The NUS sung and spoken lyrics corpus: A quantitative comparison of singing and speech.
Zhiyan DuanHaotian FangBo LiKhe Chai SimYe WangPublished in: APSIPA (2013)
Keyphrases
- music information retrieval
- audio features
- acoustic features
- speech recognition
- automatic speech recognition
- spontaneous speech
- spoken language
- audio recordings
- conversational speech
- broadcast news
- audio visual
- music retrieval
- speech signal
- lexical features
- music emotion classification
- text data
- audio signals
- emotion classification
- qualitative and quantitative
- spoken words
- speaker identification
- information retrieval systems
- digital music
- speech recognizer
- feature set
- visual features
- spoken documents
- speech retrieval
- human machine interaction
- speech synthesis
- genre classification
- audio signal
- high level
- dialogue system
- semantic information
- low level