facebookresearch / ears_datasetLinks
Expressive Anechoic Recordings of Speech (EARS)
☆200Updated last year
Alternatives and similar repositories for ears_dataset
Users that are interested in ears_dataset are comparing it to the libraries listed below
Sorting:
- Speech Human Evaluation Estimation Toolkit (SHEET)☆127Updated 2 months ago
- Official data preparation scripts for the URGENT 2024 Challenge☆87Updated 7 months ago
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement☆158Updated 3 years ago
- SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)☆99Updated 4 months ago
- Reference-aware automatic speech evaluation toolkit☆172Updated last year
- Unofficial SoundStream implementation of Pytorch with training code and 16kHz pretrained checkpoint☆77Updated 2 years ago
- A simple package for Guided source separation (GSS)☆131Updated last year
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆110Updated last year
- High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec☆112Updated 6 months ago
- ☆107Updated 2 years ago
- ☆149Updated 7 months ago
- PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio☆214Updated 2 years ago
- ☆61Updated last year
- This github repo is for Neurips 2021 and Interspeech 2022 papers on Non-Matching Reference based estimation of speech quality assessment.…☆105Updated 2 years ago
- Transformer with Local Modeling by Convolution for Speech Separation and Enhancement☆114Updated 4 months ago
- High-Fidelity Neural Phonetic Posteriorgrams☆120Updated 10 months ago
- Official repository for FlowSE (Interspeech 2025)☆78Updated 5 months ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆79Updated last year
- Predicts the level of noise and reverberation on your audiofiles☆172Updated 6 months ago
- ☆56Updated last year
- Single channel speech source separation by diffusion process (ICASSP 2023)☆123Updated last year
- ☆66Updated 2 years ago
- Official implementation of DNSMOS Pro (accepted at INTERSPEECH 2024).☆73Updated 6 months ago
- ☆65Updated 2 years ago
- MOS score prediction by fine-tuned wav2vec2.0 model☆173Updated 3 years ago
- PAM is a no-reference audio quality metric for audio generation tasks☆76Updated last year
- Pytorch implementation of subband decomposition☆92Updated 3 years ago
- Evaluation and Benchmarking of Speech Super-resolution Methods☆152Updated 3 years ago
- The official PyTorch implementation of "Inter-SubNet: Speech Enhancement with Subband Interaction", accepted by ICASSP 2023.☆98Updated 2 years ago
- Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"☆211Updated last year