marianne-m / brouhaha-vad
Predicts the level of noise and reverberation on your audiofiles
☆143Updated 7 months ago
Alternatives and similar repositories for brouhaha-vad:
Users that are interested in brouhaha-vad are comparing it to the libraries listed below
- Reference-aware automatic speech evaluation toolkit☆139Updated last month
- A simple package for Guided source separation (GSS)☆112Updated 7 months ago
- UT-Sarulab MOS prediction system using SSL models☆199Updated 9 months ago
- This is the Python library for an unsupervised, fast method for robust voice activity detection (rVAD), as in the paper rVAD: An Unsuperv…☆129Updated last month
- A sequence-to-sequence voice conversion toolkit.☆92Updated 6 months ago
- Unofficial implementation of miipher☆114Updated 8 months ago
- Evaluation and Benchmarking of Speech Super-resolution Methods☆144Updated 2 years ago
- Clustering-based methods for overlapping diarization☆74Updated last year
- Versatile Evaluation of Speech and Audio☆146Updated 2 weeks ago
- ☆88Updated last year
- The official Pytorch implementation of "Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based …☆106Updated last week
- Target Speaker Extraction Toolkit☆139Updated 2 months ago
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆183Updated 4 months ago
- Matlab and Python libraries for an unsupervised method for robust voice activity detection (rVAD), as in the paper rVAD: An Unsupervised …☆130Updated 11 months ago
- Reproducible experimental protocols for multimedia (audio, video, text) database☆92Updated this week
- An implementation of Microsoft's "AdaSpeech: Adaptive Text to Speech for Custom Voice"☆96Updated 2 years ago
- This is the official implementation of the SEMamba paper. (Accepted to IEEE SLT 2024)☆159Updated last month
- A python library for voice activity detection (VAD) for speech/non-speech segmentation.☆85Updated 2 years ago
- FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3☆183Updated 8 months ago
- ☆51Updated last year
- ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations☆137Updated 10 months ago
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆75Updated last year
- ☆55Updated 11 months ago
- A PyTorch implementation of End-to-End Neural Diarization☆101Updated last year
- Spot the conversation: speaker diarisation in the wild☆132Updated 2 years ago
- High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec☆91Updated 3 months ago
- Confidence interval computation for evaluation in machine learning using the bootstrapping approach☆70Updated 9 months ago
- Easy-to-Use Speech MOS predictors☆251Updated last year
- Update ASR paper everyday☆105Updated this week
- Expressive Anechoic Recordings of Speech (EARS)☆141Updated 6 months ago