IMPROVING THE RECOGNITION PERFORMANCE BY USING A PARALLEL-BRANCH SUBUNIT MODEL-BASED ON MISRECOGNISED DATA

被引:0
|
作者
PARK, YK
UN, CK
机构
[1] Communication Research Laboratory, Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Taejon, 371-1 Kusung-Dong, Yusung-Ku
关键词
SPEECH RECOGNITION; MARKOV PROCESSES;
D O I
10.1049/el:19940964
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
An initialisation and training method using a parallel-branch subunit model is obtained which uses a continuous hidden Markov model for improved recognition performance. The model is obtained by adding a new subunit branch based on misrecognised data in the training data to the previous parallel branches for that subunit. This procedure is shown to be efficient and gives good word recognition performance.
引用
收藏
页码:1380 / 1382
页数:3
相关论文
共 50 条
  • [1] Word recognition by a parallel-branch subunit model based on misrecognized data in semi-continuous HMM
    Korea Advanced Inst of Technology, Taejon, Korea, Republic of
    [J]. IEEE Signal Process Lett, 3 (66-68):
  • [2] Word recognition by a parallel-branch subunit model based on misrecognized data in semi-continuous HMM
    Park, YK
    Un, CK
    [J]. IEEE SIGNAL PROCESSING LETTERS, 1996, 3 (03) : 66 - 68
  • [3] On the generation and use of a parallel-branch subunit model in continuous HMM
    Park, YK
    Un, CK
    [J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1996, 4 (04): : 290 - 293
  • [4] Model-based motion filtering for improving arm gesture recognition performance
    Schmidt, GS
    House, DH
    [J]. GESTURE-BASED COMMUNICATION IN HUMAN-COMPUTER INTERACTION, 2003, 2915 : 210 - 230
  • [5] A PARALLEL ARCHITECTURE FOR MODEL-BASED OBJECT RECOGNITION
    LIVESEY, MJ
    OWCZARCZYK, J
    [J]. LECTURE NOTES IN COMPUTER SCIENCE, 1988, 301 : 288 - 295
  • [6] Improving Multisite Workflow Performance using Model-based Scheduling
    Maheshwari, Ketan
    Jung, Eun-Sung
    Meng, Jiayuan
    Vishwanath, Venkatram
    Kettimuthu, Rajkumar
    [J]. 2014 43RD INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING (ICPP), 2014, : 131 - 140
  • [7] Effect of AR model-based data extrapolation on target recognition performance
    Kim, KT
    Bae, JH
    Kim, HT
    [J]. IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 2003, 51 (04) : 912 - 914
  • [8] Parallel model-based diagnosis using PVM
    Anglano, C.
    Portinale, L.
    [J]. Lecture Notes in Computer Science, 1156
  • [9] Performance characterization of a model-based SAR target recognition system using invariants
    Bhanu, B
    Jones, G
    [J]. ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY IV, 1997, 3070 : 305 - 321
  • [10] Parallel Overloading Operations using a Model-Based Strategy
    Happich, Georg
    Harms, Hans-Heinrich
    Lang, Thorsten
    [J]. CONFERENCE: AGRICULTURAL ENGINEERING - LAND-TECHNIK AGENG 2009: INNOVATIONS TO MEET FUTURE CHALLENGES, 2009, 2060 : 153 - 158