Paper Info
Title
Audio textures: theory and applications
Abstract
In this paper, we introduce a new audio medium, called audio texture, as a means of synthesizing long audio stream according to a given short example audio clip. The example clip is first analyzed to extract its basic building patterns. An audio stream of arbitrary length is then synthesized using a sequence of extracted building patterns. The patterns can be varied in the synthesis process to add variations to the generated sound to avoid simple repetition. Audio textures are useful in applications such as background music, lullabies, game music, and screen saver sounds. We also extend this idea to audio texture restoration, or constrained audio texture synthesis for restoring the missing part in an audio clip. It is also useful in many applications such as error concealment for audio/music delivery with packets loss on the Internet. Novel methods are proposed for unconstrained and constrained audio texture synthesis. Preliminary results are provided for evaluation.
Year
DOI
Venue
2004
10.1109/TSA.2003.819947
IEEE Transactions on Speech and Audio Processing
Keywords
Field
DocType
music delivery,audio clip,audio texture restoration,audio medium,extracted building patterns,lullabies,signal restoration,long audio stream synthesizing,game music,audio delivery,screen saver sounds,audio textures,packet loss,internet,background music,error concealment,audio signal processing,audio texture synthesis,constrained audio texture,network synthesis,pattern analysis,image restoration,helium,image texture
Computer vision,Speech coding,Computer science,Audio mining,Network packet,Delay,Speech recognition,Sound quality,Digital audio,Artificial intelligence,Audio signal processing,Texture synthesis
Journal
Volume
Issue
ISSN
12
2
1063-6676
Citations 
PageRank 
References 
24
1.90
14
Authors
3
Name
Order
Citations
PageRank
Lie LU11840134.64
Liu Wenyin22531215.13
Hong-Jiang ZHANG3173781393.22