NN and hybrid strategies for speech recognition in romanian language

被引:0
|
作者
Dumitru, Corneliu-Octavian [1 ]
Gavat, Inge [1 ]
机构
[1] Univ Politehn Bucuresti, Fac Elect Telecommun & Informat Technol, Bucharest, Romania
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
In this paper we present results obtained with learning structures more "human likely" than the very effective and widely used hidden Markov model. Good results were obtained with simple artificial neural networks like the multilayer perceptron or the Kohonen maps. Hybrid structures have proven also their efficiency, the neuro-statistical hybrid applied enhancing the digit recognition rate of the initial HMM. Also fuzzy variants of the MLP and HMM gave good results in the tested tasks of vowel recognition.
引用
收藏
页码:51 / 60
页数:10
相关论文
共 50 条
  • [41] Robust Romanian language automatic speech recognizer
    Munteanu, Doru-Petru
    Vizitiu, Constantin-Iulian
    CIMMACS '07: PROCEEDINGS OF THE 6TH WSEAS INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, MAN-MACHINE SYSTEMS AND CYBERNETICS, 2007, : 251 - +
  • [42] Mandarin emotional speech recognition based on SVM and NN
    Pao, Tsang-Long
    Chen, Yu-Te
    Yeh, Jun-Heng
    Li, Pei-Jia
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2006, : 1096 - +
  • [43] Automatic speech emotion recognition based on hybrid features with ANN, LDA and K_NN classifiers
    Al Dujaili, Mohammed Jawad
    Ebrahimi-Moghadam, Abbas
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (27) : 42783 - 42801
  • [44] Automatic speech emotion recognition based on hybrid features with ANN, LDA and K_NN classifiers
    Mohammed Jawad Al Dujaili
    Abbas Ebrahimi-Moghadam
    Multimedia Tools and Applications, 2023, 82 : 42783 - 42801
  • [45] Emotion Recognition Expressed Contextually for Romanian Language
    Marius-Dan, Zbancioc
    Monica, Feraru Silvia
    2018 INTERNATIONAL CONFERENCE AND EXPOSITION ON ELECTRICAL AND POWER ENGINEERING (EPE), 2018, : 179 - 182
  • [46] A KIND OF HYBRID LANGUAGE MODEL EMPLOYED IN POST PROCESSING OF CHINESE SPEECH RECOGNITION
    Mei Yong Xu Bingzheng Wang Qunsheng(Dept. of Radio Engineering
    JournalofElectronics(China), 1998, (03) : 221 - 225
  • [47] Recognition of Positive and Negative Emotions for Romanian Language
    Feraru, Silvia Monica
    Zbancioc, Marius Dan
    2017 IEEE INTERNATIONAL CONFERENCE ON E-HEALTH AND BIOENGINEERING CONFERENCE (EHB), 2017, : 725 - 728
  • [48] Hybrid Approach for Language Identification Oriented to Multilingual Speech Recognition in the Basque Context
    Barroso, N.
    Lopez de Ipina, K.
    Ezeiza, A.
    Barroso, O.
    Susperregi, U.
    HYBRID ARTIFICIAL INTELLIGENCE SYSTEMS, PT 1, 2010, 6076 : 196 - +
  • [49] Learning strategies in speech recognition
    Gavat, I
    Dumitru, O
    Iancu, C
    Costache, G
    Proceedings ELMAR-2005, 2005, : 237 - 240
  • [50] Spontaneous Speech Database for the Romanian Language with Medical Applicability
    Petrea, Cristina Sorina
    Hanes, Diana Mirela
    Buzo, Andi
    Popescu, Vladimir
    Burileanu, Corneliu
    MOBILIZING HEALTH INFORMATION TO SUPPORT HEALTHCARE-RELATED KNOWLEDGE WORK, 2009, : 78 - 86