Related papers: Rethinking Speech Representation Aggregation in Sp…

Self-supervised learning (SSL) speech representations learned from large amounts of diverse, mixed-quality speech data without transcriptions are gaining ground in many speech technology applications. Prior work has shown that SSL is an…

In challenging environments with significant noise and reverberation, traditional speech enhancement (SE) methods often lead to over-suppressed speech, creating artifacts during listening and harming downstream tasks performance. To…

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

This paper investigates the performance of various speech SSL models on dialectal Arabic (DA) and Arabic-English code-switched (CS) speech. To address data scarcity, a modified audio-splicing approach is introduced to generate artificial CS…

Self-supervised learning (SSL) has advanced speech processing but suffers from quadratic complexity due to self-attention. To address this, SummaryMixing (SM) has been proposed as a linear-time alternative that summarizes entire utterances…

Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…

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…

Self-supervised learning (SSL) is now a serious competitor for supervised learning, even though it does not require data annotation. Several baselines have attempted to make SSL models exploit information about data distribution, and less…

Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a gate to filter out such spoofing attacks. This study…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie,…

Self-supervised learning (SSL) models offer powerful representations for sound event detection (SED), yet their synergistic potential remains underexplored. This study systematically evaluates state-of-the-art SSL models to guide optimal…

Semi-supervised learning (SSL) has recently proven to be an effective paradigm for leveraging a huge amount of unlabeled data while mitigating the reliance on large labeled data. Conventional methods focused on extracting a pseudo label…

Pre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks. However, their potential in target speech extraction (TSE) has not been fully exploited. TSE aims to extract the speech of a target…

Self-supervised learning (SSL) has recently shown remarkable results in closing the gap between supervised and unsupervised learning. The idea is to learn robust features that are invariant to distortions of the input data. Despite its…

Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments. SE focuses on improving the auditory quality of speech, but the enhanced feature distribution is…

Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual…

In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference…

Self-Supervised Learning (SSL) models have demonstrated exceptional performance in various speech tasks, particularly in low-resource and multilingual domains. Recent works show that fusing diverse SSL models could achieve superior…

Automatic syllable stress detection is a crucial component in Computer-Assisted Language Learning (CALL) systems for language learners. Current stress detection models are typically trained on clean speech, which may not be robust in…

Self-training (ST) and self-supervised learning (SSL) methods have demonstrated strong improvements in automatic speech recognition (ASR). In spite of these advances, to the best of our knowledge, there is no analysis of how the composition…