Related papers: SA-SSL-MOS: Self-supervised Learning MOS Predictio…

The sequential recommendation aims at predicting the next items in user behaviors, which can be solved by characterizing item relationships in sequences. Due to the data sparsity and noise issues in sequences, a new self-supervised learning…

Self-supervised representation learning (SSL) has attained SOTA results on several downstream speech tasks, but SSL-based speech enhancement (SE) solutions still lag behind. To address this issue, we exploit three main ideas: (i)…

Self-Supervised Learning (SSL) has led to considerable progress in Speaker Verification (SV). The standard framework uses same-utterance positive sampling and data-augmentation to generate anchor-positive pairs of the same speaker. This is…

Self-supervised learning (SSL) has emerged as a promising paradigm in medical imaging, addressing the chronic challenge of limited labeled data in healthcare settings. While SSL has shown impressive results, existing studies in the medical…

To understand why self-supervised learning (SSL) models have empirically achieved strong performances on several speech-processing downstream tasks, numerous studies have focused on analyzing the encoded information of the SSL layer…

This study proposes a multi-task pseudo-label learning (MPL)-based non-intrusive speech quality assessment model called MTQ-Net. MPL consists of two stages: obtaining pseudo-label scores from a pretrained model and performing multi-task…

Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the world's 7000+ languages. We propose XEUS, a Cross-lingual…

Automatic speech quality assessment aims to quantify subjective human perception of speech through computational models to reduce the need for labor-consuming manual evaluations. While models based on deep learning have achieved progress in…

The ground truth used for training image, video, or speech quality prediction models is based on the Mean Opinion Scores (MOS) obtained from subjective experiments. Usually, it is necessary to conduct multiple experiments, mostly with…

Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this paper, we explore the…

Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high…

Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech…

Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppress the noises in…

Mean Opinion Score (MOS) is a popular measure for evaluating synthesized speech. However, the scores obtained in MOS tests are heavily dependent upon many contextual factors. One such factor is the overall range of quality of the samples…

Semi-supervised learning (SSL) has shown notable potential in relieving the heavy demand of dense prediction tasks on large-scale well-annotated datasets, especially for the challenging multi-organ segmentation (MoS). However, the…

Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing drastically benefitted from SSL as most of the current…

Recent advances in synthetic speech have made audio deepfakes increasingly realistic, posing significant security risks. Existing detection methods that rely on a single modality, either raw waveform embeddings or spectral based features,…

Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large models, we employ light-weight networks to comply with tight…

The information loss or distortion caused by single-channel speech enhancement (SE) harms the performance of automatic speech recognition (ASR). Observation addition (OA) is an effective post-processing method to improve ASR performance by…

The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and…