asr_003.md

20200927

-

cnn-lstm-ctc

Theano implementation of LSTM and CTC to recognize simple english sentence image
https://github.com/aaron-xichen/cnn-lstm-ctc
https://github.com/Ewenwan/cnn-lstm-ctc

PWN0N/SLAM, Speech Automatic Speech Recognition,(ASR)

https://github.com/PWN0N/SLAM/blob/master/Speech/readme.md
科大讯飞 TTS
https://github.com/Ewenwan/Ros/blob/master/src/voice_system/src/xf_tts.cpp

openSMILE

https://github.com/naxingyu/opensmile

Apache Mahout

https://github.com/apache/mahout

NVIDIA/NeMo

https://github.com/NVIDIA/NeMo

EssayKiller_V2

基于开源GPT2.0的初代创作型人工智能 | 可扩展、可进化
https://github.com/EssayKillerBrain/EssayKiller_V2

高斯过程

https://github.com/MingchaoZhu/DeepLearning
机器学习精讲 全彩印刷 机器学习原理算法与应用教程 一本精简机器学习入门手册 美亚机器学习深度学习畅销书

knn

https://github.com/search?q=knn+speech
https://github.com/kkiani/animal-voice-recognition

TensorFlow Machine Learning Cookbook

https://github.com/nfmcclure/tensorflow_cookbook
TensorFlow机器学习实战指南 原书第2版
https://github.com/search?q=TensorFlow机器学习实战指南
https://github.com/Asurada2015/TF_Cookbook

机器学习经典算法实践

search baidupan, 机器学习经典算法实践

异步社区

https://www.epubit.com/search?txt=深度学习

深度学习原理与实践

https://github.com/chenzomi12/DeepLearning-In-Action/blob/master/chapter8/audio_FeatureExtraction.py

uTensor

https://github.com/uTensor/uTensor
https://github.com/ARMmbed/utensor-mnist-demo

Arduino+MAX9814制作简易录音机

https://www.jianshu.com/p/2b031a7fd2e6
https://github.com/TMRh20/TMRpcm
https://www.instructables.com/Make-Your-Own-Spy-Bug-Arduino-Voice-Recorder/
https://www.adafruit.com/product/1713
GND<->GND
V+<->VCC(3V3 or 5V)
GAIN<->NC
OUT<->A0
AR<->NC
(in pcmConfig.h, uncomment:)
#define buffSize 128. May need to increase.
#define ENABLE_RECORDING
#define BLOCK_COUNT 10000UL

arduino_microspeech

https://github.com/donwardpeng/arduino_microspeech/tree/master/lib/ArduinoSound

• ArduinoSound
  https://www.arduino.cc/en/Reference/ArduinoSound
  This library provides simple way to play and analyze audio data using Arduino on SAMD21 based boards
  (i.e Arduino or Genuino Zero, MKRZero or MKR1000 Board) using the I2S bus.
  ICS43432I2S
  https://www.arduino.cc/en/Tutorial/ArduinoSoundAmplitudeSerialPlotter
  MKR ZERO (I2S BUS & SD FOR SOUND, MUSIC & DIGITAL AUDIO DATA)
  https://store.arduino.cc/usa/arduino-mkrzero
  MKR 1000 (Zero plus the Wi-Fi)
  https://store.arduino.cc/usa/arduino-mkr1000
  MAX08357I2S
  https://www.arduino.cc/en/Tutorial/ArduinoSoundWavePlayback
• Arduino Esplora Microphone
  https://www.arduino.cc/en/Tutorial/LibraryExamples/EsploraSoundSensor
• Analog Sound Sensor, DFR0034, dfrobot
  https://blog.csdn.net/md521/article/details/78038012
  https://wiki.dfrobot.com/Analog_Sound_Sensor_SKU__DFR0034

