A Pitch-Based Rapid Speech Segmentation for Speaker Indexing.
Min YangYingchun YangZhaohui WuPublished in: ISM (2005)
Keyphrases
- speech recognition
- acoustic features
- speaker adaptation
- automatic speech recognition
- speaker recognition
- audio visual
- speaker verification
- image segmentation
- segmentation method
- multiscale
- automatic speech recognition systems
- speech signal
- vocal tract
- segmentation algorithm
- level set
- information retrieval
- segmentation accuracy
- prosodic features
- image analysis
- region growing
- maximum likelihood
- mel frequency cepstral coefficients
- speaker diarization
- speaker identification
- speech synthesis
- content based retrieval
- object segmentation
- formant frequencies
- speech recognizer
- energy function
- spoken language
- database
- fully unsupervised
- multi modal
- audio features
- music information retrieval
- medical images
- speaker dependent
- audio stream
- speech segments
- indexing techniques