Deep learning has emerged as a powerful tool in various domains, revolutionising machine
learning research. However, one persistent challenge is the scarcity of labelled training …

Although audio generation shares commonalities across different types of audio, such as
speech, music, and sound effects, designing models for each type requires careful …

Audio-visual target speech extraction (AV-TSE) is one of the enabling technologies in
robotics and many audio-visual applications. One of the challenges of AV-TSE is how to …

Automatic proficiency assessment can be a useful tool in language learning, for self-
evaluation of language skills and to enable educators to tailor instruction effectively. Often …

Since the first speech recognition systems were built more than 30 years ago, improvement
in voice technology has enabled applications such as smart assistants and automated …

Employing a monaural speech separation (SS) model as a front-end for automatic speech
recognition (ASR) involves balancing two kinds of trade-offs. First, while a larger model …

The Streaming Unmixing and Recognition Transducer (SURT) model was proposed recently
as an end-to-end approach for continuous, streaming, multi-talker speech recognition (ASR) …

In real-world scenarios, speech signals are often contaminated with environmental noises,
and reverberation, which degrades speech quality and intelligibility. Lately, the development …

Accent recognition (AR) is challenging due to the lack of training data as well as the accents
are entangled with speakers and regional characteristics. This paper aims to improve AR …