An end-to-end framework for joint speech enhancement (SE) and automatic gain control (AGC)

Production First and Production Ready End-to-End Keyword Spotting Toolkit

The official Pytorch implementation of "Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors". [ICASSP 2024] and "LS-EEND: long-form streaming…

The official repo of UL-UNAS, an ultra-lightweight SE model.

An unofficial implementation of DeepVQE proposed by Microsoft Corp.

partitioned block based frequency domain Kalman filter

The dataset of Speech Recognition

Port of OpenAI's Whisper model in C/C++

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Open-source framework for conversational voice AI agents

Official repository for U-SAM (Interspeech 2025)

The official repo of NBC & SpatialNet for multichannel speech separation, denoising, and dereverberation

Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios

Muon is an optimizer for hidden layers in neural networks

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，接入openClaw，真正的个人语音助手，时延低至800ms，Mac等低配置也可运行，支持打断

Silero Models: pre-trained text-to-speech models made embarrassingly simple

Collect super-resolution related papers, data, repositories

This repository is the official implementation of the ICASSP 2025 paper: 'Self-supervised blind room parameter estimation using attention mechanisms.' The code will be made available upon the accep…

Fully Quantized Neural Networks For Speech Enhancement

Acoustic Echo Canceller for Mobile Module Port From WebRTC

A Flutter project can make you watch live with ease.

校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.