趙殊陽

audioset_tagging_cnn. Python

MaskSpec. The Pytorch implementation of paper: Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training

DeepComplexCRN. HTML

ergodox_nordic_colemak. C

Python-WORLD. Python

vits_chinese. Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

childrenize. Signal processing method to convert adult speech into child-like

AEC-Challenge. AEC Challenge

android-demo-app. PyTorch android examples of usage in applications

TCN. Sequence modeling benchmarks and temporal convolutional networks

DeepXi. Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.

IRM-based-Speech-Enhancement-using-LSTM. Ideal Ratio Mask (IRM) Estimation based Speech Enhancement using LSTM

ru_norm_kaggle. Python

Speech-Separation-Paper-Tutorial. A must-read paper for speech separation based on neural networks

Conv-TasNet. Python

vits. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

dcase2022_task1_baseline. Baseline system for DCASE 2022 task 1

traditional-speech-enhancement. Spectral Subtraction, Wiener Filtering, MMSE

Python-Wrapper-for-World-Vocoder. A Python wrapper for the high-quality vocoder "World"

python-speech-enhancement. a python library for speech enhancement

AutoEq. Automatic headphone equalization from frequency responses

awesome-speech-enhancement. speech enhancement\speech seperation\sound source localization

active_learning. The active learning algorithm, mismatch-first farthest-traversal. Implementation and visualization.

mongol_code. Unicode conversion library for traditional Mongolian script

NISQA. NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

wav2vec2-live. A live speech recognition using Facebooks wav2vec 2.0 model.

Real-Time-Voice-Cloning. Clone a voice in 5 seconds to generate arbitrary speech in real-time

s3prl. Self-Supervised Speech Pre-training and Representation Learning Toolkit

pytorch-wavenet. An implementation of WaveNet with fast generation

emacs-from-scratch. An example of a fully custom Emacs configuration developed live on YouTube!

formant_edit. software for editing dynamic formant measurements

jackaudio.github.com. jackaudio's Website and Wiki hosted at github

audio_embedding_segmentation. Extracting audio embeddings based on a gated CNN trained using Audioset. A change point detection algorithm based on embeddings.

torch_audioset. PyTorch transcribed audioset classifier, including VGGish and YAMNet, along with utils to manipulate autioset category ontology.

matrix-creator-hal. Hardware Abstraction Layer for MATRIX Creator & MATRIX Voice

dcase2019-task5-urban-sound-tagging. 1st place solution to the DCASE 2019 - Task 5 - Urban Sound Tagging

onnx. Open standard for machine learning interoperability

awesome-emacs. A community driven list of useful Emacs packages, libraries and other items.

youtube-dl. Command-line program to download videos from YouTube.com and other video sites

weak_feature_extractor. Python

ESC-50. ESC-50: Dataset for Environmental Sound Classification

models. Models and examples built with TensorFlow