TEN Agent is a conversational AI powered by the TEN, integrating Gemini 2.0 Live, OpenAI Realtime, RTC, and more. It delivers real-time capabilities to see, hear, and speak, while being fully compa…

This is the code and dataset repo for Interspeech 2024 paper "Target conversation extraction: Source separation using turn-taking dynamics"

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

A novel human-interaction method for real-time speech extraction on headphones.

simple and efficient python implemention of a series of adaptive filters. including time domain adaptive filters(lms、nlms、rls、ap、kalman)、nonlinear adaptive filters(volterra filter、functional link a…

MT3: Multi-Task Multitrack Music Transcription

Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

Perceptual Quality Estimator for speech and audio

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…

An Industrial Grade Federated Learning Framework

A high performance and generic framework for distributed DNN training

This library provides common speech features for ASR including MFCCs and filterbank energies.

SoundNet: Learning Sound Representations from Unlabeled Video. NIPS 2016

Deezer source separation library including pretrained models.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"

Chinese text normalization for speech processing

DDSP: Differentiable Digital Signal Processing

A tutorial for Speech Enhancement researchers and practitioners. The purpose of this repo is to organize the world’s resources for speech enhancement and make them universally accessible and useful.

The PyTorch-based audio source separation toolkit for researchers

A UNIFIED SPEECH ENHANCEMENT FRONT-END FOR ONLINE DEREVERBERATION, ACOUSTIC ECHO CANCELLATION, AND SOURCE SEPARATION

Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of sep…

In defence of metric learning for speaker recognition