BPI-EAI80, Key words recognition (closed source, see DSpotter2.lib, see Cyberon)

http://wiki.banana-pi.org/BPI-EAI80_AIoT_开发板
https://github.com/BPI-SINOVOIP/BPI-EAI80-bsp/blob/master/KelisSDK/ugelis/kelis_example/ai_example/ai/src/app/speechai/speech_recognize.c
https://github.com/waynelinbo/ARC---Sport-at-home

ISD9160, CSpotterSDK, Cyberon

https://blog.csdn.net/iotisan/article/details/53798704

(???IMP) keyword-spotter

https://github.com/accraze/keyword-spotter
https://rapidapi.com/accraze/api/keyword-spotter
https://github.com/search?q=SAMPLES_TO_CONSIDER+tensorflow&type=code
(dataset) https://github.com/osamaxsyed/speechRecognition
https://github.com/iamlekh/Speech-Recognition
https://github.com/musikalkemist/Deep-Learning-Audio-Application-From-Design-to-Deployment
Speech Commands Dataset：数千名讲话者说出的简短命令
https://blog.csdn.net/rubyboss/article/details/81083568
(may be ok)
xubuntu200464
Python==2.7.18rc1
tensorflow==1.5.0
tensorflow-tensorboard==1.5.1
pip==20.1.1

OpenSeq2Seq

https://nvidia.github.io/OpenSeq2Seq/html/speech-recognition.html
https://nvidia.github.io/OpenSeq2Seq/html/speech-commands.html

Speech Command

https://ai.googleblog.com/2017/08/launching-speech-commands-dataset.html
http://cs229.stanford.edu/proj2019aut/data/assignment_308875_raw/26500748.pdf
https://arxiv.org/pdf/1804.03209.pdf
翻译
http://www.ijiandao.com/2b/baijia/67523.html
https://github.com/weimingtom/wmt_ai_study/blob/master/launching-speech-commands-dataset.txt
https://github.com/tensorflow/tensorflow/tree/r1.4/tensorflow/examples/speech_commands

开放语音识别数据集大列表

https://www.ctolib.com/amp/JRMeyer-open-speech-corpora.html
https://github.com/JRMeyer/open-speech-corpora

零资源挑战赛

https://zerospeech.com
http://www.nwpu-aslp.org/newsContent/news20171225.html
Zerospeech Challenge（零资源挑战赛）是语音研究领域的一项重要的国际学术测评。
该测评旨在缺少语言专家知识的前提下，探寻从语音数据中自动学得语言学结构信息的方法。
据悉，在零资源（zero resource）或少资源（low resource）的情境下，
采用无监督、弱监督方法进行数据建模已经成为机器学习和语音研究的热点问题
https://zerospeech.com/2019/getting_started.html

ML-KWS-for-MCU, mbed2, mbed-cli, NUCLEO-F411RE

https://github.com/weimingtom/wmt_ai_study/blob/master/mbed_001.txt
https://github.com/ARM-software/ML-KWS-for-MCU/tree/master/Deployment
https://os.mbed.com/users/mbed_official/code/mbed/
https://os.mbed.com/users/mbed_official/code/mbed-sdk-tools/

ciglet

https://github.com/Sleepwalking/ciglet

声纹识别算法阅读之deep-speaker

https://github.com/luomingshuang/speaker_recognition_pytorch_v0
https://www.cnblogs.com/zy230530/p/13657717.html

Particle_TensorFlowLite_Examples

https://github.com/bsatrom/Particle_TensorFlowLite_Examples/blob/master/micro_speech/src/particle_audio_provider.cpp

mbed code search, i2s, microphone

https://os.mbed.com/search/repository?q=microphone
https://os.mbed.com/search/repository?q=i2s
https://os.mbed.com/teams/ST/code/ST_I2S/

STM32CubeMx with AI 体验

https://blog.csdn.net/weixin_37598106/article/details/107105068
https://github.com/Lebhoryi/Edge_AI

Speech-Recognition-Via-CNN

孤立词语音识别，复旦大学计算机科学技术学院数字信号处理期末项目
https://github.com/ichn-hu/Speech-Recognition-Via-CNN

