xiaomi-research / dasheng-denoiserLinks
Official PyTorch inference code for the Interspeech 2025 paper: Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders
☆35Updated this week
Alternatives and similar repositories for dasheng-denoiser
Users that are interested in dasheng-denoiser are comparing it to the libraries listed below
Sorting:
- （WIP）long form speech generatoins☆31Updated 2 months ago
- ☆28Updated last month
- faster inference☆28Updated 5 months ago
- Official Implementation of GLAP - General Language Audio Pretraining☆25Updated this week
- An evaluation set for large-scale trained TTS models (Coming in Sep 2024)☆12Updated 9 months ago
- A robust pitch tracker using synchro-squeezed fft and frequency domain autocorrelation☆34Updated last year
- The open source code of ALMTokenizer2: Towards Low bit-rate and Semantic-rich Audio Tokenizer with Flow-based Scalar Diffusion Transforme…☆26Updated last month
- Code of the paper "Low-Latency Speech Separation Guided Diarization for Telephone Conversations"☆14Updated 2 years ago
- Streaming Vocos☆27Updated last week
- A single-layer, streaming codec model providing SOTA audio quality and discrete tokens designed for superior downstream modelability.☆68Updated 2 weeks ago
- This is the official train-dev-test release of the Interspeech2024 Discrete Speech Representation Challenge.☆32Updated last year
- Try to replicate the architecture of MiniMaxTTS mentioned in it's technical report☆33Updated last month
- An unofficial implementation of "UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding".☆26Updated last year
- LLaSE: Maximizing Acoustic Preservation for LLaMA based Speech Enhancement☆16Updated 3 months ago
- Spherical residual vector quantization (SRVQ)☆30Updated 9 months ago
- A Neural Audio Codec (NAC) for Universal Audio☆36Updated 3 weeks ago
- A simple command line tool to calculate WER for ASR.☆14Updated 8 months ago
- ☆74Updated 2 weeks ago
- ☆21Updated 8 months ago
- A toolkit for researchers in the multimodal sound separation.☆16Updated last year
- ☆16Updated 6 months ago
- 60k hours of phoneme-aligned audio from audio books☆18Updated 10 months ago
- ICASSP2022 TTS&VC Summary☆14Updated 3 years ago
- Tidy Tunes is an easy-to-use pipeline for mining high-quality audio data for speech generation models. To do so, it chains multiple open …☆16Updated 2 weeks ago
- ☆19Updated last year
- Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark☆28Updated last month
- Please visit https://thuhcsi.github.io/SnakeGAN/☆37Updated 2 years ago
- ☆28Updated 4 months ago
- A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation☆34Updated 2 weeks ago
- ☆47Updated 2 months ago