gaoyiyeah

ASR---Word-Error-Rate-GUI

This is an interactive GUI where you can enter some ground truth and hypothesis/asr-output to compute the Word Error Rate. It shows the evaluation.

asr-evaluation

Python module for evaluating ASR hypotheses (e.g. word error rate, word recognition rate).

asv-subtools

An Open Source Tools for Speaker Recognition

ChineseNLP

Datasets, SOTA results of every fields of Chinese NLP

cocoapi

COCO API - Dataset @ http://cocodataset.org/

Conv-TasNet-1

A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).

Conv-TasNet-2

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement

DBFace

DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy

DCUNetTorchSound

Implementation of Phase-aware speech enhancement with deep complex U-Net

deep-sdm

deep-sdm is appied for face landmark.

delta

DELTA is a deep learning based natural language and speech processing platform.

dual-path-RNNs-DPRNNs-based-speech-separation

A PyTorch implementation of dual-path RNNs (DPRNNs) based speech separation described in "Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation".

duckling

Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.

end-to-end-lipreading

Pytorch code for End-to-End Audiovisual Speech Recognition

FewShotTagging

Code for ACL2020 paper: Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network

Interspeech-2020-Non-native-children-ASR

mediapipe

MediaPipe is the simplest way for researchers and developers to build world-class ML solutions and applications for mobile, edge, cloud and the web.

MicArrayBeamforming

Microphone Array Beamforming Toolbox

NLP-Models-Tensorflow

Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0

NSNet

This in an implementation of NSNet in PyTorch and PyTorch Lightning. NSNet is a recurrent neural network for single channel speech enhancement.

Online-Speech-Recognition

Working online speech recognition based on RNN Transducer. ( Trained model release soon ... )

OpenAttack

An Open-Source Package for Textual Adversarial Attack.

OpenTransformer

A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

pytorch_face_landmark

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100FPS landmark inference on CPU.

re2

RE2 is a fast, safe, thread-friendly alternative to backtracking regular expression engines like those used in PCRE, Perl, and Python. It is a C++ library.

sound-source-localization-algorithm_DOA_estimation

关于语音信号声源定位DOA估计所用的一些传统算法

SpeechAlgorithms

Code of my WeChat Offical Account

speechmetrics

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

spokestack-android

Spokestack speech recognition pipeline for Android

VL-BERT

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".