STM32H743BaiduSpeech

https://github.com/ensky16/STM32H743BaiduSpeech

stm32-tflm-micro-speech

https://github.com/PhilippvK/stm32-tflm-micro-speech

voiceprint, ivector

https://github.com/iwaterxt/voiceprint
(IMP???) C++
ivector
xvector
dnn-ivector
tdvector

tflm, mbed

https://github.com/uTensor/tflm

SparkFun MEMS Microphone Breakout - INMP401 (ADMP401)

https://os.mbed.com/users/rayxke/notebook/sparkfun-mems-microphone-breakout---inmp401-admp40/
https://github.com/sparkfun/MEMS_Mic_Breakout-ADMP401/blob/V_1.3/Firmware/SparkFun_ADMP401_Simple_Sketch/SparkFun_INMP401.ino

168种传感器模块系列实验（159）---MAX9814咪头传感器

https://www.mydigit.cn/forum.php?mod=viewthread&tid=129060

ISR(ADC_vect)

https://blog.csdn.net/sun6gm/article/details/19758967
https://github.com/sebastiancarlsson/fusion-totem/blob/master/master/master.ino

MAX9814

https://os.mbed.com/components/?q=microphone
https://os.mbed.com/components/Electret-Microphone-Amplifier-MAX9814/
https://os.mbed.com/users/andcor02/code/MAX9814_LED_Sound_Indicator/
https://os.mbed.com/components/Adafruit-MEMS-Microphone-Breakout-SPW243/
https://os.mbed.com/users/andcor02/code/MAX9814_Electret_Microphone_LED_Volume_I/#49d2ee7cb020

I2S Sound Tutorial for ESP32

https://diyi0t.com/i2s-sound-tutorial-for-esp32/

ESP32, blog.tensorflow.org

https://blog.tensorflow.org/2020/08/announcing-tensorflow-lite-micro-esp32.html
https://github.com/espressif/tensorflow/tree/master/tensorflow/lite/micro/examples/micro_speech#deploy-to-esp32
https://github.com/espressif/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/esp/audio_provider.cc

How to port TensorFlow Lite for Microcontroller applications to the Arm Cortex-M55 Processor

https://community.arm.com/developer/tools-software/tools/b/tools-software-ides-blog/posts/port-tensorflow-lite-for-cortex-m55
https://github.com/ARM-software/Tool-Solutions/blob/master/docker/tensorflow-lite-micro-models/build_tflite_micro_test.sh
如何将Arm Cortex-M55处理器与开源CMSIS库一起使用
https://aijishu.com/a/1060000000099377
移植TFLite-micro应用程序到Arm Cortex-M55处理器
https://zhuanlan.zhihu.com/p/268162039

Tensorflow in SDK_2.6.0_EVKB-IMXRT1050

https://www.nxp.com.cn/design/development-boards/i-mx-evaluation-and-development-boards/i-mx-rt1050-evaluation-kit:MIMXRT1050-EVK
Tensorflow Lite Micro (???) (only for IAR ???)

i.MX RT1010 eIQ

https://github.com/diegohdorta/pyeiq
恩智浦推出1美元i.MX RT1010 eIQ环境让MCU实现AI功能
http://www.cncms.com.cn/ai/20190710/07106541.html

eIQ ML Software Development Environment

https://www.nxp.com/design/software/development-software/eiq-ml-development-environment:EIQ
eIQ for TensorFlow Lite
https://www.nxp.com/design/software/development-software/eiq-ml-development-environment/eiq-for-tensorflow-lite:eIQTensorFlowLite

