Toward Content-Based Audio Indexing and Retrieval and a New Speaker Discrimination Technique
Lonce Wyse and Stephen W. Smoliar, National University of Singapore
Several techniques for identifying segment transitions in an audio stream are discussed. Gross features are first identified that control more detailed and computationally expensive analysis down stream. Pitch is tracked using some basic streaming principles, and then used as one cue to speaker transitions. A novel speaker discrimination technique is described that makes segmentation decisions when a continuously updated model of the current speaker suddenly ceases to sufficiently account for the input data.
23.1 INTRODUCTION
Despite the multimedia hype, video and audio ...
Get Readings in Multimedia Computing and Networking now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
