Kuo-Hsuan Hung

Szu-Wei Fu, Kuo-Hsuan Hung, Yu Tsao et al.

Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label collection. To solve this problem, we propose VQScore, a self-supervised metric for evaluating speech based on the quantization error of a vector-quantized-variational autoencoder (VQ-VAE). The training of VQ-VAE relies on clean speech; hence, large quantization errors can be expected when the speech is distorted. To further improve correlation with real quality scores, domain knowledge of speech processing is incorporated into the model design. We found that the vector quantization mechanism could also be used for self-supervised speech enhancement (SE) model training. To improve the robustness of the encoder for SE, a novel self-distillation mechanism combined with adversarial training is introduced. In summary, the proposed speech quality estimation method and enhancement models require only clean speech for training without any label requirements. Experimental results show that the proposed VQScore and enhancement model are competitive with supervised baselines. The code will be released after publication.

Yu-Wen Chen, Kuo-Hsuan Hung, Shang-Yi Chuang et al.

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.

Kai-Chun Liu, Kuo-Hsuan Hung, Chia-Yeh Hsieh et al.

In the last two decades, fall detection (FD) systems have been developed as a popular assistive technology. Such systems automatically detect critical fall events and immediately alert medical professionals or caregivers. To support long-term FD services, various power-saving strategies have been implemented. Among them, a reduced sampling rate is a common approach for an energy-efficient system in the real-world. However, the performance of FD systems is diminished owing to low-resolution (LR) accelerometer signals. To improve the detection accuracy with LR accelerometer signals, several technical challenges must be considered, including misalignment, mismatch of effective features, and the degradation effects. In this work, a deep-learning-based accelerometer signal enhancement (ASE) model is proposed to improve the detection performance of LR-FD systems. This proposed model reconstructs high-resolution (HR) signals from the LR signals by learning the relationship between the LR and HR signals. The results show that the FD system using support vector machine and the proposed ASE model at an extremely low sampling rate (sampling rate < 2 Hz) achieved 97.34% and 90.52% accuracies in the SisFall and FallAllD datasets, respectively, while those without ASE models only achieved 95.92% and 87.47% accuracies in the SisFall and FallAllD datasets, respectively. This study demonstrates that the ASE model helps the FD systems tackle the technical challenges of LR signals and achieve better detection performance.

Yu-Wen Chen, Kuo-Hsuan Hung, You-Jin Li et al.

This study presents a deep learning-based speech signal-processing mobile application known as CITISEN. The CITISEN provides three functions: speech enhancement (SE), model adaptation (MA), and background noise conversion (BNC), allowing CITISEN to be used as a platform for utilizing and evaluating SE models and flexibly extend the models to address various noise environments and users. For SE, a pretrained SE model downloaded from the cloud server is used to effectively reduce noise components from instant or saved recordings provided by users. For encountering unseen noise or speaker environments, the MA function is applied to promote CITISEN. A few audio samples recording on a noisy environment are uploaded and used to adapt the pretrained SE model on the server. Finally, for BNC, CITISEN first removes the background noises through an SE model and then mixes the processed speech with new background noise. The novel BNC function can evaluate SE performance under specific conditions, cover people's tracks, and provide entertainment. The experimental results confirmed the effectiveness of SE, MA, and BNC functions. Compared with the noisy speech signals, the enhanced speech signals achieved about 6\% and 33\% of improvements, respectively, in terms of short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ). With MA, the STOI and PESQ could be further improved by approximately 6\% and 11\%, respectively. Finally, the BNC experiment results indicated that the speech signals converted from noisy and silent backgrounds have a close scene identification accuracy and similar embeddings in an acoustic scene classification model. Therefore, the proposed BNC can effectively convert the background noise of a speech signal and be a data augmentation method when clean speech signals are unavailable.

Szu-Wei Fu, Chien-Feng Liao, Tsun-An Hsieh et al.

The Transformer architecture has demonstrated a superior ability compared to recurrent neural networks in many different natural language processing applications. Therefore, our study applies a modified Transformer in a speech enhancement task. Specifically, positional encoding in the Transformer may not be necessary for speech enhancement, and hence, it is replaced by convolutional layers. To further improve the perceptual evaluation of the speech quality (PESQ) scores of enhanced speech, the L_1 pre-trained Transformer is fine-tuned using a MetricGAN framework. The proposed MetricGAN can be treated as a general post-processing module to further boost the objective scores of interest. The experiments were conducted using the data sets provided by the organizer of the Deep Noise Suppression (DNS) challenge. Experimental results demonstrated that the proposed system outperformed the challenge baseline, in both subjective and objective evaluations, with a large margin.

Cheng Yu, Kuo-Hsuan Hung, Syu-Siang Wang et al.

Previous studies have proven that integrating video signals, as a complementary modality, can facilitate improved performance for speech enhancement (SE). However, video clips usually contain large amounts of data and pose a high cost in terms of computational resources and thus may complicate the SE system. As an alternative source, a bone-conducted speech signal has a moderate data size while manifesting speech-phoneme structures, and thus complements its air-conducted counterpart. In this study, we propose a novel multi-modal SE structure in the time domain that leverages bone- and air-conducted signals. In addition, we examine two ensemble-learning-based strategies, early fusion (EF) and late fusion (LF), to integrate the two types of speech signals, and adopt a deep learning-based fully convolutional network to conduct the enhancement. The experiment results on the Mandarin corpus indicate that this newly presented multi-modal (integrating bone- and air-conducted signals) SE structure significantly outperforms the single-source SE counterparts (with a bone- or air-conducted signal only) in various speech evaluation metrics. In addition, the adoption of an LF strategy other than an EF in this novel SE multi-modal structure achieves better results.