TensorFlow Machine Learning Projects

https://github.com/PacktPublishing/TensorFlow-Machine-Learning-Projects
TensorFlow机器学习项目开发实战, 清华大学出版社
第5章, 使用NLP进行从语音到文本的转换和主题的提取
（1）三个模块：特征提取（特征向量），DNN（深度神经网络，特征向量输入帧每个单词生成Softmax概率），
后处理（帧级后验分数，posterior score）
（2）特征提取中，使用GMM做活动检测器（VAD）。
（3）DNN中，有五种网络可选，默认使用conv，完全连接的卷积层（CNN）
（4）训练中，不断打印step（步数）、rate（学习率，最初0.001）、accuracy和cross entropy（交叉熵损失）。
最终Step达到18000（几个小时后），rate降低到0.0001，accuracy达到88.5%。每隔100步保存一次模型，
便于随时中断，然后从最新保存的checkpoint（检查点）重新启动训练。

TensorFlow_MIMXRT1064-EVK_Microspeech

https://github.com/ARMmbed/TensorFlow_MIMXRT1064-EVK_Microspeech

__ICCARM__, __REV  

https://github.com/ARMmbed/TensorFlow_MIMXRT1064-EVK_Microspeech/blob/master/packs/flatbuffers/1.12.0/src/include/flatbuffers/base.h

机器学习理论导引

https://github.com/datawhalechina/key-book

search BiRNN 语音识别

CNN-BiRNN-Attention, CTC, LSTM
TensorFlow入门教程(20)语音识别固化模型和应用
https://blog.csdn.net/rookie_wei/article/details/89721441
BIRNN语言识别中遇到的坑
https://blog.csdn.net/qq_29678299/article/details/89755422
[TensorFlow深度学习入门]实战十一·用双向BiRNN(LSTM)做手写数字识别准确率99%+
https://xiaosongshine.blog.csdn.net/article/details/84954385

深度学习之TensorFlow 入门、原理与进阶实战

https://www.aianaconda.com/index/CodeOne
https://github.com/search?l=Python&p=100&q=batch_cost+sess+run&type=Code
https://blog.csdn.net/qq_29678299/article/details/89755422
(IMP???) BiRNN 语音识别
https://github.com/KFUA/TensorflowCode
https://github.com/KFUA/TensorflowCode/blob/master/9-23%20%20yuyinchall.py

TensorFlow入门教程(17)语音识别

search baidupan, 17.speech_recognition.zip TensorFlow入门教程(17)语音识别(上)
https://blog.csdn.net/rookie_wei/article/details/84527839
TensorFlow入门教程(18)语音识别(中)
https://blog.csdn.net/rookie_wei/article/details/84618774
TensorFlow入门教程(19)语音识别(下)
https://blog.csdn.net/rookie_wei/article/details/84640258

TensorFlow入门教程(20)语音识别固化模型和应用

search baidupan, 20.speech_recognition_app.zip
TensorFlow入门教程(20)语音识别固化模型和应用
https://blog.csdn.net/rookie_wei/article/details/89721441

TensorflowLiteMicro, RT-Thread

https://github.com/QingChuanWS/TensorflowLiteMicro
raspi4-tfliteMicro, RT-Thread, rpi4
https://github.com/QingChuanWS/raspi4-tfliteMicro

Programming PyTorch for Deep Learning

基于PyTorch的深度学习, 第6章，声音之旅
https://github.com/falloutdurham/beginners-pytorch-deep-learning/blob/master/chapter6/Chapter%206.ipynb
https://github.com/falloutdurham/pytorchupandrunning/blob/master/chapter6/Chapter%206.ipynb
https://github.com/karolpiczak/ESC-50

Pico语音助手

https://zhuanlan.zhihu.com/p/72896282
Project-Quantum, 超迷你模块化卡片电脑计划, 量子计划, seeedstudio
https://github.com/peng-zhihui/Project-Quantum
https://github.com/liukai-tech/Project-Quantum

emlearn

https://github.com/emlearn/emlearn
https://github.com/emlearn/emlearn/blob/master/emlearn/eml_audio.h
https://github.com/emlearn/emlearn/blob/audio-example/emlearn.ino

