Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

Self-supervised learning (SSL) has proven vital for advancing research in natural language
processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on …

The sound codec's dual roles in minimizing data transmission latency and serving as
tokenizers underscore its critical importance. Recent years have witnessed significant …

In modern multilingual societies, there is a demand for multilingual Automatic Speech
Recognition (ASR) and Spoken Term Detection (STD). Multilingual Spoken Term Detection …

Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-
machine interactions by seamlessly integrating various forms of data. Developing a …

Neural audio codec models are becoming increasingly important as they serve as
tokenizers for audio, enabling efficient transmission or facilitating speech language …

There is a growing interest in cost-effective self-supervised fine-tuning (SSFT) of self-
supervised learning (SSL)-based speech models to obtain task-specific representations …

Anomia (word-finding difficulties) is the hallmark of aphasia, an acquired language disorder
most commonly caused by stroke. Assessment of speech performance using picture naming …

In this paper, we describe the “Query by Example Search on Speech Task”(QUESST), held
as part of the MediaEval 2015 evaluation campaign. As in previous years, the proposed task …

The foundation model paradigm leverages a shared foundation model to achieve state-of-
the-art (SOTA) performance for various tasks, requiring minimal downstream-specific data …