AMADEUS: a scalable HMM-based audio information retrieval system
Authors:
- 1 January 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 731-734
Abstract
The new transmission and storage technologies now avail- able have put together a vast amount of digital audio. All this audio is ready and easy to transfer but it might be use- less with a clear knowledge of its content as metadata at- tached to it. This knowledge can be manually added but this is not feasible for millions of on-line files. In this paper we present a method to automatically derive acoustic infor- mation about audio files and a technology to classify and retrieve audio examples.Keywords
This publication has 7 references indexed in Scilit:
- Visualization of metre and other rhythm features2004
- Real-time discrimination of broadcast speech/music2002
- Construction and evaluation of a robust multifeature speech/music discriminator2002
- An overview of audio information retrievalMultimedia Systems, 1999
- Markov Chains1999
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- Error bounds for convolutional codes and an asymptotically optimum decoding algorithmIEEE Transactions on Information Theory, 1967