OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.

[TACL'26] VoiceBench: Benchmarking LLM-Based Voice Assistants

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.

multi-scale time domain speaker extraction

SpEx+(tied) source code

This repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.

Constrained Permutation Invariant Training, Speech Separation

target speaker extraction and verification for multi-talker speech

Weighted Spatial Covariance Matrix Estimation for MUSIC based TDOA Estimation of Speech Source

Matlab-based deep learning toolkit that supports arbitrary directed acyclic graphs (DAG). Support DNN, LSTM, CNN layers and many signal processing layers. Include recipes/examples of using the tool…

Deep Learning for humans

A Powerful Spider(Web Crawler) System in Python.

A little library for text analysis with RNNs.