In this paper, we introduce self-distillation and online clustering for self-supervised speech
representation learning (DinoSR) which combines masked language modeling, self …

Lately, propelled by the phenomenal advances around the transformer architecture, the
legal NLP field has enjoyed spectacular growth. To measure progress, well curated and …

Many self-supervised speech models (S3Ms) have been introduced over the last few years,
improving performance and data efficiency on various speech tasks. However, these …

Many self-supervised speech models (S3Ms) have been introduced over the last few years,
producing performance and data efficiency improvements for a variety of speech tasks …

In recent years, speech generation has seen remarkable progress, now achieving one-shot
generation capability that is often virtually indistinguishable from real human voice …

This paper introduces Robust Spin (R-Spin), a data-efficient self-supervised fine-tuning
framework for speaker and noise-invariant speech representations by learning discrete …

The emergence of the'code naturalness' concept, which suggests that software code shares
statistical properties with natural language, paves the way for deep neural networks (DNNs) …

Access to speech datasets is essential for the effective use of modern ASR systems in low-
resource languages like Polish. However, the lack of centralized information and metadata …

Despite success across various tasks, self-supervised speech models face significant
challenges in enhancing content-related performance with unlabeled data, requiring …

摘要英語逐漸作為許多國家的第二語言 (English as a Second Language, ESL),
同時也帶動電腦輔助語言學習的發展, 近年來又以發展自動口語評測較為熱門. 然而 …