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)
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
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
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
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