CREATING LARGE SUBWORD UNITS FOR SPEECH RECOGNTION

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 1191-1194

  Pfau, T ^a   Beham, M ^b   Reichl, W ^c   Ruske, G ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

^b Pc plus COMPUTING   (Germany)

^c LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH RECOGNITION;

AUTOMATIC DECOMPOSITION; DOMAIN SPECIFIC; HMM-BASED; LARGE-SIZED; MIXTURE COEFFICIENTS; QUALITY MEASURES; SINGLE WORDS; SPEECH RECOGNITION SYSTEMS; SPEECH RECOGNTION; SUBWORD UNITS;

SPEECH COMMUNICATION;

EID: 33645783460     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. E.G.Schukat-Talamazzini, H.Niemann, W.Eckert, T.Kuhn, S.Rieck; Acoustic modelling of subword units in the ISADORA speech recognizer, in Proc. ICASSP'92, San Francisco, 1992, Vol. 1, pp 577-580.
2. E.G.Schukat-Talamazzini, Automatische Spracherkennung, statistische Verfahren der Musteranalyse, pp 271-316, Vieweg-Verlag, 1995.
3. B.Plannerer, G.Ruske, A continuous speech recognition system using phonotactic constraints, in Proc. of EUROSPEECH'93, Berlin, 1993, Vol. 2, pp 859-862.
4. J.Reinecke, Evaluierung der signalnahen Spracherkennung im Verbundprojekt Verbmobil (Herbst 1996), Memo 113, Verbmobil, DFKI Saarbrücken, 1996.