ASR

Automatic speaker recognition with variation across vocal conditions: a controlled experiment with implications for forensics

Proceedings of Interspeech 2023. Dublin, Ireland.

Impact of the changes in long-term acoustic features upon different-speaker ASR scores

Presentation at the 31st International Association for Forensic Phonetics and Acoustics conference (IAFPA 2023), Universität Zürich, Switzerland.

Utilising ASR in Linguistic Research (ongoing)

This tutorial is designed to help you understand the basic concepts in ASR and guide you step-by-step to utilise ASR in your own linguistic research.      4 Chapters Unix Shell  Python  Whisper  Kaldi  ASR  Corpus  Applying large pre-trained models (Whisper & Wav2Vec2)  ASR from Scratch I: Training models of Hong Kong Cantonese using the Kaldi recipe  ASR from Scratch II: Training models of Hong Kong Cantonese with MFA implementation  ASR from Scratch III: Training models of Bora, a Low-resource Language (MFA)

Training your first ASR model: Introduction to ASR in linguistic research

Introduction to Automatic Speech Recognition (ASR) in linguistic research.

Person-specific Automatic Speaker Recognition

The ESRC-funded project "Person-specific automatic speaker recognition : understanding the behaviour of individuals for applications of ASR" is a three year project running from 2022 to 2025 led by Dr Vincent Hughes (PI), Professor Paul Foulkes (CI) and Dr Philip Harrison in the Department of Language and Linguistic Science at the University of York. The project involves collaboration with the Netherlands Forensic Institute and Oxford Wave Research.