@inproceedings{aef4b07caff240788b3d2b6124ffd1a4,
title = "Real time voice processing with audiovisual feedback: Toward autonomous agents with perfect pitch",
abstract = "We have implemented a real time front end for detecting voiced speech and estimating its fundamental frequency. The front end performs the signal processing for voice-driven agents that attend to the pitch contours of human speech and provide continuous audiovisual feedback. The algorithm we use for pitch tracking has several distinguishing features: it makes no use of FFTs or autocorrelation at the pitch period; it updates the pitch incrementally on a sample-by-sample basis; it avoids peak picking and does not require interpolation in time or frequency to obtain high resolution estimates; and it works reliably over a four octave range, in real time, without the need for postprocessing to produce smooth contours. The algorithm is based on two simple ideas in neural computation: the introduction of a purposeful nonlinearity, and the error signal of a least squares fit. The pitch tracker is used in two real time multimedia applications: a voice-to-MIDI player that synthesizes electronic music from vocalized melodies, and an audiovisual Karaoke machine with multimodal feedback. Both applications run on a laptop and display the user's pitch scrolling across the screen as he or she sings into the computer.",
author = "Saul, {Lawrence K.} and Lee, {Daniel D.} and Isbell, {Charles L.} and Yann LeCun",
year = "2003",
language = "English (US)",
isbn = "0262025507",
series = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
booktitle = "Advances in Neural Information Processing Systems 15 - Proceedings of the 2002 Conference, NIPS 2002",
note = "16th Annual Neural Information Processing Systems Conference, NIPS 2002 ; Conference date: 09-12-2002 Through 14-12-2002",
}