(IMP???) embeddedml

https://github.com/jonnor/embeddedml
TensorFlow Speech Recognition Challenge
https://www.kaggle.com/c/tensorflow-speech-recognition-challenge/data

通过kaggle学习speech recognition笔记——TF SR Challenge

https://zhuanlan.zhihu.com/p/64977527

Matrix Voice ：一个内嵌FPGA硬件加速器的低价语音识别平台

https://www.sohu.com/a/130212699_292853
https://github.com/matrix-io/matrixio_hal_esp32
https://github.com/Romkabouter/Matrix-Voice-ESP32-MQTT-Audio-Streamer
https://matrix-io.github.io/matrix-documentation/
https://github.com/matrix-io/matrixio_hal_esp32/tree/master/examples

(IMP???) stm32录音

https://github.com/gitroberto92/embes

github speech-to-text

https://github.com/topics/speech-to-text

SDL2 record, Audio Recording

https://lazyfoo.net/tutorials/SDL/34_audio_recording/index.php
https://stackoverflow.com/questions/52121428/sdl-openaudiodevice-with-multiple-devices

search github, SDL_OpenAudioDevice speech

https://github.com/search?q=SDL_OpenAudioDevice+speech&type=code
(IMP???) https://github.com/s-r-north/KIFT/blob/4e03263a87bf4a65f0d3c1ec4f614493489f2bda/src/client/client.c
how to use pocketsphinx ???

Python自然语言处理实战

https://www.ituring.com.cn/book/2679
《Python自然语言处理实战》链接表
https://www.ituring.com.cn/article/510382
Hands-On Natural Language Processing with Python
https://www.packtpub.com/free-ebook/hands-on-natural-language-processing-with-python/9781789139495
(IMP) 第11章, 使用DeepSpeech进行语音识别
https://github.com/PacktPublishing/Hands-On-Natural-Language-Processing-with-Python/blob/master/Chapter11/01_example.ipynb
search baidupan, Python自然语言处理实战
Jakobovski的免费数字音频数据集
https://github.com/Jakobovski/free-spoken-digit-dataset/
librosa
https://github.com/librosa/librosa
DeepSpeech模型原始论文
https://arxiv.org/abs/1412.5567
语言数据协会语音录音下载
https://www.kaggle.com/nltkdata/timitcorpus
DeepSpeech在大型数据集上的实现
https://github.com/mozilla/DeepSpeech
Listen, Attend, and Spell: A Neural Network for Large Vocabulary Conversational Speech Recognition
https://a.google/research/pubs/pub44926
DeepSpeech模型的PyTorch实现
(dead link) https://github.com/XenderLiu/ListenAttend-and-Spell-Pytorch
https://github.com/liuchenbaidu/Listen-Attend-and-Spell-Pytorch
https://github.com/Alexander-H-Liu/End-to-end-ASR-Pytorch

卷积神经网络（CNN）在语音识别中的应用

ResNet
https://www.cnblogs.com/jins-note/p/9897191.html

esp32_audio

Sample code for reading audio samples from the ESP32 ADC using I2S
https://github.com/atomic14/esp32_audio

