Corpus Creation and Automatic Alignment of Historical Dutch Dialect Speech.
Martijn BentumEric SandersAntal P. J. van den BoschDouwe ZeldenrustHenk van den HeuvelPublished in: LREC/COLING (2024)
Keyphrases
- semi automatic
- speech recognition
- speech signal
- speech music discrimination
- lexical features
- spontaneous speech
- spoken language
- spanish language
- manually annotated
- sentence level
- neural network
- hand crafted
- open domain
- automatic speech recognition
- parallel texts
- historical data
- endpoint detection
- artificial intelligence