alessandroragano / scoreqLinks
SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)
☆92Updated 2 months ago
Alternatives and similar repositories for scoreq
Users that are interested in scoreq are comparing it to the libraries listed below
Sorting:
- Speech Human Evaluation Estimation Toolkit (SHEET)☆119Updated 3 weeks ago
- [InterSpeech 24] FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter☆93Updated last year
- Official implementation of DNSMOS Pro (accepted at INTERSPEECH 2024).☆65Updated 4 months ago
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆106Updated last year
- ICASSP 2024 - Generative De-Quantization for Neural Speech Codec via Latent Diffusion.☆55Updated last week
- (ICASSP 2025, official code)FlowSE: Flow Matching-based Speech Enhancement☆68Updated 3 months ago
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆78Updated 9 months ago
- ☆55Updated 10 months ago
- Official data preparation scripts for the URGENT 2024 Challenge☆84Updated 5 months ago
- High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec☆108Updated 4 months ago
- [ICASSP 2024] Official code for FreGrad☆36Updated last year
- NOMAD: Non-Matching Audio Distance (ICASSP 2024)☆29Updated 4 months ago
- Implementation of SpatialCodec.☆62Updated 2 years ago
- PAM is a no-reference audio quality metric for audio generation tasks☆74Updated last year
- ☆108Updated last month
- Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".☆70Updated 2 months ago
- Code for vec2wav 2.0, a speech token vocoder for VC. Paper: https://arxiv.org/abs/2409.01995☆79Updated 10 months ago
- ☆28Updated last year
- ☆147Updated 5 months ago
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆83Updated 6 months ago
- Unofficial SoundStream implementation of Pytorch with training code and 16kHz pretrained checkpoint☆74Updated 2 years ago
- BAE-NET: A LOW COMPLEXITY AND HIGH FIDELITY BANDWIDTH-ADAPTIVE NEURAL NETWORK FOR SPEECH SUPER-RESOLUTION☆72Updated last year
- ☆29Updated last year
- Generation scripts for EARS-WHAM and EARS-Reverb☆38Updated 3 months ago
- Official data preparation and metric evaluation scripts for the Interspeech 2025 URGENT challenge.☆74Updated 5 months ago
- ☆49Updated 6 months ago
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement☆157Updated 3 years ago
- Source code of APNet2, a vocoder☆55Updated last year
- ☆35Updated 2 years ago
- A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation☆108Updated last month