Speech synthesis, voice conversion, self-supervised learning, music generation,Automatic Speech Recognition, Speaker Verification, Speech Synthesis, Language Modeling

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.

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

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

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

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

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.

It is an algorithm analysed the acoustic features of a voice and creates an acoustic classifier - USEFUL for auto-speech-rater

PyTorch implementation of automatic speech recognition models.

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.

Some approaches based on deep learning to build the acoustic model for an end-to-end automatic speech recognition (ASR) pipeline.

A Bash script designed to make training sphinx4 and pocketsphinx acoustic libraries faster and easier

This is a sub-repository in building to create acoustic model in Mandarin speech recognition.

It is an algorithm analysed the acoustic features of a voice and creates an acoustic classifier - USEFUL for auto-speech-rater

This is now the official location of the Kaldi project.

Notebooks notes about Automatic Speech Recognition

A voice user interface that recognizes the user's voice via the Sphinx library to execute some commands. The system responds with a computer generated voice and sound clips. Finally, there's a server for storing and reacting to the data, and a client for connecting to the system.

some papers about automatic speech recognition

Development of a simulator of acoustic model

This python script is to convert an Indonesian word to phoneme sequence to generate a lexicon used to train Indonesian Automatic Speech Recognition system.

Acoustic event detection using yamnet model. Model is deployed using tensorflow serving in docker container and Flask API

A set of scripts to create an acoustic models based on OPS Aphasia database