Abstract | ||
---|---|---|
This work addresses lexical unit discovery for languages without (usable) written resources. Previous work has addressed this problem using entirely unsupervised methodologies. Our approach in contrast investigates the use of linguistic and speaker knowledge which are often available even if text resources are not. We create a framework that benefits from such resources, not assuming orthographic representations and avoiding generation of word-level transcriptions. We adapt a universal phone recognizer to the target language and use it to convert audio into a searchable phone string for lexical unit discovery via fuzzy sub-string matching. Linguistic knowledge is used to constrain phone recognition output and to constrain lexical unit discovery on the phone recognizer output. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/SLT.2016.7846246 | 2016 IEEE Spoken Language Technology Workshop (SLT) |
Keywords | Field | DocType |
lexical discovery,low resource languages,automatic speech recognition | USable,Data modeling,Transcription (linguistics),Pragmatics,Computer science,Lexical item,Fuzzy logic,Speech recognition,Phone,Artificial intelligence,Natural language processing | Conference |
ISSN | ISBN | Citations |
2639-5479 | 978-1-5090-4904-2 | 0 |
PageRank | References | Authors |
0.34 | 6 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chris Bartels | 1 | 0 | 0.34 |
Wen Wang | 2 | 106 | 11.93 |
Vikramjit Mitra | 3 | 299 | 24.83 |
Colleen Richey | 4 | 118 | 10.91 |
Andreas Kathol | 5 | 68 | 11.86 |
Dimitra Vergyri | 6 | 373 | 36.97 |
Harry Bratt | 7 | 153 | 15.12 |
Chiachi Hung | 8 | 0 | 0.34 |