tutorial

Audio Processing (ongoing)

This series takes you on a journey through the fundamental concepts and practical aspects of audio processing.   1 Chapter Unix Shell  Python  Corpus  Audio data augmentation (in progress)

Research Hacks (ongoing)

This series features a carefully curated set of research tips, tools, and techniques, empowering you to cut through information clutter effectively and uncover insights that matter efficiently.   1 Chapter Zotero  Let's talk about reference management and Zotero

Speech Corpus Querying

This tutorial introduces a way to compile a speech corpus and make queries of speech intervals, using the command-line interface.    3 Chapters Unix Shell  Python  Corpus  Assemble time-aligned transcription files  Create query scripts  Create audio-trimming scripts

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.     3 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

Forced Alignment for Mandarin data

This tutorial walks you through the use of the Penn Forced Aligner (P2FA) and the Montreal Forced Aligner (MFA) on Mandarin data, from data preparation and installation to post-aligning processing. It integrates curated online resources along with original code snippets to streamline the workflow.       6 Chapters Unix Shell  Python  Montreal Forced Aligner  Penn Forced Aligner  Prepare Audio Files  Prepare Transcripts  Use Penn Forced Aligner  Use Montreal Forced Aligner (legacy)  Post-alignment Options  New Update: A Gentle Guide to Montreal Forced Aligner