Investigating automatic decomposition for ASR in less represented languages

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

Volumn 1, Issue , 2006, Pages 285-288

  Pellegrini, Thomas ^a   Lamel, Lori ^a  

^a CNRS   (France)

Author keywords

Amharic; Less represented languages; Lexicon construction; Speech recognition; Word decomposition

Indexed keywords

DEEP NEURAL NETWORKS;

AMHARIC; AUTOMATIC DECOMPOSITION; HARRIS ALGORITHM; SUPERVISED TRAININGS; WELL-COVERED;

SPEECH RECOGNITION;

EID: 44949117449     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. W. Menzel S.T. Abate and B. Tafila, "An Amharic Speech Corpus for Large Vocabulary Continuous Speech Recognition," in Interspeech, Lisboa, 2005.
2. B. Gamback H. Seid, "A speaker independent continuous speech recognizer for Amharic," in Interspeech, Lisboa, 2005.
3. S. Eyassu and B.Gamback, "Classifying Amharic news texts using self-organizing Maps," in ACL05 Workshop on computational Approaches to Semitic Languages, Ann Arbor, 2005.
4. R. Schwartz and al., "Speech recognition in multiple languages and domains: The 2003 bbn/limsi ears system," in ICASSP, May 2004.
5. M. Adda-Decker, "A corpus-based decompounding algorithm for German lexical modeling in LVCSR,"in Eurospeech, Geneva, 2003.
6. Z. Harris, "From Phoneme to Morpheme," in Language 31, 1996, pp. 190-222.
7. T. Pellegrini and L. Lamel, "Experimental detection of vowel pronunciation variants in Amharic," in LREC, Genoa, 2006.
8. J.L. Gauvain, L. Lamel, and G. Adda, "The LIMSI Broadcast News Transcription System,"Speech Communication, vol. 37, pp. 89-108, 2002.