MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization.
Yi Han Victoria ChuaHexin LiuLeibny Paola GarcíaFei Ting WoonJinyi WongXiangyu ZhangSanjeev KhudanpurAndy W. H. KhongJustin DauwelsSuzy J. StylesPublished in: INTERSPEECH (2023)
Keyphrases
- language identification
- speaker identification
- speech corpus
- automatic speech recognition
- broadcast news
- speech recognition
- speech synthesis
- spoken document retrieval
- speech signal
- english text
- hidden markov models
- noisy environments
- document images
- indian languages
- pattern recognition
- speaker verification
- feature extraction
- gaussian mixture model
- language model
- video sequences