kukum's repositories
AIOpen
AIOpen是一个按人工智能三要素（数据、算法、算力）进行AI开源项目分类的汇集项目，项目致力于跟踪目前人工智能（AI）的深度学习（DL）开源项目，并尽可能地罗列目前的开源项目，同时加入了一些曾经研究过的代码。通过这些开源项目，使初次接触AI的人们对人工智能（深度学习）有更清晰和更全面的了解。
AndroidUtilLib
🔥 旨在打造一款属于Android开发的强大工具库：内置各种开发必备工具类、Dialog封装、组件重写等
app_process-shell-use
利用 app_process 实现免root调用shell
Audioutils
:notes: Audioutils-音频录制和音频播放工具
decoder
digiter ASR based on cvte acoustic model
ESP
The Example-based Sensor Predictions (ESP) system applies machine learning to real-time sensor data.
findopenblas_cmake
CMake package finder for OpenBLAS
GMM_baseline
未来杯语音赛道说话人识别的baseline
hosts
:statue_of_liberty:最新可用的google hosts文件。镜像：
ivector-xvector
Extract xvector and ivector under kaldi
java-Speech-preprocessing
java版语音预处理以及MFCC提取 speech preprocessing and MFCC
kaldi-alligner
scripts to align a given wave to its transcription using trained models by Kaldi
kaldi-ivector-gender-classification
ivector demo for gender classification
kaldi-ivectors-for-python
This repository allows to use kaldi to train an i-vector extractor and extract i-vectors through a python interface.
KaldiRobot
ivector&PLDA
LeetCodeAnimation
Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路）
Master-Voice_Prints
This Repository includes four different implementations of the Speaker Verification task including the GMM_UBM, Ivector, Deep-Speaker, and voice-vector
my-kaldi-project
Improved cuda version for kaldi project
myVpDemo
Voice print demo(one man voice verify)
NeuroSpeech
Toolkit to asses speech impairments in patients with neurological disorders
speaker-embedding-with-phonetic-information
The code for the Interspeech paper "Speaker Embedding Extraction with Phonetic Information"
speaker-feature-extractor
说话人特征（声纹）提取工具，基于VGG-SR预训练模型。
Speaker_Verification_Tencent
Deep Discriminative Embeddings for Duration Robust Speaker Verification
SpeakerRecognizer
Recognizes speaker