No Arabic abstract
Although deep learning algorithms are widely used for improving speech enhancement (SE) performance, the performance remains limited under highly challenging conditions, such as unseen noise or noise signals having low signal-to-noise ratios (SNRs). This study provides a pilot investigation on a novel multimodal audio-articulatory-movement SE (AAMSE) model to enhance SE performance under such challenging conditions. Articulatory movement features and acoustic signals were used as inputs to waveform-mapping-based and spectral-mapping-based SE systems with three fusion strategies. In addition, an ablation study was conducted to evaluate SE performance using a limited number of articulatory movement sensors. Experimental results confirm that, by combining the modalities, the AAMSE model notably improves the SE performance in terms of speech quality and intelligibility, as compared to conventional audio-only SE baselines.
In noisy conditions, knowing speech contents facilitates listeners to more effectively suppress background noise components and to retrieve pure speech signals. Previous studies have also confirmed the benefits of incorporating phonetic information in a speech enhancement (SE) system to achieve better denoising performance. To obtain the phonetic information, we usually prepare a phoneme-based acoustic model, which is trained using speech waveforms and phoneme labels. Despite performing well in normal noisy conditions, when operating in very noisy conditions, however, the recognized phonemes may be erroneous and thus misguide the SE process. To overcome the limitation, this study proposes to incorporate the broad phonetic class (BPC) information into the SE process. We have investigated three criteria to build the BPC, including two knowledge-based criteria: place and manner of articulatory and one data-driven criterion. Moreover, the recognition accuracies of BPCs are much higher than that of phonemes, thus providing more accurate phonetic information to guide the SE process under very noisy conditions. Experimental results demonstrate that the proposed SE with the BPC information framework can achieve notable performance improvements over the baseline system and an SE system using monophonic information in terms of both speech quality intelligibility on the TIMIT dataset.
Previous studies have confirmed the effectiveness of leveraging articulatory information to attain improved speech enhancement (SE) performance. By augmenting the original acoustic features with the place/manner of articulatory features, the SE process can be guided to consider the articulatory properties of the input speech when performing enhancement. Hence, we believe that the contextual information of articulatory attributes should include useful information and can further benefit SE. In this study, we propose an SE system that incorporates contextual articulatory information; such information is obtained using broad phone class (BPC) end-to-end automatic speech recognition (ASR). Meanwhile, two training strategies are developed to train the SE system based on the BPC-based ASR: multitask-learning and deep-feature training strategies. Experimental results on the TIMIT dataset confirm that the contextual articulatory information facilitates an SE system in achieving better results. Moreover, in contrast to another SE system that is trained with monophonic ASR, the BPC-based ASR (providing contextual articulatory information) can improve the SE performance more effectively under different signal-to-noise ratios(SNR).
Recent single-channel speech enhancement methods based on deep neural networks (DNNs) have achieved remarkable results, but there are still generalization problems in real scenes. Like other data-driven methods, DNN-based speech enhancement models produce significant performance degradation on untrained data. In this study, we make full use of the contribution of multi-target joint learning to the model generalization capability, and propose a lightweight and low-computing dilated convolutional network (DCN) model for a more robust speech denoising task. Our goal is to integrate the masking target, the mapping target, and the parameters of the traditional speech enhancement estimator into a DCN model to maximize their complementary advantages. To do this, we build a multi-stage learning framework to deal with multiple targets in stages to achieve their joint learning, namely `MT-in-MS. Our experimental results show that compared with the state-of-the-art time domain and time-frequency domain models, this proposed low-cost DCN model can achieve better generalization performance in speaker, noise, and channel mismatch cases.
Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (namely, eliminating non-target signals from the Gaussian noise and noisy signals) could be utilized to restore clean signals. Based on this property, we propose a diffusion probabilistic model-based speech enhancement (DiffuSE) model that aims to recover clean speech signals from noisy signals. The fundamental architecture of the proposed DiffuSE model is similar to that of DiffWave--a high-quality audio waveform generation model that has a relatively low computational cost and footprint. To attain better enhancement performance, we designed an advanced reverse process, termed the supportive reverse process, which adds noisy speech in each time-step to the predicted speech. The experimental results show that DiffuSE yields performance that is comparable to related audio generative models on the standardized Voice Bank corpus SE task. Moreover, relative to the generally suggested full sampling schedule, the proposed supportive reverse process especially improved the fast sampling, taking few steps to yield better enhancement results over the conventional full step inference process.
Synthesized speech from articulatory movements can have real-world use for patients with vocal cord disorders, situations requiring silent speech, or in high-noise environments. In this work, we present EMA2S, an end-to-end multimodal articulatory-to-speech system that directly converts articulatory movements to speech signals. We use a neural-network-based vocoder combined with multimodal joint-training, incorporating spectrogram, mel-spectrogram, and deep features. The experimental results confirm that the multimodal approach of EMA2S outperforms the baseline system in terms of both objective evaluation and subjective evaluation metrics. Moreover, results demonstrate that joint mel-spectrogram and deep feature loss training can effectively improve system performance.