mingmchen Goto Github PK

rokid-blacksiren

Rokid语音服务中，针对嵌入式设备环境的前端降噪模块

rpi_web_remote_control

利用树莓派和web界面远程控制空调等家电

rvidenet

Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes. CVPR 2020

seetafaceengine

september

:microphone: A text-independent real-time speaker recognition system

sesame

An OpenId Connect based voice print identification server

simplespeakerverification

simpletpu

A CNN accelerator, following Google's TPU V1.

single-image-super-resolution

A collection of high-impact and state-of-the-art SR methods

smartdeblur

Restoration of defocused and blurred photos/images

snips-nlu

Snips Python library to extract meaning from text

snips-nlu-language-resources

Language resources for the Snips Natural Language Understanding (NLU)

snr-based-progressive-learning-of-deep-neural-network-for-speech-enhancement

The implementation of the paper SNR-Based Progressive Learning of Deep Neural Network for Speech Enhancement.

sonic

Simple library to speed up or slow down speech

sonic-1

sonic-ndk

Android NDK wrapper for libsonic

soundlocation

基于pynq-z2的声源定位系统

soundmeter

分贝仪,检测周围噪音分贝大小

speaker-id

This repository contains audio samples and supplementary materials accompanying publications related to the speaker-id team at Google.

speaker-identification

Identifying individual speakers from utterances in the wild

speaker-recognition

A Speaker Recognition System

speaker-recognition-program

This program recognizes the speaker from a pre-existing database with 90% accuracy.

speaker-recognition-using-neuralnet

Used an audio dataset of 37 speakers each speaking 37 scripts in a variety of ways like whispering, speaking fast, etc. Aims at recognizing the identity of a speaker in a voice recording. Using Tensorflow to model a multi neural network and achieved an accuracy of 91%.

speaker-verification

Implementation of state of the art d-vector approach for speaker verification

speaker-verification-1

speaker-verification-using-gmm

Speaker Verification using Gaussian Mixture Model

speaker-verification_amsoftmax_pytorch

SE-Resnet+AMSoftmax for Speaker Verification

speakeridentificationneuralnetworks

⇨ The Speaker Recognition System consists of two phases, Feature Extraction and Recognition. ⇨ In the Extraction phase, the Speaker's voice is recorded and typical number of features are extracted to form a model. ⇨ During the Recognition phase, a speech sample is compared against a previously created voice print stored in the database. ⇨ The highlight of the system is that it can identify the Speaker's voice in a Multi-Speaker Environment too. Multi-layer Perceptron (MLP) Neural Network based on error back propagation training algorithm was used to train and test the system. ⇨ The system response time was 74 µs with an average efficiency of 95%.

speakerverification-tf

Speaker Embedding for verification / identification task using Tensorflow

speakervoiceidentifier

SpeakerVoiceIdentifier can recognize the voice of a speaker by learning.