nxp-nanoai/nanoai

https://github.com/nxp-nanoai/nanoai

• https://github.com/BVLC/caffe
  Caffe
• https://github.com/protocolbuffers/protobuf
  Protobuffer
• https://github.com/Tencent/ncnn
  NCNN
• https://github.com/onnx/onnx
  ONNX
• https://github.com/alibaba/MNN
  https://www.mnn.zone
  MNN
• https://arm-software.github.io/CMSIS_5/NN/html/index.html
  CMSIS NN
• https://opencv.org/
  Open CV
• https://github.com/Tencent/TNN
  TNN
• https://github.com/PaddlePaddle/Paddle-Lite
  PL
• https://github.com/XiaoMi/mace
  mace
• https://gitee.com/OAL/Tengine/tree/tengine-lite
  tengine-lite
• https://github.com/PaddlePaddle/Anakin
  Anakin
• https://gitee.com/mindspore/mindspore
  https://www.mindspore.cn/tutorial/training/zh-CN/master/index.html
  MindSpore
  https://www.mindspore.cn/tutorial/lite/zh-CN/r1.0/index.html
  MindSpore Lite
• https://gitee.com/explore/machine-learning
  etc
• http://www.openailab.com
  Open AI Lab
  http://www.openailab.com/int/ability/list2.html
  Tengine
  https://mp.weixin.qq.com/s/CzqmyCeNiWcseHZlSOMRQg
  精于型 悍于心！Tengine-Lite以开源致敬AIoT
  https://github.com/OAID/Tengine/tree/tengine-lite
  Tengine-Lite GitHub开源链接
  http://www.openailab.com/int/solution/4.html
  超低功耗IoT语音解决方案
  穿戴设备语音解决方案功耗＜3mW
  智能家居设备语音解决方案功耗＜10mW
  可在M4F流畅运行双麦前端拾音、唤醒词/命令词算法
  可在M0流畅运行唤醒词/命令词算法
  支持业内主流芯片Cortex-A、Cortex-M、RISC-V、HiFi3/4、CEVA等异构平台
  支持FreeRTOS、RT-Thread、Linux、Android等多种操作系统
• https://github.com/pytorch/QNNPACK
  QNNPACK
• https://github.com/pytorch/pytorch/tree/master/android
  https://pytorch.org/mobile/android/
  https://github.com/pytorch/android-demo-app
  https://github.com/pytorch/android-demo-app/tree/master/PyTorchDemoApp
  PyTorch Mobile
• https://github.com/google/XNNPACK
  XNNPACK

diy-alexa

DIY Alexa With the ESP32 and Wit.AI
https://github.com/atomic14/diy-alexa
Atomic14 Builds a "DIY Alexa" with an ESP32, TensorFlow Lite, and Facebook's Wit.ai Service
https://www.hackster.io/news/atomic14-builds-a-diy-alexa-with-an-esp32-tensorflow-lite-and-facebook-s-wit-ai-service-422dc8c30fb1
https://www.bilibili.com/video/av927675797

synaptic

architecture-free neural network library for node.js and the browser
https://github.com/cazala/synaptic
Tiny-RNN
https://github.com/peterrudenko/tiny-rnn

HDNNLib

https://github.com/microhu/HDNNLib

https://github.com/search?q=Synaptic.js+lstm&type=code

(IMP???) TC-ResNet, tensorflow

https://github.com/hyperconnect/TC-ResNet/
https://blog.csdn.net/weixin_37598106/article/details/105518851
maze, KWS
https://github.com/XiaoMi/mace/blob/master/micro/pretrained_models/tensorflow/README.md

(IMP???) honk, tfjs

https://github.com/castorini/honk
https://github.com/castorini/honk-models
https://github.com/castorini/kws-gen-data
(IMP???) js网页版关键词语音识别
https://castorini.github.io/honkling/view/home.html
https://github.com/mingri-lt/KeyWordSpotting02_lt

LibreASR

https://github.com/iceychris/LibreASR
LibreASR using the ESP32_LyraT as a Client
https://github.com/iceychris/LibreASR/tree/master/apps/esp32

CMU Flite: a small, fast run time synthesis engine

http://www.festvox.org/flite/
esp32-flite
https://github.com/alkhimey/esp32-flite

pytorch-lightning

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
https://github.com/PyTorchLightning/pytorch-lightning

中国 AI 市场份额：涉及视觉；语音语义；机器学习开发平台

https://baijiahao.baidu.com/s?id=1651402421807295182&wfr=spider&for=pc
Bert
https://github.com/google-research/bert
Xlnet
https://github.com/zihangdai/xlnet
ERINE(???)

