Search

This paper addresses the prevalent issue of incorrect speech output in audio-visual speech enhancement (AVSE) systems, which is often caused by poor video quality and mismatched training and test data. We introduce a post-processing classifier (PPC) to rectify these erroneous outputs, ensuring that the enhanced speech corresponds accurately to the intended speaker. We also adopt a mixup strategy in PPC training to improve its robustness. Experimental results on the AVSE-challenge dataset show that integrating PPC into the AVSE model can significantly improve AVSE performance, and combining PPC with the AVSE model trained with permutation invariant training (PIT) yields the best performance. The proposed method substantially outperforms the baseline model by a large margin. This work highlights the potential for broader applications across various modalities and architectures, providing a promising direction for future research in this field., Comment: The 27th International Conference of the Oriental COCOSDA

While pre-trained automatic speech recognition (ASR) systems demonstrate impressive performance on matched domains, their performance often degrades when confronted with channel mismatch stemming from unseen recording environments and conditions. To mitigate this issue, we propose a novel channel-aware data simulation method for robust ASR training. Our method harnesses the synergistic power of channel-extractive techniques and generative adversarial networks (GANs). We first train a channel encoder capable of extracting embeddings from arbitrary audio. On top of this, channel embeddings are extracted using a minimal amount of target-domain data and used to guide a GAN-based speech synthesizer. This synthesizer generates speech that faithfully preserves the phonetic content of the input while mimicking the channel characteristics of the target domain. We evaluate our method on the challenging Hakka Across Taiwan (HAT) and Taiwanese Across Taiwan (TAT) corpora, achieving relative character error rate (CER) reductions of 20.02% and 9.64%, respectively, compared to the baselines. These results highlight the efficacy of our channel-aware data simulation method for bridging the gap between source- and target-domain acoustics., Comment: Submitted to ICASSP 2025

In multichannel speech enhancement, effectively capturing spatial and spectral information across different microphones is crucial for noise reduction. Traditional methods, such as CNN or LSTM, attempt to model the temporal dynamics of full-band and sub-band spectral and spatial features. However, these approaches face limitations in fully modeling complex temporal dependencies, especially in dynamic acoustic environments. To overcome these challenges, we modify the current advanced model McNet by introducing an improved version of Mamba, a state-space model, and further propose MCMamba. MCMamba has been completely reengineered to integrate full-band and narrow-band spatial information with sub-band and full-band spectral features, providing a more comprehensive approach to modeling spatial and spectral information. Our experimental results demonstrate that MCMamba significantly improves the modeling of spatial and spectral features in multichannel speech enhancement, outperforming McNet and achieving state-of-the-art performance on the CHiME-3 dataset. Additionally, we find that Mamba performs exceptionally well in modeling spectral information.

This work investigates two strategies for zero-shot non-intrusive speech assessment leveraging large language models. First, we explore the audio analysis capabilities of GPT-4o. Second, we propose GPT-Whisper, which uses Whisper as an audio-to-text module and evaluates the naturalness of text via targeted prompt engineering. We evaluate assessment metrics predicted by GPT-4o and GPT-Whisper examining their correlations with human-based quality and intelligibility assessments, and character error rate (CER) of automatic speech recognition. Experimental results show that GPT-4o alone is not effective for audio analysis; whereas, GPT-Whisper demonstrates higher prediction, showing moderate correlation with speech quality and intelligibility, and high correlation with CER. Compared to supervised non-intrusive neural speech assessment models, namely MOS-SSL and MTI-Net, GPT-Whisper yields a notably higher Spearman's rank correlation with the CER of Whisper. These findings validate GPT-Whisper as a reliable method for accurate zero-shot speech assessment without requiring additional training data (speech data and corresponding assessment scores).

This study investigates the efficacy of data augmentation techniques for low-resource automatic speech recognition (ASR), focusing on two endangered Austronesian languages, Amis and Seediq. Recognizing the potential of self-supervised learning (SSL) in low-resource settings, we explore the impact of data volume on the continued pre-training of SSL models. We propose a novel data-selection scheme leveraging a multilingual corpus to augment the limited target language data. This scheme utilizes a language classifier to extract utterance embeddings and employs one-class classifiers to identify utterances phonetically and phonologically proximate to the target languages. Utterances are ranked and selected based on their decision scores, ensuring the inclusion of highly relevant data in the SSL-ASR pipeline. Our experimental results demonstrate the effectiveness of this approach, yielding substantial improvements in ASR performance for both Amis and Seediq. These findings underscore the feasibility and promise of data augmentation through cross-lingual transfer learning for low-resource language ASR.

