Speech Recognition in Mixed Sound of Speech and Music Based on Vector Quantization and Non-Negative Matrix Factorization.
Shoichi NakanoKazumasa YamamotoSeiichi NakagawaPublished in: INTERSPEECH (2011)
Keyphrases
- speech recognition
- vector quantization
- negative matrix factorization
- audio signal
- speech signal
- speaker identification
- acoustic features
- automatic speech recognition
- image compression
- speech synthesis
- speech recognizer
- hidden markov models
- document clustering
- principal component analysis
- speech recognition systems
- language model
- matrix factorization
- speaker recognition
- sparse representation
- sound source
- music information retrieval
- noisy environments
- pattern recognition
- speaker independent
- audio features
- face recognition
- information retrieval
- maximum likelihood
- information retrieval systems
- feature space