Pinned Repositories
AEC-Challenge
AEC Challenge
awesome-speech-enhancement
speech enhancement\speech seperation\sound source localization
beamforming_research
BinauralSpeechSynthesis
N/A
ConferencingSpeech2021
Conferencing Speech Challenge
crepe
CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)
DeepFilterNet
Noise supression using deep filtering
DTLN
Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.
Enhancement-Coded-Speech
ESC-50
ESC-50: Dataset for Environmental Sound Classification
FMzzq's Repositories
FMzzq/beamforming_research
FMzzq/AEC-Challenge
AEC Challenge
FMzzq/awesome-speech-enhancement
speech enhancement\speech seperation\sound source localization
FMzzq/BinauralSpeechSynthesis
N/A
FMzzq/ConferencingSpeech2021
Conferencing Speech Challenge
FMzzq/crepe
CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)
FMzzq/DeepFilterNet
Noise supression using deep filtering
FMzzq/DTLN
Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.
FMzzq/Enhancement-Coded-Speech
FMzzq/ESC-50
ESC-50: Dataset for Environmental Sound Classification
FMzzq/HowToCook
程序员在家做饭方法指南。
FMzzq/mcse
Multi-channel speech enhancement system (MVDR beamformer + several postfilters)
FMzzq/micronet
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
FMzzq/odddML
Machine Learning tools and utils for devs, brought to you by ODDD Technologies
FMzzq/PINTO_model_zoo
A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]
FMzzq/rnnoise
Recurrent neural network for audio noise reduction
FMzzq/Speech-Resources
语音方向实验室/公司/资源/实习等，欢迎推荐或自荐（排名不分先后）
FMzzq/speech_dataset
The dataset of Speech Recognition
FMzzq/SpeechAlgorithms
Speech Algorithms Collections
FMzzq/speechbrain
A PyTorch-based Speech Toolkit
FMzzq/TCN
Sequence modeling benchmarks and temporal convolutional networks
FMzzq/TensorflowASR
集成了Tensorflow 2版本的端到端语音识别模型，并且RTF(实时率)在0.1左右/Mandarin State-of-the-art Automatic Speech Recognition in Tensorflow 2
FMzzq/voicefilter
Unofficial PyTorch implementation of Google AI's VoiceFilter system
FMzzq/VoiceFilter-1
Unofficial Keras implementation of Google AI VoiceFilter
FMzzq/zhvoice
Chinese voice corpus. 中文语音语料，语音更加清晰自然，包含8个开源数据集，3200个说话人，900小时语音，1300万字。