Using automatic speech processing to analyze fundamental frequency of child-directed speech stored in a very large audio corpus.
Paul De PalmaMark VanDamPublished in: IFSA-SCIS (2017)
Keyphrases
- speech processing
- speech signal
- speaker identification
- fundamental frequency
- speech recognition
- spoken dialog
- signal processing
- natural language processing
- multimedia systems
- english text
- automatic speech recognition
- artificial intelligence
- noisy environments
- non stationary
- pattern recognition
- machine learning
- variable length
- multi modal
- language identification
- language model
- acoustic features
- speech music discrimination
- gaussian mixture model
- computer vision