Audio indexing including frequency tracking of simultaneous multiple sources in speech and music.
Maxime Le CozJulien PinquierRégine André-ObrechtJulie MauclairPublished in: CBMI (2013)
Keyphrases
- multiple sources
- audio signals
- audio features
- speech music discrimination
- audio content
- audio recordings
- audio visual
- digital audio
- music information retrieval
- music retrieval
- audio stream
- multiple information sources
- audio signal
- speaker identification
- music score
- music genre classification
- acoustic features
- music scores
- cepstral features
- data sources
- audio visual speech recognition
- information retrieval
- content based video retrieval
- multi source
- broadcast news
- content based retrieval
- multimedia databases
- particle filter
- multimedia
- emotion recognition
- data from multiple sources
- multi stream
- database
- hidden markov models
- speech corpus
- automatic transcription
- speech recognition
- databases
- text to speech
- speech signal
- feature set
- database systems
- musical instruments
- audio files
- soccer video
- visual features
- content based music retrieval
- automatic music genre classification