Untrained Forced Alignment of Transcriptions and Audio for Language Documentation Corpora using WebMAUS.
Jan StrunkFlorian SchielFrank SeifartPublished in: LREC (2014)
Keyphrases
- broadcast news
- natural language
- human language
- parallel corpus
- multimedia
- comparable corpora
- language learning
- linguistic resources
- automatic transcription
- visual data
- audio visual
- language processing
- text to speech
- visual information
- programming language
- dynamic time warping
- word alignment
- multi modal
- xml documents
- spoken documents
- information retrieval