A lightweight on-the-fly capitalization system for automatic speech recognition

International Conference Recent Advances in Natural Language Processing, RANLP

Volumn 2007-January, Issue , 2007, Pages 52-57

  Batista, Fernando ^a,b   Mamede, Nuno ^a,c   Caseiro, Diamantino ^a,c   Trancoso, Isabel ^a,c  

^a INESC ID   (Portugal)

^b INSTITUTO UNIVERSITÁRIO DE LISBOA ISCTE IUL   (Portugal)

^c INSTITUTO SUPERIOR TÉCNICO   (Portugal)

Author keywords

Capitalization; Language Models; Maximum entropy; Rich transcription; Truecasing; Weighted finite state transducers

Indexed keywords

COMPUTATIONAL LINGUISTICS; ENTROPY; NEWSPRINT; SPEECH COMMUNICATION; SPEECH TRANSMISSION; TRANSCRIPTION; TRANSDUCERS;

AUTOMATIC SPEECH RECOGNITION; CAPITALIZATION; FINITE STATE TRANSDUCERS; LANGUAGE MODEL; MAXIMUM ENTROPY MODELS; MAXIMUM-ENTROPY; RICH TRANSCRIPTIONS; SPEECH TRANSCRIPTIONS; TRUECASING; WEIGHTED FINITE-STATE TRANSDUCERS;

SPEECH RECOGNITION;

EID: 84959056043     PISSN: 13138502     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. C. Chelba and A. Acero. Adaptation of maximum entropy capitalizer: Little data can help a lot. EMNLP'04, 2004.
2. H. Daumé III. Notes on CG and LM-BFGS optimization of logistic regression. Implementation available at http://hal3.name/megam/, August 2004.
3. J.-H. Kim and P. C. Woodland. Automatic capitalisation generation for speech input. Computer Speech & Language, 18(1):67-90, 2004.
4. J. Makhoul, F. Kubala, R. Schwartz, and R. Weischedel. Performance measures for information extraction. In Proceedings of DARPA Broadcast News Workshop, Herndon, VA, February 1999.
5. A. Mikheev. Periods, capitalized words, etc. Computational Linguistics, 28(3):289-318, 2002.
6. A. Stolcke. SRILM - An extensible language modeling toolkit. In Proceedings of International Conference on Spoken Language Processing, volume 2, pages 901-904, Denver, CO, 2002.
7. A. Stolcke and E. Shriberg. Automatic linguistic segmentation of conversational speech. In Proc. ICSLP'96, volume 2, pages 1005-1008, Philadelphia, PA, 1996.