Skip to content

Latest commit

 

History

History
37 lines (22 loc) · 1.41 KB

README.md

File metadata and controls

37 lines (22 loc) · 1.41 KB

cs160-audio-examples

(mostly) Android audio processing examples for UC Berkeley CS160, Spring 2014.

More details for working with audio in cs160 can be found on our course wiki: http://husk.eecs.berkeley.edu/courses/cs160-sp14/index.php/Sound_Programming

Speech to Text

Requires that Google Voice Search is installed on the device or emulator. To install this on an emulator (not Genymotion) you can grab the apk for Google Voice search here: https://docs.google.com/file/d/0B5rZBNIQG5NWZHV0dWdGVmkzRG8/edit

Click the button and then begin speaking. The text box below will be update after you stop speaking.

Text to Speech

Type your text in the edit box and then press the Speak button.

Speech to Phonemes

This is not for Android, but could run on a server that your app could access.

There's no code to list here, but here are detailed instructions on how to get Speech-to-phoneme recognition set up using Sphinx: http://cmusphinx.sourceforge.net/wiki/phonemerecognition

Detecting pre-recorded audio segments

A la Shazam/SoundHound, but could be applied to detecting any fixed sounds.

See music fingerprinting code:

More information about the subject: http://en.wikipedia.org/wiki/Acoustic_fingerprint