TsinghuaAI/CPM-Generate

https://github.com/TsinghuaAI/CPM-Generate

(IMP) cortex-m-kws, tengine-lite

https://github.com/OAID/cortex-m-kws
https://github.com/OAID/Tengine/tree/tengine-lite

webfansplz/volute

volute(蜗壳)是一个使用 Raspberry Pi+Node.js 制作的语音助手.
https://github.com/webfansplz/volute

ARM NN, TinyML

https://github.com/ARM-software/armnn
https://developer.arm.com/solutions/machine-learning-on-arm/developer-material/how-to-guides
https://github.com/arduino/AIoT-Dev-Summit-2019#tinyml-application-development-for-everyone

pytorch_template_audio

https://github.com/wuaalb/pytorch_template_audio

Tengine

http://www.tengine.org.cn

xboot/libonnx

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.
https://github.com/xboot/libonnx
计划手写一份纯C版AI深度学习推理引擎，并支持硬件加速接口
https://whycan.com/t_5440.html

onnxjs

https://github.com/microsoft/onnxjs
https://github.com/microsoft/onnxjs-demo
onnxjs-demo
https://microsoft.github.io/onnxjs-demo/#/mnist

keras-js

https://github.com/transcranial/keras-js

yuantiku/ytk-learn

https://github.com/yuantiku/ytk-learn

深度学习核心技术与实践

http://www.broadview.com.cn/book/2422
猿题库、猿辅导
search baidupan, 32905.zip

OAID/SpeechRecognition, kaldi

https://github.com/OAID/SpeechRecognition

MatrixSlow

https://github.com/zackchen/MatrixSlow
用Python实现深度学习框架

梅尔频率倒谱系数（MFCC） 学习笔记

https://www.cnblogs.com/BaroC/p/4283380.html
libMFCC - C library for computing Mel-Frequency Cepstral Coefficients
https://github.com/jsawruk/libmfcc

深入比较kaldi和python_speech_features提取的fbank特征之间的区别

https://zhuanlan.zhihu.com/p/55371926
mfcc

speech-recognition-on-stm32

https://github.com/Simakeng/speech-recognition-on-stm32

search lifter hz2mel

https://github.com/search?q=lifter+hz2mel&type=code
c_keyword_spotting, kws_guess
https://github.com/ruslanbasic/cpes/tree/master/projects/iobjects-esp_cp/components/kws_guess/c_keyword_spotting

32F411EDISCOVERY

https://www.st.com/en/evaluation-tools/32f411ediscovery.html#overview

google/XNNPACK

https://github.com/google/XNNPACK

CNNdroid

https://github.com/ENCP/CNNdroid
请问在CPU下最快的深度学习框架是哪种？caffe2?mkldnn?nnpack?
https://www.zhihu.com/question/54841525

C语言实现基2DIF-FFT算法（桑德·图基快速傅立叶变换）

https://blog.csdn.net/sinat_25549771/article/details/53320396

【毕业造物】-自制迷你语音助手机器人 Pico 【19.7.15更新】

http://www.pengzhihui.xyz/2019/07/15/pico/

在STM32上跑神经网络做手势检测 (where are CNN-SLR and M4CNN codes ???)

http://www.pengzhihui.xyz/2019/07/20/m4cnn/
http://www.pengzhihui.xyz/2019/09/13/k210-1/

Arduino实现VGA输出

http://www.51hei.com/bbs/dpj-122615-1.html
Arduino制作：支持Basic和VGA显示器的复古计算机
https://www.quwj.com/2019/01/25/arduino-basic-pc-with-vga-output.html
https://github.com/BleuLlama/TinyBasicPlus
https://make.quwj.com/project/92

[开发工具] AC5 to AC6

http://www.armbbs.cn/forum.php?mod=viewthread&tid=95736

ARM Assembly Programming Using Raspberry Pi

http://www.microdigitaled.com/ARM/ASM_ARM/Software/ARM_Assembly_Programming_Using_Raspberry_Pi_GUI.pdf

