Cameron Macleod - Implementing a Sound Identifier in Python

Cameron Macleod - Implementing a Sound Identifier in Python
[EuroPython 2016]
[18 July 2016]
[Bilbao, Euskadi, Spain]
(https://ep2016.europython.eu//conference/talks/implementing-a-sound-identifier-in-python)

The talk will go over implementing a Shazam-style sound recogniser
using DSP techniques and some fantastic libraries. It will cover
implementation, challenges and further steps. The project is still a
work in progress and the code is [available on GitHub][1]. It was
inspired by the [Over-the-Air Audio Identification talk][2] at FOSDEM
2016.

[1]: https://github.com/notexactlyawe/abracadabra
[2]: https://fosdem.org/2016/schedule/event/audio_identification/

-----

The talk will go over the journey of implementing a Shazam-style sound
recogniser using DSP techniques and some fantastic libraries. It will
cover implementation, challenges and further steps. The project is
still a work in progress at the time of proposal and the code is
[available on GitHub][1]. It was inspired by the [Over-the-Air Audio
Identification talk][2] at FOSDEM 2016.

The basic structure of the project consists a classifier that
fingerprints audio and stores it in a searchable form and a recogniser
that fingerprints a smaller chunk of audio and then searches the
stored records to find the most suitable fit for it. The recogniser
will be exposed as an API to allow for different front-ends.

I will aim to introduce both the field of DSP and concepts behind
applications like Shazam in a simple easy-to-understand manner. The
audience will not need any prior experience in anything except Python.

[1]: https://github.com/notexactlyawe/abracadabra
[2]: https://fosdem.org/2016/schedule/event/audio_identification/