Supervised and semi-supervised suppression of background music in monaural speech recordings.
Felix WeningerJordi FeliuBjörn W. SchullerPublished in: ICASSP (2012)
Keyphrases
- audio recordings
- supervised and semi supervised
- acoustic features
- music information retrieval
- spontaneous speech
- audio visual
- audio signals
- audio features
- semi supervised
- speech music discrimination
- speech recognition
- multi label
- automatic speech recognition
- locally weighted
- speech signal
- unlabeled data
- hidden markov models
- machine learning
- prediction accuracy
- text categorization
- supervised learning
- probabilistic model
- pairwise
- e learning
- learning algorithm