Phonetic segmentation of singing voice using MIDI and parallel speech.
Minghui DongPaul Y. ChanLing CenHaizhou LiJason TeoPing Jen KuaPublished in: INTERSPEECH (2010)
Keyphrases
- speech sounds
- speech recognition
- text to speech
- image segmentation
- speech synthesis
- speech recognition errors
- emotion recognition
- segmentation method
- speech signal
- segmentation algorithm
- spoken document retrieval
- level set
- segmentation accuracy
- vocal tract
- automatic speech recognition
- region growing
- object segmentation
- medical images
- fundamental frequency
- edge detection
- spoken term detection
- acoustic features
- shape prior
- fully automatic
- energy function
- image analysis
- broadcast news
- parallel implementation
- prosodic features
- speech quality
- voice activity detection
- feature extraction