Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

Command line utility for forced alignment using Kaldi

My-Voice Analysis is a Python library for the analysis of voice (simultaneous speech, high entropy) without the need of a transcription. It breaks utterances and detects syllable boundaries, fundamental frequency contours, and formants.

A Python library for measuring the acoustic features of speech (simultaneous speech, high entropy) compared to ones of native speech.

PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi

Foreign Accent Conversion by Synthesizing Speech from Phonetic Posteriorgrams (Interspeech'19)

Official code for "Learning Neural Acoustic Fields" (NeurIPS 2022)

[AAAI 2024] CTX-txt2vec, the acoustic model in UniCATS

Acoustic mosquito detection code with Bayesian Neural Networks

The official code for the SALMon🍣 benchmark

🎵 A repository for manually annotating files to create labeled acoustic datasets for machine learning.

SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems

PyTorch implementation of automatic speech recognition models.

Code for the paper: Audio to Score Matching by Combining Phonetic and Duration Information

A crash course for training speech recognition models using DeepSpeech.

A Simple Automatic Speech Recognition (ASR) Model in Tensorflow, which only needs to focus on Deep Neural Network. It's easy to test popular cells (most are LSTM and its variants) and models (unidirectioanl RNN, bidirectional RNN, ResNet and so on). Moreover, you are welcome to play with self-defined cells or models.

Automated, end-to-end wakeword model maker using the Precise Wakeword Engine

Sequential adaptive elastic net (SAEN) approach, complex-valued LARS solver for weighted Lasso/elastic-net problems, and sparsity (or model) order detection with an application to single-snapshot source localization.

A voice driven 3D chess game for learning Voice AI