Code Monkey home page Code Monkey logo

Deep Speaker: speaker recognition system

Data Set: LibriSpeech
Reference paper: "Deep Speaker: an End-to-End Neural Speaker Embedding System"
Reference code : (Thanks Philippe Rémy. I have greatly modified the code during the experiment, but the theme is still similar.)

This code was trained using librispeech-train-clean dataset, tested using librispeech-test-clean dataset. In my code librispeech dataset shows ~5% EER using CNN.

About Code
This is the main file. This file train the model,then save the model and evaluate the result every specific steps.
This is the implementation of model used in this project. It contains three models, the CNN model (similar with the paper's CNN), the GRU model (similar with the paper's GRU), and the third model is simplified simple_cnn model.
Choose the optimal batch feed to the network. This is one of the core of this experiment.
This is the code for calculating the triplet-loss for network training.
This is a code that evaluate (test) the model, Such as eer...
This file contains equal error rate, f-measure, accuracy and other metrics used in evaluation part.
This is a code for pre-training of softmax classification.
This code implemented for read the voice-data, filter the mute, extract the fbank feature, and save the extracted-features as .npy format.


This code was trained using librispeech-train-clean dataset, tested using librispeech-test-clean dataset. In my code, librispeech dataset shows ~5% EER using CNN.

If you want to know more details, please read 'deep_speaker实验报告.pdf'(Chinese). If you want to read details in English, please contact me.

Siomarry's Projects

7days-golang icon 7days-golang

7 days golang programs from scratch (web framework Gee, distributed cache GeeCache, object relational mapping ORM framework GeeORM, rpc framework GeeRPC etc) 7天用Go动手写/从零实现系列

bootstrap icon bootstrap

The most popular HTML, CSS, and JavaScript framework for developing responsive, mobile first projects on the web.

cppprimer icon cppprimer

:books: Solutions for C++ Primer 5th exercises.

deep-speaker icon deep-speaker

Deep Speaker: an End-to-End Neural Speaker Embedding System

examples icon examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

hello-wolrd icon hello-wolrd

this is my first step to go deep into Github and Git that I haven't know so far

java icon java


muduo icon muduo

Event-driven network library for multi-threaded Linux server in C++11

pliers icon pliers

Automated feature extraction in Python

springsnail icon springsnail

《Linux 高性能服务器》附带的项目程序springsnil详细解读,一个负载均衡服务器

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.