Master thesis project adapting the WhisperSeg model for ring-tailed lemurs, including all code necessary for experiment reproducibility.

An Audio Framework to Segment and Classify audio. It can process audios of different types (wav and mp3) and classify emotion, gender and authenticity of the audio.

Training and using audio segmentation

Whole Audio Analysis Research with Python

SEGAUGMENT: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations

Music Source Separation web application using U-Net model with 2 main features: Audio Separation & Karaoke

AsegTool is a tool designed to generate a segmentation file that is usable within my other tool. 🌵

Automatic generation of speech dataset markup using Wav2Vec2 ASR models

tensorflow for speech-music-detection task，acc 96%+

Automatic annotation of timbre variation for monophonic musical instruments

Our Little Tools

pitch detection,CNN

Synthetic sounds datasets and real sounds datasets of waterflow sounds for the repo 'Neural-Texture-Sound-Synthesis-with-physically-driven-continuous-controls'.

Build a digital music library by downloading and segmenting youtube videos.

This repository contains a web application that integrates with a music recommendation system, which leverages a dataset of 3,415 audio files, each lasting thirty seconds, utilising a Locality-Sensitive Hashing (LSH) implementation to determine rhythmic similarity, as part of an assignment for the Fundamental of Big Data Analytics (DS2004) course.

Voice activity detection and speaker gender segmentation audiovisual corpus

PyAnnote Voice Activity Detection (ONNX version)

Code for ICASSP 2024 paper WhisperSeg: Positive Transfer of the Whisper Speech Transformer to Human and Animal Voice Activity Detection

SHAS: Approaching optimal Segmentation for End-to-End Speech Translation

A data annotation pipeline to generate high-quality, large-scale speech datasets with machine pre-labeling and fully manual auditing.