Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Zochová, Petra | |
| dc.contributor.author | Radová, Vlasta | |
| dc.date.accessioned | 2015-12-09T10:46:02Z | |
| dc.date.available | 2015-12-09T10:46:02Z | |
| dc.date.issued | 2004 | |
| dc.identifier.citation | ZOCHOVÁ, Petra; RADOVÁ, Vlasta. A method for speaker-based segmentation of audio signals. In: Speech processing: 14th Czech-German workshop. Prague: Academy of sciences of the Czech Republic, 2004, p. 109 - 112. ISBN 80-86269-10-8. | en |
| dc.identifier.isbn | 80-86269-10-8 | |
| dc.identifier.uri | http://www.kky.zcu.cz/cs/publications/ZochovaP_2004_Amethodfor | |
| dc.identifier.uri | http://hdl.handle.net/11025/16939 | |
| dc.description.abstract | Článek se zabývá úlohou segmentace nahrávky podle řečníka. Cílem úlohy je vydělit z nahrávky úseky, z nichž každý obsahuje co nejdelší promluvu vyslovenou pouze jedniným řečníkem. Metoda popsaná v tomto článku nepotřebuje žádné apriorní znalosti o řečníkovi ani o charakteristikách řečového signálu. | cs |
| dc.format | 4 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.language.iso | en | en |
| dc.publisher | Academy of sciences of the Czech Republic | en |
| dc.rights | © Petra Zochová - Vlasta Radová | cs |
| dc.subject | segmentace promluvy podle řečníka | cs |
| dc.subject | bayesovské informační kritérium | cs |
| dc.subject | detekce změny řečníka | cs |
| dc.title | A method for speaker-based segmentation of audio signals | en |
| dc.title.alternative | Metoda pro segmentaci audio signálů podle řečníka | cs |
| dc.type | článek | cs |
| dc.type | article | en |
| dc.rights.access | openAccess | en |
| dc.type.version | publishedVersion | en |
| dc.description.abstract-translated | The paper deals with the problem of speaker-based segmentation. The goal of this task is to extract homogeneous segments containing the longest possible utterances produced by a single speaker. In the method presented here, no assumption is made about prior knowledge of the speaker or speech signal characteristics (there is no speaker model, no speech model, even the number of speakers in the recording is not known). | en |
| dc.subject.translated | speaker-based segmentation | en |
| dc.subject.translated | bayesian information criterion | en |
| dc.subject.translated | detection of speaker turn | en |
| dc.type.status | Peer-reviewed | en |
| Appears in Collections: | Články / Articles (KKY) | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ZochovaP_2004_Amethodfor.pdf | Plný text | 45,81 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/16939Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.