Home Catalogue search

eng

Refine your search:

Search in the Catalogues and Directories






	Sort by
Simple Search

Page: 1 2 3 4

Hits 1 – 20 of 62

1	Quantifying the value of pronunciation lexicons for keyword search in low resource languages
	Guoguo Chen; Sanjeev Khudanpur; Daniel Povey...
	In: http://www.clsp.jhu.edu/%7Eguoguo/papers/icassp2013_lexicon_value.pdf (2013)
	BASE
	Show details

2	Sequential system combination for machine translation of speech
	Damianos Karakos; Sanjeev Khudanpur
	In: http://www.clsp.jhu.edu/~damianos/slt08_mt_combination.pdf (2008)
	BASE
	Show details

3	Unsupervised Learning of Acoustic Subword Units
	Balakrishnan Varadarajan; Sanjeev Khudanpur; Emmanuel Dupoux
	In: http://www.clsp.jhu.edu/~balakris/pubs/acl08superbrief.pdf (2008)
	BASE
	Show details

4	Unsupervised learning of acoustic sub-word units
	Balakrishnan Varadarajan; Sanjeev Khudanpur; Emmanuel Dupoux
	In: http://aclweb.org/anthology-new/P/P08/P08-2042.pdf (2008)
	BASE
	Show details

5	Lexical triggers and latent semantic analysis for crosslingual language model adaptation
	Woosung Kim; Sanjeev Khudanpur
	In: http://www.clsp.jhu.edu/~woosung/pdf/talip04.pdf (2004)
	BASE
	Show details

6	Contemporaneous Text as Side-Information in Statistical Language Modeling
	Sanjeev Khudanpur; Woosung Kim
	In: http://www.clsp.jhu.edu/~woosung/pdf/csl04.pdf (2004)
	BASE
	Show details

7	Cross-lingual latent semantic analysis for LM
	Woosung Kim; Sanjeev Khudanpur
	In: http://www.clsp.jhu.edu/~woosung/pdf/icassp04.pdf (2004)
	BASE
	Show details

8	Language Model Adaptation Using Cross-Lingual Information
	Woosung Kim; Sanjeev Khudanpur
	In: http://www.clsp.jhu.edu/~woosung/pdf/euro03.pdf (2003)
	BASE
	Show details

9	Cross-Lingual Lexical Triggers in Statistical Language Modeling
	Woosung Kim Woosung; Sanjeev Khudanpur
	In: http://acl.ldc.upenn.edu/W/W03/W03-1003.pdf (2003)
	BASE
	Show details

10	Cross-Lingual Lexical Triggers in Statistical Language Modeling
	Woosung Kim; Sanjeev Khudanpur
	In: http://www.clsp.jhu.edu/~woosung/pdf/emnlp03.pdf (2003)
	BASE
	Show details

11	Contemporaneous Text as Side-Information in Statistical Language Modeling
	Sanjeev Khudanpur; Woosung Kim
	In: http://www.clsp.jhu.edu/~sanjeev/Pubs/CSL2003b.pdf (2003)
	BASE
	Show details

12	Making miracles: Interactive translingual search for cebuano and hindi
	Daqing He; Douglas W. Oard; Jianqiang Wang...
	In: http://www.sis.pitt.edu/~daqing/docs/talip-final.pdf (2003)
	BASE
	Show details

13	Maximum Entropy Language Modeling with Non-Local and Syntactic Dependencies
	Jun Wu; Advisor Dr. Sanjeev Khudanpur
	In: http://www.cs.jhu.edu/~junwu/gbo.ps (2002)
	BASE
	Show details

14	Using Cross-Language Cues For Story-Specific Language Modeling
	Sanjeev Khudanpur; Woosung Kim
	In: http://www.clsp.jhu.edu/~woosung/pdf/icslp02.pdf (2002)
	BASE
	Show details

15	Smoothing Issues in the Structured Language Model
	Woosung Kim; Sanjeev Khudanpur; Jun Wu
	In: http://cs.jhu.edu/~junwu/eurospeech01.ps (2001)
	BASE
	Show details

16	Smoothing Issues in the Structured Language Mode
	Woosung Kim; Sanjeev Khudanpur; Jun Wu
	In: http://www.clsp.jhu.edu/~woosung/pdf/euro01.pdf (2001)
	BASE
	Show details

17	Pronunciation modeling by sharing Gaussian densities across phonetic models,” Computer Speech and Language
	Murat Saraclar; Harriet Nock; Sanjeev Khudanpur
	In: http://busim.ee.boun.edu.tr/~speech/publications/Speech_Recognition/eurospeech99.pdf (2000)
	Abstract: Conversational speech exhibits considerable pronunciation variability, which has been shown to have a detrimental effect on the accuracy of automatic speech recognition. There have been many attempts to model pronunciation variation, including the use of decision-trees to generate alternate word pronunciations from phonemic baseforms. Use of such pronunciation models during recognition is known to improve accuracy. This paper describes the use of such pronunciation models during acoustic model training. Subtle difficulties in the straightforward use of alternatives to canonical pronunciations are first illustrated: it is shown that simply improving the accuracy of the phonetic transcription used for acoustic model training is of little benefit. Analysis of this paradox leads to a new method of accommodating nonstandard pronunciations: rather than allowing a phoneme in the canonical pronunciation to be realized as one of a few distinct alternate phones predicted by the pronunciation model, the HMM states of the phoneme’s model are instead allowed to share Gaussian mixture components with the HMM states of the model of the alternate realization. Qualitatively, this amounts to making a soft decision about which surface-form is realized. Quantitative experiments on the Switchboard corpus show that this method improves accuracy by 1.7 % (absolute). 1.
	URL: http://busim.ee.boun.edu.tr/~speech/publications/Speech_Recognition/eurospeech99.pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.6147
	BASE
	Hide details

18	Pronunciation modeling by sharing Gaussian densities across phonetic models
	Murat Saraçlar; Harriet Nock; Sanjeev Khudanpur
	In: ftp://svr-ftp.eng.cam.ac.uk/pub/reports/nock_csl00.pdf (2000)
	BASE
	Show details

19	Mandarin-English Information (MEI): Investigating Translingual Speech Retrieval
	Helen Meng; Berlin Chen; Erika Grams...
	In: http://www.se.cuhk.edu.hk/PEOPLE/hmmeng/MEI_Final_Report2000.pdf (2000)
	BASE
	Show details

20	Pronunciation modeling by sharing Gaussian densities across phonetic models
	Murat Saraclar; Harriet Nock; Sanjeev Khudanpur
	In: http://mi.eng.cam.ac.uk/reports/svr-ftp/auto-pdf/nock_euro99.pdf (2000)
	BASE
	Show details

Page: 1 2 3 4

© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern