A Survey of Spoken Dialogue Models (60 pages)

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

A playbook for systematically maximizing the performance of deep learning models.

View model summaries in PyTorch!

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit

Data manipulation and transformation for audio signal processing, powered by PyTorch

python wrapper for kaldi's native I/O

Production First and Production Ready End-to-End Speech Recognition Toolkit

A curated list of the latest breakthroughs in AI (in 2021) by release date with a clear video explanation, link to a more in-depth article, and code.

This repository is a curated list of awesome Speech Keyword Spotting (Wake-Up Word Detection).

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to provide participants with baseline systems for speech recogniti…

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

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

深度学习经典、新论文逐段精读

Maix Speech AI lib, a fast and small speech lib running on embedded devices, including ASR, chat, TTS etc.

A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

FSA/FST algorithms, differentiable, with PyTorch compatibility.

neural network based speaker embedder

OpenSpeaker is a completely independent and open source speaker recognition project. It provides the entire process of speaker recognition including multi-platform deployment and model optimization.

A 10000+ hours dataset for Chinese speech recognition

Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Large, modern dataset for speech recognition

Guidelines Support Library

Translation of C++ Core Guidelines [https://github.com/isocpp/CppCoreGuidelines] into Simplified Chinese.

Achieve a tiny STL in C++11

The C++ Core Guidelines are a set of tried-and-true guidelines, rules, and best practices about coding in C++

Implementation of the paper: Replay and Synthetic Speech Detection with Res2Net architecture (ICASSP 2021) https://arxiv.org/abs/2010.15006