ASR

Utilising ASR in Linguistic Research

A step-by-step guide to apply automatic speech recognition technology in linguistic research.

Speech Synthesis and Recognition

HG4052 introduces the linguistic, acoustic, and computational foundations of speech recognition and synthesis for linguistics students, from the speech chain and DTW/HMMs to CTC, Whisper, and neural TTS, with hands-on Praat and Colab practicals and a focus on Singapore's multilingual speech environment.

Performance of Montreal Forced Aligner on Cantonese Spontaneous Speech

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

Working with large-scale speech corpus for phonetic research: Pipeline and tools

Introduction to pipeline and tools for phonetic research using large-scale speech corpora.

Performance of Montreal Forced Aligner on Cantonese Spontaneous Speech

Poster Presentation at INTERSPEECH 2025, Rotterdam, The Netherlands.

The processing of neutral tone in self-supervised learning speech models

Poster Presentation at UK and Ireland Speech 2025, York, UK.

Voice quality in telephone speech: Comparing acoustic measures between VoIP telephone and high-quality recordings

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.

Exploring individual speaker performance within a forensic automatic speaker recognition system

Poster Presentation at the UK and Ireland Speech Workshop 2024, Cambridge, UK.

Voice quality in telephone speech: Comparing acoustic measures between VoIP telephone and high-quality recordings

Poster Presentation at INTERSPEECH 2024, Kos Island, Greece.

Exploring individual speaker characteristics within a forensic automatic speaker recognition system

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.