We present the third edition of the VoiceMOS Challenge, a scientific initiative designed to advance research into automatic prediction of human speech ratings. There were three tracks. The first track was on predicting the quality of ``zoomed-in'' high-quality samples from speech synthesis systems. The second track was to predict ratings of samples from singing voice synthesis and voice conversion with a large variety of systems, listeners, and languages. The third track was semi-supervised quality prediction for noisy, clean, and enhanced speech, where a very small amount of labeled training data was provided. Among the eight teams from both academia and industry, we found that many were able to outperform the baseline systems. Successful techniques included retrieval-based methods and the use of non-self-supervised representations like spectrograms and pitch histograms. These results showed that the challenge has advanced the field of subjective speech rating prediction., Comment: Accepted to SLT2024

Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch between training and test conditions. This study puts forward a novel data simulation method to address this issue, leveraging noise-extractive techniques and generative adversarial networks (GANs) with only limited target noisy speech data. Notably, our method employs a noise encoder to extract noise embeddings from target-domain data. These embeddings aptly guide the generator to synthesize utterances acoustically fitted to the target domain while authentically preserving the phonetic content of the input clean speech. Furthermore, we introduce the notion of dynamic stochastic perturbation, which can inject controlled perturbations into the noise embeddings during inference, thereby enabling the model to generalize well to unseen noise conditions. Experiments on the VoiceBank-DEMAND benchmark dataset demonstrate that our domain-adaptive SE method outperforms an existing strong baseline based on data simulation., Comment: Accepted to IEEE SLT 2024

Representations from pre-trained speech foundation models (SFMs) have shown impressive performance in many downstream tasks. However, the potential benefits of incorporating pre-trained SFM representations into speaker voice similarity assessment have not been thoroughly investigated. In this paper, we propose SVSNet+, a model that integrates pre-trained SFM representations to improve performance in assessing speaker voice similarity. Experimental results on the Voice Conversion Challenge 2018 and 2020 datasets show that SVSNet+ incorporating WavLM representations shows significant improvements compared to baseline models. In addition, while fine-tuning WavLM with a small dataset of the downstream task does not improve performance, using the same dataset to learn a weighted-sum representation of WavLM can substantially improve performance. Furthermore, when WavLM is replaced by other SFMs, SVSNet+ still outperforms the baseline models and exhibits strong generalization ability., Comment: Accepted to INTERSPEECH 2024

The emergence of contemporary deepfakes has attracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content. Currently, machine learning techniques have been extensively studied for automatically detecting deepfakes. However, human perception has been less explored. Malicious deepfakes could ultimately cause public and social problems. Can we humans correctly perceive the authenticity of the content of the videos we watch? The answer is obviously uncertain; therefore, this paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-ofthe-art audiovisual deepfake detection models. To this end, we used gamification concepts to provide 110 participants (55 native English speakers and 55 non-native English speakers) with a webbased platform where they could access a series of 40 videos (20 real and 20 fake) to determine their authenticity. Each participant performed the experiment twice with the same 40 videos in different random orders. The videos are manually selected from the FakeAVCeleb dataset. We found that all AI models performed better than humans when evaluated on the same 40 videos. The study also reveals that while deception is not impossible, humans tend to overestimate their detection capabilities. Our experimental results may help benchmark human versus machine performance, advance forensics analysis, and enable adaptive countermeasures.

The recently proposed visually grounded speech model SpeechCLIP is an innovative framework that bridges speech and text through images via CLIP without relying on text transcription. On this basis, this paper introduces two extensions to SpeechCLIP. First, we apply the Continuous Integrate-and-Fire (CIF) module to replace a fixed number of CLS tokens in the cascaded architecture. Second, we propose a new hybrid architecture that merges the cascaded and parallel architectures of SpeechCLIP into a multi-task learning framework. Our experimental evaluation is performed on the Flickr8k and SpokenCOCO datasets. The results show that in the speech keyword extraction task, the CIF-based cascaded SpeechCLIP model outperforms the previous cascaded SpeechCLIP model using a fixed number of CLS tokens. Furthermore, through our hybrid architecture, cascaded task learning boosts the performance of the parallel branch in image-speech retrieval tasks., Comment: Accepted to ICASSP 2024, Self-supervision in Audio, Speech, and Beyond (SASB) workshop

This paper introduces HAAQI-Net, a non-intrusive deep learning model for music audio quality assessment tailored for hearing aid users. Unlike traditional methods like the Hearing Aid Audio Quality Index (HAAQI), which rely on intrusive comparisons to a reference signal, HAAQI-Net offers a more accessible and efficient alternative. Using a bidirectional Long Short-Term Memory (BLSTM) architecture with attention mechanisms and features from the pre-trained BEATs model, HAAQI-Net predicts HAAQI scores directly from music audio clips and hearing loss patterns. Results show HAAQI-Net's effectiveness, with predicted scores achieving a Linear Correlation Coefficient (LCC) of 0.9368, a Spearman's Rank Correlation Coefficient (SRCC) of 0.9486, and a Mean Squared Error (MSE) of 0.0064, reducing inference time from 62.52 seconds to 2.54 seconds. Although effective, feature extraction via the large BEATs model incurs computational overhead. To address this, a knowledge distillation strategy creates a student distillBEATs model, distilling information from the teacher BEATs model during HAAQI-Net training, reducing required parameters. The distilled HAAQI-Net maintains strong performance with an LCC of 0.9071, an SRCC of 0.9307, and an MSE of 0.0091, while reducing parameters by 75.85% and inference time by 96.46%. This reduction enhances HAAQI-Net's efficiency and scalability, making it viable for real-world music audio quality assessment in hearing aid settings. This work also opens avenues for further research into optimizing deep learning models for specific applications, contributing to audio signal processing and quality assessment by providing insights into developing efficient and accurate models for practical applications in hearing aid technology.