ARM DS-5到底是什么？为什么不建议使用DS-5开发STM32？

https://blog.csdn.net/ybhuangfugui/article/details/99514317

himax_tflm, micro_speech

https://github.com/HimaxWiseEyePlus/himax_tflm/blob/master/tensorflow/lite/micro/examples/micro_speech/himax_we1_evb/audio_provider.cc

osx tflm, micro_speech

https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/osx/audio_provider.cc

MT_MicroSpeech-Tak_Ni-, Cypress

https://github.com/maryan167/MT_MicroSpeech-Tak_Ni-

语音信号增强技术及其应用

search baidupan

Speech Command Recognition with torchaudio

https://pytorch.org/tutorials/intermediate/speech_command_recognition_with_torchaudio.html

汇编语言程序设计：基于ARM体系结构(第3版)

search baidupan, book
search baidupan, 20160414hbarm.zip
北京航空航天大学出版社
http://service.buaapress.com.cn//mzs/file/index/c/d/id/8

X-CUBE-AI

AI expansion pack for STM32CubeMX

• https://my.st.com/content/my_st_com/en/products/embedded-software/mcu-mpu-embedded-software/stm32-embedded-software/stm32cube-expansion-packages/x-cube-ai.license=1607411616870.product=X-CUBE-AI-Win.version=5.2.0.html#documentation
• Getting started with X-CUBE-AI Expansion Package for Artificial Intelligence (AI)
  https://my.st.com/resource/en/user_manual/dm00570145-getting-started-with-xcubeai-expansion-package-for-artificial-intelligence-ai-stmicroelectronics.pdf
• HAR-CNN-Keras
  https://github.com/Shahnawax/HAR-CNN-Keras
• ConvNetJS MNIST demo
  https://cs.stanford.edu/people/karpathy/convnetjs/demo/mnist.html
  https://cs.stanford.edu/people/karpathy/convnetjs/
• Lasagne
  https://lasagne.readthedocs.io/en/latest/
• Caffe
  http://caffe.berkeleyvision.org
• ONNX
  https://onnx.ai
• Keras
  https://keras.io

about X-CUBE-AI

• 基于stm32f407cube ai实例
  https://blog.csdn.net/qq_39505991/article/details/95176720
• 嵌入式MCU也能跑AI？STM32 Cube.AI工具包使用初探
  https://zhuanlan.zhihu.com/p/64353677
• STM32CubeMx wiht AI 初体验
  https://blog.csdn.net/weixin_37598106/article/details/107105068
  https://github.com/Lebhoryi/Edge_AI/tree/master/Project1-linear
• 基于STM32F767ZI AI 应用工程创建
  https://bbs.21ic.com/icview-2611188-1-2.html
• search MX_X_CUBE_AI_Process
  https://github.com/dasmehdix/stm32f303_simpleCustomNN/blob/master/Core/Src/main.c
• search MX_X_CUBE_AI_Process har
  https://github.com/search?q=MX_X_CUBE_AI_Process+har&type=code
  https://github.com/wiyarun/stm32l476_hello_ai
  https://github.com/c106czs/HAR_STM32L475VG-Project
• CUBEMX-AI-STM32F4-DISCO
  https://github.com/TrevorHeyl/CUBEMX-AI-STM32F4-DISCO

移动深度学习, mobile-deep-learning, Paddle-Lite

http://www.broadview.com.cn/book/5147
search baidupan, paddle-lite代码.zip
https://github.com/PaddlePaddle/Paddle-Lite
https://github.com/allonli/mobile-deep-learning
https://github.com/DeepScale/SqueezeNet
https://github.com/PaddlePaddle/Paddle-Lite/blob/develop/mobile/src/operators/math/winograd/winograd_transform_f6k3.cpp
mobile-deep-learning (MDL) -> Paddle-Mobile -> Paddle-Lite
https://github.com/xiebaiyuan/paddle-mobile
https://paddle-lite.readthedocs.io/zh/latest/demo_guides/opencl.html