Abstract | ||
---|---|---|
We demonstrate an automatic speech recognition system for Polish continuous speech. As most of the progress in the field is done for English, a few layers of our system are different from popular approaches in this field. These elements of our system could be successfully ported to other languages which share some features with Polish: the speech contains a lot of high-frequency phones (fricatives and plosives) and is highly inflective and non-positional. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICSC.2010.16 | Semantic Computing |
Keywords | Field | DocType |
popular approach,high-frequency phone,automatic speech recognition system,wavelet analysis,polish continuous speech,semantics,wavelet transforms,high frequency,speech,natural language processing,hidden markov models,speech recognition,lattices,automatic speech recognition | Speech processing,Audio mining,Computer science,Speech recognition,Speaker recognition,Natural language processing,Artificial intelligence,Hidden Markov model,Linear predictive coding,Wavelet transform,Acoustic model,Wavelet | Conference |
ISSN | ISBN | Citations |
2325-6516 | 978-0-7695-4154-9 | 0 |
PageRank | References | Authors |
0.34 | 2 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mariusz Ziolko | 1 | 6 | 2.30 |
Jakub Galka | 2 | 44 | 7.47 |
Bartosz Ziólko | 3 | 46 | 15.76 |
Tomasz Jadczyk | 4 | 20 | 5.70 |
Dawid Skurzok | 5 | 12 | 2.89 |
Jan Wicijowski | 6 | 0 | 0.34 |