DDxk's repositories
3D-convolutional-speaker-recognition
:speaker: Deep Learning & 3D Convolutional Neural Networks for Speaker Verification
100-Days-Of-ML-Code
100-Days-Of-ML-Code中文版
Algorithm_Interview_Notes-Chinese
2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记
ASR_Syllable
基于卷积神经网络的语音识别声学模型的研究
ASR_Theory
中文语音识别理论，包括研一与研二期间正在部分所学，论文和PPT
ASRT_SpeechRecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
deep-speaker
Deep Speaker: an End-to-End Neural Speaker Embedding System https://arxiv.org/pdf/1705.02304.pdf
deepSpeech-1
End-to-end speech recognition using distributed TensorFlow.
DeepSpeechRecognition
A Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型
dVectorSpeakerRecognition
基于dVector的说话人识别keras
ge2e-speaker-verification
Pytorch implement of "Generalized End-to-End Loss for Speaker Verification"
GMM_baseline
未来杯语音赛道说话人识别的baseline
go-common-1
听说这是来自 https://github.com/openbilibili/go-common/ 的 “哔哩哔哩 bilibili 网站后台工程 源码”，不过咱也不知道这是啥。 据说 是他干的
kaldi
This is the official location of the Kaldi project.
keras-yolo3
A Keras implementation of YOLOv3 (Tensorflow backend)
MachineLearningDOC
图像、人脸、OCR、语音相关算法整理
MyKaggle
练习和打Kaggle时记录的笔记和心得，用的colab
neural_sp
End-to-end ASR implementation with pytorch.
OctaveConv_pytorch
Pytorch implementation of Octave convolution
practicalAI-cn
AI实战-practicalAI 中文版
scikit-learn
scikit-learn: machine learning in Python
SincNet
SincNet is a neural architecture for efficiently processing raw audio samples.
Speaker_Verification
Tensorflow implementation of generalized end-to-end loss for speaker verification
Speech_Signal_Processing_and_Classification
Front-end speech processing aims at extracting proper features from short- term segments of a speech utterance, known as frames. It is a pre-requisite step toward any pattern recognition problem employing speech or audio (e.g., music). Here, we are interesting in voice disorder classification. That is, to develop two-class classifiers, which can discriminate between utterances of a subject suffering from say vocal fold paralysis and utterances of a healthy subject.The mathematical modeling of the speech production system in humans suggests that an all-pole system function is justified [1-3]. As a consequence, linear prediction coefficients (LPCs) constitute a first choice for modeling the magnitute of the short-term spectrum of speech. LPC-derived cepstral coefficients are guaranteed to discriminate between the system (e.g., vocal tract) contribution and that of the excitation. Taking into account the characteristics of the human ear, the mel-frequency cepstral coefficients (MFCCs) emerged as descriptive features of the speech spectral envelope. Similarly to MFCCs, the perceptual linear prediction coefficients (PLPs) could also be derived. The aforementioned sort of speaking tradi- tional features will be tested against agnostic-features extracted by convolu- tive neural networks (CNNs) (e.g., auto-encoders) [4]. The pattern recognition step will be based on Gaussian Mixture Model based classifiers,K-nearest neighbor classifiers, Bayes classifiers, as well as Deep Neural Networks. The Massachussets Eye and Ear Infirmary Dataset (MEEI-Dataset) [5] will be exploited. At the application level, a library for feature extraction and classification in Python will be developed. Credible publicly available resources will be 1used toward achieving our goal, such as KALDI. Comparisons will be made against [6-8].
triplet-loss-train-for-speaker-recognition
It is a complete project of voiceprint recognition or speaker recognition.Before, I upload a very classic VGG based model for speaker recognition . The model simply use softmax-loss to train super-parameters. But during testing stage,we found the model is not very reliable。for example, the model can easily distinguish man-man group, and man-woman group, but difficultly in woman-woman. So, we try another method called triplet-group to retrain our model, of course, we use triplet-loss as the loss for back propagation. The I upload our core code, and training curve for the two training stage. Why, I refer to "two training stage"? That need you to understand the triplet-group method. And very very welcome to my mailbox: primtee_nxg@163.com
VGG-Speaker-Recognition
Utterance-level Aggregation For Speaker Recognition In The Wild