Semi-Supervised Single-Channel Speech-Music Separation for Automatic Speech Recognition.
Cemil DemirA. Taylan CemgilMurat SaraclarPublished in: INTERSPEECH (2011)
Keyphrases
- single channel
- automatic speech recognition
- sound source
- speech signal
- semi supervised
- audio features
- speech recognition
- acoustic features
- speech enhancement
- multi channel
- word error rate
- noisy environments
- speaker identification
- broadcast news
- conversational speech
- linear prediction
- vocal tract
- hidden markov models
- non stationary
- speech corpus
- pairwise
- spoken words
- spontaneous speech
- audio signal
- recognition errors
- speech sounds
- additive noise
- independent component analysis
- music information retrieval
- speech retrieval
- pattern recognition
- brain activity
- noisy images
- speech recognizer
- prior information
- frequency domain
- prior knowledge
- neural network