anooptoffy/DLJeju2018CodeRepoASR
Details on my work on using GANs for speech synthesis for improving Speech Recognition accuracy for ASR problem
This project helps improve the accuracy of speech recognition systems by generating additional synthetic speech data. It takes existing labeled and unlabeled speech recordings as input and produces new, synthesized speech outputs. This expanded dataset is then used to train and enhance a baseline speech recognition system, making it more robust. It is intended for researchers and engineers working on automatic speech recognition (ASR) systems.
No commits in the last 6 months.
Use this if you need to improve the accuracy of a speech recognition system but are limited by the amount or variety of real-world speech data available for training.
Not ideal if you are looking for a general-purpose speech synthesis tool or a complete, production-ready speech recognition system out-of-the-box.
Stars
8
Forks
2
Language
—
License
MIT
Category
Last pushed
Aug 01, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/anooptoffy/DLJeju2018CodeRepoASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
fatchord/WaveRNN
WaveRNN Vocoder + TTS
shangeth/wavencoder
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation,...
rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier...
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)