smartcore

This repo contains the different libraries and scripts used for the core functionalities of the SmartMeet project.

Beamforming

Direction of Arrival

Implements the SRP-PHAT and the GCC-PHAT

https://github.com/matrix-io/matrix-creator-hal/tree/125b75a4256db56533a9227b5c80cbe2c96b11ab/cpp/driver

https://github.com/Roboy/roboy_audio

https://github.com/solens/Matrix/tree/1dacb839f46a642e89b7f5eec5b7da9ef732ec23

https://github.com/bergos/voice-engine-js-respeaker-4mic-pi

https://github.com/xiongyihui/tdoa

https://github.com/LeeTaewoo/TL-SSC_SRP-PHAT

https://github.com/0x00-pl/srp_phat

https://github.com/wangwei2009/DOA

https://github.com/morriswmz/doa-tools

https://github.com/EttusResearch/gr-doa

https://github.com/bouabidiMezni/Direction-Of-Arrival-Estimation

https://github.com/LCAV/FRIDA

https://github.com/msamsami/doa-estimation-music

https://github.com/SqrtPapere/DOA-Estimation

https://github.com/rejuvyesh/doa-est-info-theory

https://github.com/lucasuf/SpeakerTracker

https://github.com/jopedroliveira/speech_recog_uc

https://github.com/dengjunquan/DoA-Estimation-MUSIC-ESPRIT

Datasets

http://deeplearning.net/datasets/

http://www.voxforge.org/

http://www.speech.cs.cmu.edu/databases/micndarray/index.html

https://team.inria.fr/perception/nard/

https://www.kaggle.com/c/tensorflow-speech-recognition-challenge/data

http://www.cs.tut.fi/~heittolt/datasets

https://datashare.is.ed.ac.uk/download/DS_10283_2791.zip

https://catalog.ldc.upenn.edu/LDC2000S87

https://research.google.com/audioset/dataset/speech.html

https://github.com/dingzeyuli/SpEAR-speech-database

https://ecs.utdallas.edu/loizou/speech/noizeus/

https://ccrma.stanford.edu/~gautham/Site/daps.html

http://www.openslr.org/resources.php

https://datashare.is.ed.ac.uk/handle/10283/2826

http://www.openslr.org/17/

https://sisec.inria.fr/sisec-2015/2015-two-channel-mixtures-of-speech-and-real-world-background-noise/

https://arxiv.org/abs/1808.00606

Cocktail Recording

http://vis.uky.edu/distributed-audio-lab/experimental-data-archive/cocktail-party-recordings/

pip install python_speech_features

*** THIS IS SO GOOD *** https://looking-to-listen.github.io/