完整後設資料紀錄
DC 欄位語言
dc.contributor.authorWang, Yih-Ruen_US
dc.contributor.authorLu, Bo-Xuanen_US
dc.contributor.authorLiao, Yuan-Fuen_US
dc.contributor.authorChen, Sin-Horngen_US
dc.date.accessioned2014-12-08T15:24:37Z-
dc.date.available2014-12-08T15:24:37Z-
dc.date.issued2006en_US
dc.identifier.isbn978-3-540-49665-6en_US
dc.identifier.issn0302-9743en_US
dc.identifier.urihttp://hdl.handle.net/11536/17091-
dc.description.abstractIn this paper, the performance of the pitch detection algorithm in ETSI ES-202-212 XAFE standard is evaluated on. a Mandarin digit string recognition task. Experimental results showed that the performance of the pitch detection algorithm degraded seriously when the SNR of speech signal was lower than 10dB. This makes the recognizer using pitch information perform inferior to the original recognizer without using pitch information in low SNR environments. A modification of the pitch detection algorithm is therefore proposed to improve the performance of pitch detection in low SNR environments. The recognition performance can be improved for most SNR levels by integrating the recognizers with and without using pitch information. Overall recognition rates of 82.1% and 86.8% were achieved for clean and multi-condition training cases.en_US
dc.language.isoen_USen_US
dc.subjectdistributed speech recognitionen_US
dc.subjectExtended Advanced Front-enden_US
dc.subjecttonal language speech recognitionen_US
dc.titleDistributed speech recognition of mandarin digits stringen_US
dc.typeProceedings Paperen_US
dc.identifier.journalChinese Spoken Language Processing, Proceedingsen_US
dc.citation.volume4274en_US
dc.citation.spage370en_US
dc.citation.epage379en_US
dc.contributor.department交大名義發表zh_TW
dc.contributor.departmentNational Chiao Tung Universityen_US
dc.identifier.wosnumberWOS:000244824800035-
顯示於類別:會議論文