microsoft / MS-SNSD
The Microsoft Scalable Noisy Speech Dataset (MS-SNSD) is a noisy speech dataset that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) levels desired.
☆488Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for MS-SNSD
- Python implementation of the Short Term Objective Intelligibility measure☆327Updated 10 months ago
- Different implementations of "Weighted Prediction Error" for speech dereverberation☆494Updated 2 months ago
- Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.☆499Updated 2 years ago
- Tools for Speech Enhancement integrated with Kaldi☆399Updated last year
- An open source dataset for source separation☆380Updated 9 months ago
- A minimum unofficial implementation of the "A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement" (CRN) using PyTorc…☆315Updated 4 years ago
- End-to-End Neural Diarization☆376Updated 3 years ago
- PESQ (Perceptual Evaluation of Speech Quality) Wrapper for Python Users (narrow band and wide band)☆538Updated 2 months ago
- Python implementation of performance metrics in Loizou's Speech Enhancement book☆390Updated 5 months ago
- A tutorial for Speech Enhancement researchers and practitioners. The purpose of this repo is to organize the world’s resources for speech…☆720Updated 3 years ago
- Voice Activity Detection based on Deep Learning & TensorFlow☆355Updated last year
- Implement Wave-U-Net by PyTorch, and migrate it to the speech enhancement.☆323Updated 2 years ago
- Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech☆333Updated last year
- AEC Challenge☆386Updated 5 months ago
- A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR☆908Updated last year
- ☆398Updated last year
- NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment☆685Updated 8 months ago
- Variational Bayes HMM over x-vectors diarization☆254Updated 10 months ago
- A must-read paper for speech separation based on neural networks☆757Updated 2 years ago
- A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permuta…☆682Updated last year
- Speaker embedding (d-vector) trained with GE2E loss☆273Updated 10 months ago
- Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.☆585Updated last year
- ☆285Updated 4 years ago
- Speech Enhancement Generative Adversarial Network in PyTorch☆379Updated last year
- transform-average-concatenate (TAC) method for end-to-end microphone permutation and number invariant ad-hoc beamforming.☆258Updated 3 years ago
- PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."☆551Updated last year
- Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196☆306Updated 4 years ago
- A python package for calculating the PESQ.☆357Updated last year
- Diarization scoring tools.☆220Updated last year
- Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-R…☆308Updated last year