Large vocabulary speech recognition of Slovenian language using morphological models

被引：0
|
作者：
Maucec, M [1 ]
Rotovnik, T [1 ]
Kacic, Z [1 ]
Horvat, B [1 ]
机构：
[1] Univ Maribor, Inst Elect, Fac Elect Engn & Comp Sci, SI-2000 Maribor, Slovenia
来源：
IEEE REGION 8 EUROCON 2003, VOL B, PROCEEDINGS: COMPUTER AS A TOOL | 2003年
关键词：
language modelling; automatic continuous speech recognition; morphology; large vocabulary; data-driven methods; topic adaptation;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper concerns the development of automatic speech recognition system for Slovenian language. The large number of unique words in inflected languages is identified as the primary reason for performance degradation. This article discusses the statistical language models. A novel variation of the n-gram modelling theme is examined. Modelling units are chosen to be stems and endings instead of words. Only data-driven algorithms are employed to decompose words into stems and endings automatically. Significant reduction of OOV rate results when using stems and endings for modelling the Slovenian language. We as well discuss corpus-based topic-adapted language models. Language models are most often used in topic homogeneous environment. The problem of topic detection in highly inflected language is outlined, caused by appearance of several word forms derived from the same lemma. The problem is solved by using data-driven algorithms to group words of the same lemma into classes.
引用
收藏
页码：158 / 161
页数：4
相关论文
共 50 条
  • [31] Acoustic models of the elderly for large-vocabulary continuous speech recognition
    Baba, A
    Yoshizawa, S
    Yamada, M
    Lee, A
    Shikano, K
    [J]. ELECTRONICS AND COMMUNICATIONS IN JAPAN PART II-ELECTRONICS, 2004, 87 (07): : 49 - 57
  • [32] Multonic Markov Word Models for Large Vocabulary Continuous Speech Recognition
    Bahl, Lalit R.
    Bellegarda, Jerome R.
    de Souza, Peter V.
    Gopalakrishnan, P. S.
    Nahamoo, David
    Picheny, Michael A.
    [J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1993, 1 (03): : 334 - 344
  • [33] A comparison of constrained trajectory segment models for large vocabulary speech recognition
    Kannan, A
    Ostendorf, M
    [J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1998, 6 (03): : 303 - 306
  • [34] HYBRID ACOUSTIC MODELS FOR DISTANT AND MULTICHANNEL LARGE VOCABULARY SPEECH RECOGNITION
    Swietojanski, Pawel
    Ghoshal, Arnab
    Renals, Steve
    [J]. 2013 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2013, : 285 - 290
  • [35] Large vocabulary speech recognition in French
    Adda-Decker, M
    Adda, G
    Gauvain, JL
    Lamel, L
    [J]. ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 45 - 48
  • [36] Adaptation of precision matrix models on large vocabulary continuous speech recognition
    Sim, KC
    Gales, MJF
    [J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 97 - 100
  • [37] Unsupervised training of acoustic models for large vocabulary continuous speech recognition
    Wessel, F
    Ney, H
    [J]. ASRU 2001: IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, CONFERENCE PROCEEDINGS, 2001, : 307 - 310
  • [38] Advances in Large Vocabulary Speech Recognition
    Gauvain, JL
    De Mori, R
    Lamel, L
    [J]. COMPUTER SPEECH AND LANGUAGE, 2002, 16 (01): : 1 - 3
  • [39] Using a transcription graph for large vocabulary continuous speech recognition
    Li, Z
    OShaughnessy, D
    [J]. 1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 121 - 124
  • [40] Large vocabulary audio-visual speech recognition using the Janus speech recognition toolkit
    Kratt, J
    Metze, F
    Stiefelhagen, R
    Waibel, A
    [J]. PATTERN RECOGNITION, 2004, 3175 : 488 - 495
12345