Previous studies have confirmed the effectiveness of incorporating visual information into speech enhancement (SE) systems. Despite improved denoising performance, two problems may be encountered when implementing an audio-visual SE (AVSE) system: (1) additional processing costs are incurred to incorporate visual input and (2) the use of face or lip images may cause privacy problems. In this study, we propose a Lite AVSE (LAVSE) system to address these problems. The system includes two visual data compression techniques and removes the visual feature extraction network from the training model, yielding better online computation efficiency. Our experimental results indicate that the proposed LAVSE system can provide notably better performance than an audio-only SE system with a similar number of model parameters. In addition, the experimental results confirm the effectiveness of the two techniques for visual data compression.
Numerous noise adaptation techniques have been proposed to address the mismatch problem in speech enhancement (SE) by fine-tuning deep-learning (DL)-based models. However, adaptation to a target domain can lead to catastrophic forgetting of the previously learnt noise environments. Because SE models are commonly used in embedded devices, re-visiting previous noise environments is a common situation in speech enhancement. In this paper, we propose a novel regularization-based incremental learning SE (SERIL) strategy, which can complement these noise adaptation strategies without having to access previous training data. The experimental results show that, when faced with a new noise domain, the SERIL model outperforms the unadapted SE model in various metrics: PESQ, STOI, eSTOI, and short-time spectral amplitude SDR. Meanwhile, compared with the traditional fine-tuning adaptive SE model, the SERIL model can significantly reduce the forgetting of previous noise environments by 52%. The promising results indicate that the SERIL model can effectively overcome the catastrophic forgetting problem and can be suitably deployed in real-world applications, where the noise environment changes frequently.
Due to the simple design pipeline, end-to-end (E2E) neural models for speech enhancement (SE) have attracted great interest. In order to improve the performance of the E2E model, the locality and temporal sequential properties of speech should be efficiently taken into account when modelling. However, in most current E2E models for SE, these properties are either not fully considered or are too complex to be realized. In this paper, we propose an efficient E2E SE model, termed WaveCRN. In WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the temporal sequential property of the locality feature is modeled by stacked simple recurrent units (SRU). Unlike a conventional temporal sequential model that uses a long short-term memory (LSTM) network, which is difficult to parallelize, SRU can be efficiently parallelized in calculation with even fewer model parameters. In addition, in order to more effectively suppress the noise components in the input noisy speech, we derive a novel restricted feature masking (RFM) approach that performs enhancement on the feature maps in the hidden layers; this is different from the approach that applies the estimated ratio mask on the noisy spectral features, which is commonly used in speech separation methods. Experimental results on speech denoising and compressed speech restoration tasks confirm that with the lightweight architecture of SRU and the feature-mapping-based RFM, WaveCRN performs comparably with other state-of-the-art approaches with notably reduced model complexity and inference time.
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic features of different properties, to improve the performance of VAE-VC. We believed that the success came from more disentangled latent representations. In this paper, we extend the CDVAE-VC framework by incorporating the concept of adversarial learning, in order to further increase the degree of disentanglement, thereby improving the quality and similarity of converted speech. More specifically, we first investigate the effectiveness of incorporating the generative adversarial networks (GANs) with CDVAE-VC. Then, we consider the concept of domain adversarial training and add an explicit constraint to the latent representation, realized by a speaker classifier, to explicitly eliminate the speaker information that resides in the latent code. Experimental results confirm that the degree of disentanglement of the learned latent representation can be enhanced by both GANs and the speaker classifier. Meanwhile, subjective evaluation results in terms of quality and similarity scores demonstrate the effectiveness of our proposed methods.
Speech-related applications deliver inferior performance in complex noise environments. Therefore, this study primarily addresses this problem by introducing speech-enhancement (SE) systems based on deep neural networks (DNNs) applied to a distributed microphone architecture. The first system constructs a DNN model for each microphone to enhance the recorded noisy speech signal, and the second system combines all the noisy recordings into a large feature structure that is then enhanced through a DNN model. As for the third system, a channel-dependent DNN is first used to enhance the corresponding noisy input, and all the channel-wise enhanced outputs are fed into a DNN fusion model to construct a nearly clean signal. All the three DNN SE systems are operated in the acoustic frequency domain of speech signals in a diffuse-noise field environment. Evaluation experiments were conducted on the Taiwan Mandarin Hearing in Noise Test (TMHINT) database, and the results indicate that all the three DNN-based SE systems provide the original noise-corrupted signals with improved speech quality and intelligibility, whereas the third system delivers the highest signal-to-noise ratio (SNR) improvement and optimal speech intelligibility.
In recent years, waveform-mapping-based speech enhancement (SE) methods have garnered significant attention. These methods generally use a deep learning model to directly process and reconstruct speech waveforms. Because both the input and output are in waveform format, the waveform-mapping-based SE methods can overcome the distortion caused by imperfect phase estimation, which may be encountered in spectral-mapping-based SE systems. So far, most waveform-mapping-based SE methods have focused on single-channel tasks. In this paper, we propose a novel fully convolutional network (FCN) with Sinc and dilated convolutional layers (termed SDFCN) for multichannel SE that operates in the time domain. We also propose an extended version of SDFCN, called the residual SDFCN (termed rSDFCN). The proposed methods are evaluated on two multichannel SE tasks, namely the dual-channel inner-ear microphones SE task and the distributed microphones SE task. The experimental results confirm the outstanding denoising capability of the proposed SE systems on both tasks and the benefits of using the residual architecture on the overall SE performance.
In this paper, we tackle the problem of transfer learning for Jazz automatic generation. Jazz is one of representative types of music, but the lack of Jazz data in the MIDI format hinders the construction of a generative model for Jazz. Transfer learning is an approach aiming to solve the problem of data insufficiency, so as to transfer the common feature from one domain to another. In view of its success in other machine learning problems, we investigate whether, and how much, it can help improve automatic music generation for under-resourced musical genres. Specifically, we use a recurrent variational autoencoder as the generative model, and use a genre-unspecified dataset as the source dataset and a Jazz-only dataset as the target dataset. Two transfer learning methods are evaluated using six levels of source-to-target data ratios. The first method is to train the model on the source dataset, and then fine-tune the resulting model parameters on the target dataset. The second method is to train the model on both the source and target datasets at the same time, but add genre labels to the latent vectors and use a genre classifier to improve Jazz generation. The evaluation results show that the second method seems to perform better overall, but it cannot take full advantage of the genre-unspecified dataset.