Automatic Recognition of Sound Categories from Their Vocal Imitation Using Audio Primitives Automatically Found by SI-PLCA and HMM.
Enrico MarchettoGeoffroy PeetersPublished in: CMMR (2017)
Keyphrases
- automatic recognition
- hidden markov models
- acoustic features
- audio signal
- emotion recognition
- multi stream
- speech signal
- low level
- high level
- character segmentation
- automatically generated
- audio visual
- multimedia
- automatic speech recognition
- signal processing
- reinforcement learning
- multi modal
- decision making
- handwritten word recognition
- audio content
- classify documents
- automatic speech recognition systems