In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer that operates on latent features. SoloAudio supports both audio-oriented and language-oriented TSE by utilizing a CLAP model as the feature extractor for target sounds. Furthermore, SoloAudio leverages synthetic audio generated by state-of-the-art text-to-audio models for training, demonstrating strong generalization to out-of-domain data and unseen sound events. We evaluate this approach on the FSD Kaggle 2018 mixture dataset and real data from AudioSet, where SoloAudio achieves the state-of-the-art results on both in-domain and out-of-domain data, and exhibits impressive zero-shot and few-shot capabilities. Source code1and demos2are released.

In this paper, we introduce SSR-Speech, a neural codec autoregressive model designed for stable, safe, and robust zero-shot text-based speech editing and text-to-speech synthesis. SSR-Speech is built on a Transformer decoder and incorporates classifier-free guidance to enhance the stability of the generation process. A watermark Encodec is proposed to embed frame-level watermarks into the edited regions of the speech so that which parts were edited can be detected. In addition, the waveform reconstruction leverages the original unedited speech segments, providing superior recovery compared to the Encodec model. Our approach achieves state-of-the-art performance in the RealEdit speech editing task and the LibriTTS text-to-speech task, surpassing previous methods. Furthermore, SSR-Speech excels in multi-span speech editing and also demonstrates remarkable robustness to background sounds. The source code1and demos2are released.

Common target sound extraction (TSE) approaches primarily relied on discriminative approaches in order to separate the target sound while minimizing interference from the unwanted sources, with varying success in separating the target from the background. This study introduces DPM-TSE, a generative method based on diffusion probabilistic modeling (DPM) for Target Sound Extraction (TSE), to achieve both cleaner target renderings as well as improved separability from unwanted sounds. The technique also tackles the noise floor of DPM by introducing a correction method for noise schedules and sample steps. This approach is evaluated using both objective and subjective quality metrics on the FSD Kaggle 2018 dataset. The results show that DPM-TSE has a significant improvement in perceived quality in terms of target extraction and purity.

Auditory Attention Decoding (AAD) algorithms play a crucial role in isolating desired sound sources within challenging acoustic environments directly from brain activity. Although recent research has shown promise in AAD using shallow representations such as auditory envelope and spectrogram, there has been limited exploration of deep Self-Supervised (SS) representations on a larger scale. In this study, we undertake a comprehensive investigation into the performance of linear decoders across 12 deep and 2 shallow representations, applied to EEG data from multiple studies spanning 57 subjects and multiple languages. Our experimental results consistently reveal the superiority of deep features for AAD at decoding background speakers, regardless of the datasets and analysis windows. This result indicates possible nonlinear encoding of unattended signals in the brain that are revealed using deep nonlinear features. Additionally, we analyze the impact of different layers of SS representations and window sizes on AAD performance. These findings underscore the potential for enhancing EEG-based AAD systems through the integration of deep feature representations.

Sentiment analysis has traditionally leveraged information from text data. More recently, it has become increasingly clear that multimodal data provides a rich space to drastically boost interpretation of human sentiments by harnessing information across multiple modalities. In this study, we incorporate pre-trained feature extractors and propose a multitask training strategy to improve modality representations for Multimodal Sentiment Analysis (MSA). The experimental results on the CH-SIMS v2 dataset demonstrate the superior performance of the proposed system compared to existing state-of-the-art methods, validating the effectiveness of our proposed approach. Furthermore, our framework reduces reliance on textual data, achieving competitive outcomes even when utilizing only auditory and visual modalities.

Music tagging is the task of predicting multiple tags of a music excerpt, and plays an important role in modern music recommendation systems. To obtain superior performance, recent approaches of music tagging focus on developing sophisticated models or exploiting additional multi-modal information. However, none of them deal with the problem of label noise during the training process despite of its ubiquitous presence. In this paper, we propose a progressive two-stage teacher-student training framework to prevent the music tagging model from overfitting label noise. Experimental results suggest that the proposed method surpasses conventional label-noise-robust methods and exhibits scalability across different tagging models. Moreover, detailed analyses demonstrate that the two teachers in the framework gradually improve student model’s generalization performance and effectively avoid the impairment from label noise.