RSL2019: A Realistic Speech Localization Corpus.
Rohan SheelvantBidisha SharmaMaulik C. MadhaviRohan Kumar DasS. R. M. PrasannaHaizhou LiPublished in: O-COCOSDA (2019)
Keyphrases
- spontaneous speech
- lexical features
- speech recognition
- real life
- facial animation
- manually annotated
- endpoint detection
- speech signal
- object localization
- audio visual
- conversational speech
- spoken language
- real world
- recognition engine
- test set
- localization algorithm
- language acquisition
- broadcast news
- spanish language
- speech synthesis
- speaker recognition
- text corpus
- speech processing
- supervised machine learning
- human machine interaction
- automatic speech recognition
- natural language