Bartelds / asr-augmentationLinks
Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation
☆16Updated 2 years ago
Alternatives and similar repositories for asr-augmentation
Users that are interested in asr-augmentation are comparing it to the libraries listed below
Sorting:
- A Mixed Sample Data Augmentation method for Training with Time-Frequency Domain Features☆10Updated 2 years ago
- The official implementation of the method discussed in the paper Improving Spoken Language Identification with Map-Mix(work accepted at I…☆17Updated 2 years ago
- Mispronunciation Detection using a pretrained and finetuned wav2vec2 model for phoneme recognition and diagnosis and feedback using large…☆28Updated last year
- ☆67Updated 11 months ago
- ☆16Updated last year
- The implementation for "Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions"☆43Updated 4 months ago
- Analysis of XLS-R for Speech Quality Assessment☆14Updated 6 months ago
- ☆24Updated 3 months ago
- A mini, simple, and fast end-to-end automatic speech recognition toolkit.☆54Updated 2 years ago
- INTERSPEECH 23 - Refunction Whisper to recognize new tasks with adapters!☆42Updated last year
- ☆16Updated last year
- ☆19Updated last year
- Aty-TTS: Improving fairness for spoken language understanding in atypical speech with Text-to-Speech☆10Updated 3 months ago
- A toolkit to calculate speech audio quality. Not affiliated with the original authors☆57Updated last year
- Official implementation for Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning☆94Updated 9 months ago
- [IJCAI'23] Learning to Speak from Text for Low-Resource TTS☆63Updated 2 years ago
- The TTSDS benchmark evaluates synthetic speech quality by considering prosody, speaker identity, and intelligibility, comparing these fac…☆55Updated last month
- NOTSOFAR-1 Challenge: Distant Diarization and ASR☆55Updated 6 months ago
- Train no-reference speech quality estimators with multiple datasets via learned, per-dataset alignments.☆17Updated 3 weeks ago
- VoicePAT is a modular and efficient toolkit for voice privacy research, with main focus on speaker anonymization.☆51Updated last year
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆88Updated last year
- This is a list of speech tasks and datasets, which can provide training data for Generative AI, AIGC, AI model training, intelligent spee…☆76Updated last year
- ☆43Updated 11 months ago
- A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.☆56Updated last week
- ☆80Updated 2 months ago
- ☆19Updated 2 years ago
- The VoxTube dataset official repository☆70Updated last year
- Official implementation of MelHuBERT☆66Updated 10 months ago
- ConMamba for Automatic Speech Recognition☆81Updated last year
- Companion repo for the paper "PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings…☆95Updated 7 months ago