Audio-visual representation learning aims to develop systems with human-like perception by utilizing correlation between auditory and visual information. However, current models often focus on a limited set of tasks, and generalization abilities of learned representations are unclear. To this end, we propose the AV-SUPERB benchmark that enables general-purpose evaluation of unimodal audio/visual and bimodal fusion representations on 7 datasets covering 5 audio-visual tasks in speech and audio processing. We evaluate 5 recent self-supervised models and show that none of these models generalize to all tasks, emphasizing the need for future study on improving universal model performance. In addition, we show that representations may be improved with intermediate-task fine-tuning and audio event classification with AudioSet serves as a strong intermediate task. We release our benchmark with evaluation code and a model submission platform to encourage further research in audio-visual learning.
Automated assessment of speech intelligibility in hearing aid (HA) devices is of great importance. Our previous work introduced a non-intrusive multi-branched speech intelligibility prediction model called MBI-Net, which achieved top performance in the Clarity Prediction Challenge 2022. Based on the promising results of the MBI-Net model, we aim to further enhance its performance by leveraging Whisper embeddings to enrich acoustic features. In this study, we propose two improved models, namely MBI-Net+ and MBI-Net++. MBI-Net+ maintains the same model architecture as MBI-Net, but replaces self-supervised learning (SSL) speech embeddings with Whisper embeddings to deploy cross-domain features. On the other hand, MBI-Net++ further employs a more elaborate design, incorporating an auxiliary task to predict frame-level and utterance-level scores of the objective speech intelligibility metric HASPI (Hearing Aid Speech Perception Index) and multi-task learning. Experimental results confirm that both MBI-Net++ and MBI-Net+ achieve better prediction performance than MBI-Net in terms of multiple metrics, and MBI-Net++ is better than MBI-Net+.
Speech emotion recognition (SER) often experiences reduced performance due to background noise. In addition, making a prediction on signals with only background noise could undermine user trust in the system. In this study, we propose a Noise Robust Speech Emotion Recognition system, NRSER. NRSER employs speech enhancement (SE) to effectively reduce the noise in input signals. Then, the signal-to-noise-ratio (SNR)-level detection structure and waveform reconstitution strategy are introduced to reduce the negative impact of SE on speech signals with no or little background noise. Our experimental results show that NRSER can effectively improve the noise robustness of the SER system, including preventing the system from making emotion recognition on signals consisting solely of background noise. Moreover, the proposed SNR-level detection structure can be used individually for tasks such as data selection.
This study introduces multi-task pseudo-label (MPL) learning for a non-intrusive speech quality assessment model. MPL consists of two stages which are obtaining pseudo-label scores from a pretrained model and performing multi-task learning. The 3QUEST metrics, namely Speech-MOS (S-MOS), Noise-MOS (N-MOS), and General-MOS (G-MOS) are selected as the primary ground-truth labels. Additionally, the pretrained MOSA-Net model is utilized to estimate three pseudo-labels: perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and speech distortion index (SDI). Multi-task learning stage of MPL is then employed to train the MTQ-Net model (multi-target speech quality assessment network). The model is optimized by incorporating Loss supervision (derived from the difference between the estimated score and the real ground-truth labels) and Loss semi-supervision (derived from the difference between the estimated score and pseudo-labels), where Huber loss is employed to calculate the loss function. Experimental results first demonstrate the advantages of MPL compared to training the model from scratch and using knowledge transfer mechanisms. Secondly, the benefits of Huber Loss in improving the prediction model of MTQ-Net are verified. Finally, the MTQ-Net with the MPL approach exhibits higher overall prediction capabilities when compared to other SSL-based speech assessment models.
Individuals with hearing impairments face challenges in their ability to comprehend speech, particularly in noisy environments. The aim of this study is to explore the effectiveness of audio-visual speech enhancement (AVSE) in enhancing the intelligibility of vocoded speech in cochlear implant (CI) simulations. Notably, the study focuses on a challenged scenario where there is limited availability of training data for the AVSE task. To address this problem, we propose a novel deep neural network framework termed Self-Supervised Learning-based AVSE (SSL-AVSE). The proposed SSL-AVSE combines visual cues, such as lip and mouth movements, from the target speakers with corresponding audio signals. The contextually combined audio and visual data are then fed into a Transformer-based SSL AV-HuBERT model to extract features, which are further processed using a BLSTM-based SE model. The results demonstrate several key findings. Firstly, SSL-AVSE successfully overcomes the issue of limited data by leveraging the AV-HuBERT model. Secondly, by fine-tuning the AV-HuBERT model parameters for the target SE task, significant performance improvements are achieved. Specifically, there is a notable enhancement in PESQ (Perceptual Evaluation of Speech Quality) from 1.43 to 1.67 and in STOI (Short-Time Objective Intelligibility) from 0.70 to 0.74. Furthermore, the performance of the SSL-AVSE was evaluated using CI vocoded speech to assess the intelligibility for CI users. Comparative experimental outcomes reveal that in the presence of dynamic noises encountered during human conversations, SSL-AVSE exhibits a substantial improvement. The NCM (Normal Correlation Matrix) values indicate an increase of 26.5% to 87.2% compared to the noisy baseline.
