Speech/Music Discrimination in Audio Podcast Using Structural Segmentation and Timbre Recognition.
Mathieu BarthetSteven HargreavesMark B. SandlerPublished in: CMMR (2010)
Keyphrases
- speech music discrimination
- speech corpus
- numeral strings
- image parsing
- recognition rate
- segmentation algorithm
- gaussian mixture model
- level set
- object recognition
- image segmentation
- segmentation method
- automatic speech recognition
- structural analysis
- pattern recognition
- multimedia
- music information retrieval
- speech synthesis
- medical images
- acoustic features
- automatic transcription
- information retrieval
- recognition algorithm
- feature selection
- document analysis
- character recognition
- hidden markov models
- edge detection