The VoiceMOS Challenge 2024: Beyond Speech Quality Prediction

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.

Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation

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.

SVSNet+: Enhancing Speaker Voice Similarity Assessment Models with Representations from Speech Foundation Models

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.

Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes

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.

SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data

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.

HAAQI-Net: A non-intrusive neural music quality assessment model for hearing aids

This paper introduces HAAQI-Net, a non-intrusive deep learning model for music quality assessment tailored to hearing aid users. In contrast to traditional methods like the Hearing Aid Audio Quality Index (HAAQI), HAAQI-Net utilizes a Bidirectional Long Short-Term Memory (BLSTM) with attention. It takes an assessed music sample and a hearing loss pattern as input, generating a predicted HAAQI score. The model employs the pre-trained Bidirectional Encoder representation from Audio Transformers (BEATs) for acoustic feature extraction. Comparing predicted scores with ground truth, HAAQI-Net achieves a Longitudinal Concordance Correlation (LCC) of 0.9257, Spearman's Rank Correlation Coefficient (SRCC) of 0.9394, and Mean Squared Error (MSE) of 0.0080. Notably, this high performance comes with a substantial reduction in inference time: from 62.52 seconds (by HAAQI) to 2.71 seconds (by HAAQI-Net), serving as an efficient music quality assessment model for hearing aid users.

LC4SV: A Denoising Framework Learning to Compensate for Unseen Speaker Verification Models

The performance of speaker verification (SV) models may drop dramatically in noisy environments. A speech enhancement (SE) module can be used as a front-end strategy. However, existing SE methods may fail to bring performance improvements to downstream SV systems due to artifacts in the predicted signals of SE models. To compensate for artifacts, we propose a generic denoising framework named LC4SV, which can serve as a pre-processor for various unknown downstream SV models. In LC4SV, we employ a learning-based interpolation agent to automatically generate the appropriate coefficients between the enhanced signal and its noisy input to improve SV performance in noisy environments. Our experimental results demonstrate that LC4SV consistently improves the performance of various unseen SV systems. To the best of our knowledge, this work is the first attempt to develop a learning-based interpolation scheme aiming at improving SV performance in noisy environments.

D4AM: A General Denoising Framework for Downstream Acoustic Models

The performance of acoustic models degrades notably in noisy environments. Speech enhancement (SE) can be used as a front-end strategy to aid automatic speech recognition (ASR) systems. However, existing training objectives of SE methods are not fully effective at integrating speech-text and noisy-clean paired data for training toward unseen ASR systems. In this study, we propose a general denoising framework, D4AM, for various downstream acoustic models. Our framework fine-tunes the SE model with the backward gradient according to a specific acoustic model and the corresponding classification objective. In addition, our method aims to consider the regression objective as an auxiliary loss to make the SE model generalize to other unseen acoustic models. To jointly train an SE unit with regression and classification objectives, D4AM uses an adjustment scheme to directly estimate suitable weighting coefficients rather than undergoing a grid search process with additional training costs. The adjustment scheme consists of two parts: gradient calibration and regression objective weighting. The experimental results show that D4AM can consistently and effectively provide improvements to various unseen acoustic models and outperforms other combination setups. Specifically, when evaluated on the Google ASR API with real noisy data completely unseen during SE training, D4AM achieves a relative WER reduction of 24.65% compared with the direct feeding of noisy input. To our knowledge, this is the first work that deploys an effective combination scheme of regression (denoising) and classification (ASR) objectives to derive a general pre-processor applicable to various unseen ASR systems. Our code is available at https://github.com/ChangLee0903/D4AM.

Multi-objective Non-intrusive Hearing-aid Speech Assessment Model

Without the need for a clean reference, non-intrusive speech assessment methods have caught great attention for objective evaluations. While deep learning models have been used to develop non-intrusive speech assessment methods with promising results, there is limited research on hearing-impaired subjects. This study proposes a multi-objective non-intrusive hearing-aid speech assessment model, called HASA-Net Large, which predicts speech quality and intelligibility scores based on input speech signals and specified hearing-loss patterns. Our experiments showed the utilization of pre-trained SSL models leads to a significant boost in speech quality and intelligibility predictions compared to using spectrograms as input. Additionally, we examined three distinct fine-tuning approaches that resulted in further performance improvements. Furthermore, we demonstrated that incorporating SSL models resulted in greater transferability to OOD dataset. Finally, this study introduces HASA-Net Large, which is a non-invasive approach for evaluating speech quality and intelligibility. HASA-Net Large utilizes raw waveforms and hearing-loss patterns to accurately predict speech quality and intelligibility levels for individuals with normal and impaired hearing and demonstrates superior prediction performance and transferability.

AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection

Multimodal manipulations (also known as audio-visual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets.