Title: | Comparing and combining modeling techniques for sentence segmentation of spoken czech using textual and prosodic information |
Authors: | Kolář, Jáchym Liu, Yang |
Citation: | KOLÁŘ, Jáchym; LIU, Yang. Comparing and combining modeling techniques for sentence segmentation of spoken czech using textual and prosodic information. In: Proceeding of conference Speech prosody 2010, 11th-14th May 2010, Chicago, USA. Chicago: University of Illionois, 2010, p. [1-4]. |
Issue Date: | 2010 |
Publisher: | University of Illionois |
Document type: | článek article |
URI: | http://www.kky.zcu.cz/cs/publications/JachymKolar_2010_Comparingand http://hdl.handle.net/11025/17173 |
Keywords: | segmentace vět;prozodie;HMM;maximální entropie;posílení |
Keywords in different language: | sentence segmentation;prosody;HMM;maximum entropy;boosting |
Abstract in different language: | This paper deals with automatic sentence boundary detection in spoken Czech using both textual and prosodic information. This task is important to make automatic speech recognition (ASR) output more readable and easier for downstream language processing modules. We compare and combine three statistical models – hidden Markov model, maximum entropy, and adaptive boosting. We evaluate these methods on two Czech corpora, broadcast news and broadcast conversations, using both manual and ASR transcripts. Our results show that superior results are achieved when all the three models are combined via posterior probability interpolation, and that there is substantial difference among the three methods when using different knowledge sources, as well as in different genres. Feature analysis also reveals significant differences in prosodic feature usage patterns between the two genres. |
Rights: | © Jáchym Kolář - Yang Liu |
Appears in Collections: | Články / Articles (KKY) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
JachymKolar_2010_Comparingand.pdf | Plný text | 64,59 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/17173
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.