yxlu-0102 / AP-BWELinks
Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction
☆174Updated 9 months ago
Alternatives and similar repositories for AP-BWE
Users that are interested in AP-BWE are comparing it to the libraries listed below
Sorting:
- HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform☆237Updated last year
- Open implementation of UNIVERSE and UNIVERSE++ diffusion-based speech enhancement models.☆111Updated last year
- Diffusion Singing Voice Conversion based on Grad-TTS from HuaWei☆161Updated 2 years ago
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆99Updated last year
- SSR-Speech: Towards Stable, Safe and Robust Zero-shot Speech Editing and Synthesis☆144Updated last year
- A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows☆210Updated last week
- Training code for FAcodec presented in NaturalSpeech3☆235Updated last year
- ☆150Updated 8 months ago
- StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation☆250Updated last year
- LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement☆94Updated 9 months ago
- FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3☆231Updated last year
- Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion☆154Updated 2 years ago
- ☆145Updated last year
- DEX-TTS: Diffusion-based EXpressive TTS with Style Modeling on Time Variability☆105Updated last year
- Unofficial implementation of miipher☆134Updated last year
- [ICASSP 2025] FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion☆90Updated 5 months ago
- Awesome Neural Codec Models, Text-to-Speech Synthesizers & Speech Language Models☆234Updated last month
- VITS with phoneme-level prosody modeling based on MaskGIT☆85Updated last year
- [INTERSPEECH 2024] The official implementation of EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for …☆169Updated 8 months ago
- ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations☆184Updated last year
- Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".☆84Updated 5 months ago
- High-Fidelity Neural Phonetic Posteriorgrams☆121Updated 10 months ago
- UTokyo-SaruLab MOS Prediction System☆285Updated last month
- It's a repository for implementations of neural speech editing algorithms.☆201Updated 2 years ago
- High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec☆114Updated 6 months ago
- [TAFFC 2025] The official implementation of EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vec…☆116Updated 4 months ago
- StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion☆187Updated last year
- Style-Controllable Zero-Shot Text to Speech Synthesizer based on VALL-E☆135Updated last year
- SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)☆101Updated 5 months ago
- [InterSpeech 24] FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter☆93Updated last year