Subjective tests are the gold standard for evaluating speech quality and intelligibility, but they are time-consuming and expensive. Thus, objective measures that align with human perceptions are crucial. This study evaluates the correlation between commonly used objective measures and subjective speech quality and intelligibility using a Chinese speech dataset. Moreover, new objective measures are proposed combining current objective measures using deep learning techniques to predict subjective quality and intelligibility. The proposed deep learning model reduces the amount of training data without significantly impacting prediction performance. We interpret the deep learning model to understand how objective measures reflect subjective quality and intelligibility. We also explore the impact of including subjective speech quality ratings on speech intelligibility prediction. Our findings offer valuable insights into the relationship between objective measures and human perceptions.
Beamforming techniques are popular in speech-related applications due to their effective spatial filtering capabilities. Nonetheless, conventional beamforming techniques generally depend heavily on either the target's direction-of-arrival (DOA), relative transfer function (RTF) or covariance matrix. This paper presents a new approach, the intelligibility-aware null-steering (IANS) beamforming framework, which uses the STOI-Net intelligibility prediction model to improve speech intelligibility without prior knowledge of the speech signal parameters mentioned earlier. The IANS framework combines a null-steering beamformer (NSBF) to generate a set of beamformed outputs, and STOI-Net, to determine the optimal result. Experimental results indicate that IANS can produce intelligibility-enhanced signals using a small dual-microphone array. The results are comparable to those obtained by null-steering beamformers with given knowledge of DOAs.
Clinical guidelines underscore the importance of regularly monitoring and surveilling arteriovenous fistula (AVF) access in hemodialysis patients to promptly detect any dysfunction. Although phono-angiography/sound analysis overcomes the limitations of standardized AVF stenosis diagnosis tool, prior studies have depended on conventional feature extraction methods, restricting their applicability in diverse contexts. In contrast, representation learning captures fundamental underlying factors that can be readily transferred across different contexts. We propose an approach based on deep denoising autoencoders (DAEs) that perform dimensionality reduction and reconstruction tasks using the waveform obtained through one-level discrete wavelet transform, utilizing representation learning. Our results demonstrate that the latent representation generated by the DAE surpasses expectations with an accuracy of 0.93. The incorporation of noise-mixing and the utilization of a noise-to-clean scheme effectively enhance the discriminative capabilities of the latent representation. Moreover, when employed to identify patient-specific characteristics, the latent representation exhibited performance by surpassing an accuracy of 0.92. Appropriate light-weighted methods can restore the detection performance of the excessively reduced dimensionality version and enable operation on less computational devices. Our findings suggest that representation learning is a more feasible approach for extracting auscultation features in AVF, leading to improved generalization and applicability across multiple tasks. The manipulation of latent representations holds immense potential for future advancements. Further investigations in this area are promising and warrant continued exploration.
Patients who have had their entire larynx removed, including the vocal folds, owing to throat cancer may experience difficulties in speaking. In such cases, electrolarynx devices are often prescribed to produce speech, which is commonly referred to as electrolaryngeal speech (EL speech). However, the quality and intelligibility of EL speech are poor. To address this problem, EL voice conversion (ELVC) is a method used to improve the intelligibility and quality of EL speech. In this paper, we propose a novel ELVC system that incorporates cross-domain features, specifically spectral features and self-supervised learning (SSL) embeddings. The experimental results show that applying cross-domain features can notably improve the conversion performance for the ELVC task compared with utilizing only traditional spectral features.
Electrolarynx is a commonly used assistive device to help patients with removed vocal cords regain their ability to speak. Although the electrolarynx can generate excitation signals like the vocal cords, the naturalness and intelligibility of electrolaryngeal (EL) speech are very different from those of natural (NL) speech. Many deep-learning-based models have been applied to electrolaryngeal speech voice conversion (ELVC) for converting EL speech to NL speech. In this study, we propose a multimodal voice conversion (VC) model that integrates acoustic and visual information into a unified network. We compared different pre-trained models as visual feature extractors and evaluated the effectiveness of these features in the ELVC task. The experimental results demonstrate that the proposed multimodal VC model outperforms single-modal models in both objective and subjective metrics, suggesting that the integration of visual information can significantly improve the quality of ELVC.