Phoneme-Level Text to Audio Synchronization on Speech Signals with Background Music.
Agnès PedoneJuan José BurredSimon MallerPierre LeveauPublished in: INTERSPEECH (2011)
Keyphrases
- speech signal
- music score
- speech recognition
- automatic speech recognition
- automatic speech recognition systems
- background noise
- speaker identification
- audio signals
- acoustic features
- audio content
- broadcast news
- text graphics
- music information retrieval
- information retrieval
- hidden markov models
- audio signal
- music scores
- music retrieval
- speech sounds
- spectral analysis
- noisy environments
- non stationary
- sound signals
- speech music discrimination
- vocal tract
- audio features
- multimedia
- mel frequency cepstral coefficients
- speech enhancement
- fundamental frequency
- speech synthesis
- text to speech
- visual data
- text data
- visual information
- low level