Lattice extension and rescoring based approaches for LVCSR of Turkish

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn 2, Issue , 2006, Pages 1025-1028

  Arisoy, Ebru ^a   Saraçlar, Murat ^a  

^a BOGAZICI UNIVERSITY   (Turkey)

Author keywords

Agglutinative languages; Language modelling; Speech recognition; Vocabulary extension

Indexed keywords

COMPUTATIONAL LINGUISTICS; CONTINUOUS SPEECH RECOGNITION; DEEP NEURAL NETWORKS; ERRORS; MODELING LANGUAGES; SPEECH PROCESSING; VOCABULARY CONTROL;

AGGLUTINATIVE LANGUAGE; BASELINE MODELS; LANGUAGE MODELLING; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LATTICE EXTENSION; ROBUST ESTIMATE; VOCABULARY EXTENSION; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 37849020279     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Oh-Wook Kwon and Jun Park, "Korean large vocabulary continuous speech recognition with morpheme-based recognition units," Speech Communication, vol. 39, pp. 287-300, 2003.
2. Vesa Siivola, Teemu Hirsimäki, Mathias Creutz, and Mikko Kurimo, "Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner," in Proc. EUROSPEECH 2003, Geneva, Switzerland, 2003, pp. 2293-2296.
3. Jan Kneissler and Dietrich Klakow, "Speech recognition for huge vocabularies by using optimized sub-word units," in Proc. EUROSPEECH 2001, Aalborg, Denmark, 2001, pp. 69-73.
4. Kenan Carki, Petra Geutner, and Tanja Schultz, "Turkish LVCSR: Towards better speech recognition for agglutinative languages," in Proc. ICASSP 2000, Istanbul, Turkey, 2000, vol. 3, pp. 1563-1566.
5. Erhan Mengusoglu and Olivier Deroo, "Turkish LVCSR: Database preparation and language modeling for an agglutinative language," in Proc. ICASSP 2001, Student Forum, Salt-Lake City, 2001.
6. Ebru Arisoy and Levent M. Arslan, "Turkish dictation system for broadcast news applications," in Proc. EUSIPCO 2005, Antalya, Turkey, 2005.
7. Hakan Erdogan, Osman Buyuk, and Kemal Oflazer, "Incorporating language constraints in sub-word based speech recognition," in Proc. ASRU 2005, Cancun, Mexico, 2005.
8. Kadri Hacioglu, Brian Pellom, Tolga Ciloglu, Ozlem Ozturk, Mikko Kurimo, and Mathias Creutz, "On lexicon creation for Turkish LVCSR," in Proc. EUROSPEECH 2003, Geneva, Switzerland, 2003, pp. 1165-1168.
9. Mikko Kurimo, Antti Puurula, Ebru Arisoy, Vesa Siivola, Teemu Hirsimäki, Janne Pylkkönen, Tanel Alumäe, and Murat Saraçlar, "Unlimited vocabulary speech recognition for agglutinative languages," in Proc. HLT-NAACL 2006, New York, USA, 2006.
10. Petra Geutner, Michael Finke, Peter Scheytt, Alex Waibel, and Howard Wactlar, "Transcribing multilingual broadcast news using hypothesis driven lexical adaptation," in DARPA Broadcast News Workshop, Herndon, USA, 1998.
11. Mathias Creutz and Krista Lagus, "Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.0. Publications in Computer and Information Science, Report A81, Helsinki University of Technology, March.," 2005.
12. Petra Geutner, Michael Finke, and Alex Waibel, "Phonetic-distance- based hypothesis driven lexical adaptation for transcribing multilingual broadcast news," in ICSLP 1998, Sydney, Australia, 1998.
13. Andreas Stolcke, "Srilm - An extensible language modeling toolkit," in Proc. ICSLP 2002, Denver, 2002, vol. 2, pp. 901-904.
14. Mehryar Mohri and Michael D. Riley, "Dcd library, speech recognition decoder library, AT&T Labs - Research. http://www.research.att.com/sw/ tools/dcd/," 2002.