A PyTorch-based Speech Toolkit

audio deep-learning transformers pytorch voice-recognition speech-recognition speech-to-text language-model speaker-recognition speaker-verification speech-processing audio-processing asr speaker-diarization speechrecognition speech-separation speech-enhancement spoken-language-understanding huggingface speech-toolkit

• Updated Oct 14, 2026
• Python

End-to-End Speech Processing Toolkit

text-to-speech deep-learning chainer end-to-end machine-translation pytorch speech-synthesis speech-recognition kaldi voice-conversion speaker-diarization speech-separation speech-enhancement spoken-language-understanding speech-translation singing-voice-synthesis

• Updated Nov 11, 2026
• Python

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

audio deep-learning speech pytorch speech-separation speech-enhancement noise-suppression speaker-extraction bandwidth-extension speech-quality-evaluation speech-super-resolution

• Updated Aug 14, 2025
• Python

The PyTorch-based audio source separation toolkit for researchers

deep-learning pytorch pretrained-models source-separation audio-separation speech-separation speech-enhancement

• Updated Nov 3, 2026
• Python

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

text-to-speech tts speech-synthesis voice-recognition speech-recognition speech-to-text stt speech-processing voice-activity-detection speech-separation speech-emotion-recognition voice-cloning

• Updated Jun 6, 2024

Unofficial PyTorch implementation of Google AI's VoiceFilter system

pytorch source-separation audio-separation speech-separation voicefilter

• Updated Jul 25, 2024
• Python

A must-read paper for speech separation based on neural networks

paper speech-separation speech-enhancement voice-separation

• Updated Aug 11, 2025
• TypeScript

A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).

pytorch pit source-separation audio-separation speech-separation permutation-invariant-training tasnet conv-tasnet

• Updated Apr 6, 2023
• Python

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

audio reproducible-research paper speech pytorch band speech-processing noise-reduction denoising speech-separation speech-enhancement narrow-band single-channel pretrained-model full-band sub-band

• Updated Aug 19, 2023
• Python

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement

deep-learning pytorch cnn-architecture speech-separation

• Updated May 26, 2023
• Python

Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.

tensorflow keras attention resnet residual-networks source-separation tcn speech-separation noise-estimation speech-enhancement multi-head-attention mmse robust-asr deepxi a-priori-snr-estimator minimum-mean-square-error mmse-lsa deep-xi deepmmse mhanet

• Updated Feb 17, 2022
• MATLAB

UniSpeech - Large Scale Self-Supervised Learning for Speech

speech pytorch speech-recognition speaker-verification speech-processing speech-separation diarization speech-diarization

• Updated Apr 5, 2024
• Python

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

deep-neural-networks deep-learning signal-processing speech-processing speech-analysis speech-separation

• Updated Jan 9, 2021
• MATLAB

The dataset of Speech Recognition

audio text-to-speech deep-neural-networks deep-learning speech tts speech-synthesis dataset wav speech-recognition automatic-speech-recognition speech-to-text voice-conversion asr speech-separation speech-enhancement speech-segmentation speech-translation speech-diarization

• Updated Jan 4, 2026

Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch

deep-learning pytorch rnn-model speech-separation speech-separation-algorithm

• Updated Feb 14, 2023
• Python

Tools for Speech Enhancement integrated with Kaldi

speech kaldi beamforming speech-separation speech-enhancement rir-generator time-frequency-masking

• Updated Jul 6, 2023
• Python

The SpeechBrain project aims to build a novel speech toolkit fully based on PyTorch. With SpeechBrain users can easily create speech processing systems, ranging from speech recognition (both HMM/DNN and end-to-end), speaker recognition, speech enhancement, speech separation, multi-microphone speech processing, and many others.

deep-learning neural-network speech speech-recognition neural-networks deeplearning speech-to-text speaker-recognition speaker-verification speech-processing speech-recognizer beamforming speech-analysis timit speechrecognition speech-api speech-separation librispeech speech-emotion-recognition speaker-identification

• Updated Jun 18, 2025
• HTML

Deep Recurrent Neural Networks for Source Separation

deep-learning matlab rnn source-separation audio-separation speech-separation speech-denoising

• Updated Jul 21, 2021
• MATLAB

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 separating sources from mixtures.

audio deep-learning speech speech-separation

• Updated Jul 6, 2023
• Jupyter Notebook

Real-time GCC-NMF Blind Speech Separation and Enhancement

machine-learning real-time gcc speech ipython-notebook low-latency dictionary-learning speaker speech-processing cross-correlation nmf real-time-processing unsupervised-machine-learning speech-separation speech-enhancement gcc-nmf generalized-cross-correlation tdoa

• Updated Apr 8, 2019
• Python