Developing HMM-based recognizers with ESMERALDA

被引：0
|
作者：
Fink, GA [1 ]
机构：
[1] Univ Bielefeld, Fac Technol, D-33501 Bielefeld, Germany
来源：
TEXT, SPEECH AND DIALOGUE | 1999年 / 1692卷
关键词：
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：
ESMERALDA is an integrated environment for the development of speech recognition systems. It provides a powerful selection of methods for building statistical models together with an efficient incremental recognizer. In this paper the approaches adopted for estimating mixture densities, Hidden Markov Models, and n-gram language models are described as well as the algorithms applied during recognition. Evaluation results on a speaker independent spontaneous speech recognition task demonstrate the capabilities of ESMERALDA.
引用
收藏
页码：229 / 234
页数：6
相关论文
共 50 条
  • [1] Discriminative state-weighting of HMM-based speech recognizers
    Kwon, OW
    Un, CK
    APCCAS '96 - IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS '96, 1996, : 251 - 254
  • [2] Discriminative feature weighting for HMM-based continuous speech recognizers
    de la Torre, A
    Peinado, AM
    Rubio, AJ
    Segura, JC
    Benítez, C
    SPEECH COMMUNICATION, 2002, 38 (3-4) : 267 - 286
  • [3] An On-line Speaker Adaptation Method for HMM-based Speech Recognizers
    Banhalmi, Andras
    Kocsor, Andras
    ACTA CYBERNETICA, 2008, 18 (03): : 379 - 390
  • [4] Performance of HMM-based speech recognizers with discriminative state-weights
    Kwon, OW
    Un, CK
    SPEECH COMMUNICATION, 1996, 19 (03) : 197 - 205
  • [5] Performance of HMM-based speech recognizers with discriminative state-weights
    Korea Advanced Inst of Science and, Technology, Taejon, Korea, Republic of
    Speech Commun, 3 (197-205):
  • [6] Discriminative codebook design using multiple vector quantization in HMM-based speech recognizers
    Peinado, AM
    Segura, JC
    Rubio, AJ
    Garcia, P
    Perez, JL
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1996, 4 (02): : 89 - 95
  • [7] Connected digit recognition experiments with the OGI Toolkit's neural network and HMM-based recognizers
    Cosi, P
    Hosom, JP
    Shalkwyk, J
    Sutton, S
    Cole, RA
    1998 IEEE 4TH WORKSHOP INTERACTIVE VOICE TECHNOLOGY FOR TELECOMMUNICATIONS APPLICATIONS - IVTTA '98, 1998, : 135 - 140
  • [8] HMM-Based Trust Model
    Elsalamouny, Ehab
    Sassone, Vladimiro
    Nielsen, Mogens
    FORMAL ASPECTS IN SECURITY AND TRUST, 2010, 5983 : 21 - +
  • [9] An HMM-Based Reputation Model
    ElSalamouny, Ehab
    Sassone, Vladimiro
    ADVANCES IN SECURITY OF INFORMATION AND COMMUNICATION NETWORKS, 2013, 381 : 111 - +
  • [10] Croatian HMM-based speech synthesis
    Department of Informatics, Faculty of Philosophy, University of Rijeka, Omladinska 14, Rijeka
    51000, Croatia
    J. Compt. Inf. Technol., 2006, 4 (307-313):
12345