TS-NAT is to let the DNN clarify the relationship among noise estimate, noisy features and phonetic target through clean feature representation. However, although TS-NAT enhances the robustness of the DNN, we cannot be certain whether TS-NAT describes the clean feature representation sufficiently. In this paper, we extend TS-NAT using true noise feature and various DNN training techniques. It has been shown that the proposed technique outperforms the conventional DNN-based techniques on Aurora5-task and mismatched noise conditions.

Speech enhancement (SE) is crucial for improving the intelligibility and quality of noisy speech in applications such as speech recognition and assistive technologies. While traditional SE methods often fail in complex noise environments, deep learning-based approaches and multi-modal techniques have shown significant progress. However, existing multi-modal SE methods, such as audio-visual approaches, are limited in scenarios where visual data cannot be captured. EMG-SENet-basic explores Electromyography (EMG) signals as a robust complementary modality for SE, leveraging their resistance to environmental noise and potential for non-invasive acquisition. In addition, we propose an improved multi-modal SE framework named EMG-SENet-improved featuring a frame-level cross-attention mechanism for dynamic feature fusion, an adaptive weighting mechanism to better integrate amplitude information from both modalities, and the Con-TF-Mamba architecture to enhance local feature extraction in time and frequency domains. Furthermore, Temporal Masking, used to simulate frame loss, improves robustness under real-world conditions. Experimental results demonstrate the proposed method’s superior performance in enhancing SE quality and intelligibility, addressing key challenges in practical applications with degraded or incomplete data.

Recently, deep neural networks (DNNs) have become the mainstream strategy for speech enhancement task because it can achieve the higher speech quality and intelligibility than the traditional methods. However, these DNN-based methods always need a large number of parallel corpus consisting of clean speech and noise to produce noisy data for the training of the DNN in order to improve the generalization of the network. As a result, this implies that many noisy speech signals that are collected in real environment cannot be used to train the DNN because of the lack of corresponding clean speech and noise. Additionally, as we know, noise varies with the time and scenario, so we cannot obtain parallel speech and noise due to infinite noise data and some limited speech data. Thus, the network training with unparallel speech and noise data is essential for the generalization of the network. To address this problem, we propose a novel parallel-data-free speech enhancement method, in which the cycle-consistent generative adversarial network (CycleGAN) and multi-objective learning are employed. Our method is also able to make best use of the benefits of multi-objective learning. On the training stage, we utilize two different encoders to encode the features of clean speech and noisy speech, respectively. Then, two forward generators are immediately used to predict the ideal time-frequency (T-F) mask and log-power spectrum (LPS) of clean speech. Two inverse generators are applied to map the magnitude spectrum (MS) and LPS of noisy speech, respectively. In addition, four discriminators are used to distinguish the real speech features from the generated features. Two encoders, four generators and four discriminators are simultaneously trained by using adversarial, identity-mapping, latent similarity and cycle-consistent loss. On the test stage, we directly utilize the forward generators and encoders to acquire the enhanced speech. The experimental results indicate that the proposed approach is able to achieve the better speech enhancement performance than the reference methods. Moreover, the proposed method is also effective to improve speech quality and intelligibility when the networks are trained under the parallel data.

In this paper, we propose a novel speech enhancement (SE) method by exploiting the discrete wavelet transform (DWT). This new method reduces the amount of fast time-varying portion, viz. the DWT-wise detail component, in the spectrogram of speech signals so as to highlight the speech-dominant component and achieves better speech quality. A particularity of this new method is that it is completely unsupervised and requires no prior information about the clean speech and noise in the processed utterance. The presented DWT-based SE method with various scaling factors for the detail part is evaluated with a subset of Aurora-2 database, and the PESQ metric is used to indicate the quality of processed speech signals. The preliminary results show that the processed speech signals reveal a higher PESQ score in comparison with the original counterparts. Furthermore, we show that this method can still enhance the signal by totally discarding the detail part (setting the respective scaling factor to zero), revealing that the spectrogram can be down-sampled and thus compressed without the cost of lowered quality. In addition, we integrate this new method with conventional speech enhancement algorithms, including spectral subtraction, Wiener filtering, and spectral MMSE estimation, and show that the resulting integration behaves better than the respective component method. As a result, this new method is quite effective in improving the speech quality and well additive to the other SE methods.