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

来源：

ANNIP 2008: PROCEEDINGS OF THE ARTIFICIAL NEURAL NETWORKS AND INTELLIGENT INFORMATION PROCESSING | 2008年

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

页码：51 / 60

页数：10

共 50 条

[21] Applying Batch Normalization to Hybrid NN-HMM Model For Speech Recognition
Zhan, Hongjian
Chen, Guilin
Lu, Yue
PATTERN RECOGNITION (CCPR 2016), PT II, 2016, 663 : 427 - 435
[22] A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction
Rigoll, G
Willett, D
PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 9 - 12
[23] Hybrid Dataset for Speech Emotion Recognition in Russian Language
Kondratenko, Vladimir
Sokolov, Artem
Karpov, Nikolay
Kutuzov, Oleg
Savushkin, Nikita
Minkin, Fyodor
INTERSPEECH 2023, 2023, : 4548 - 4552
[24] Fuzzy variants of hard classification rules for speech pattern recognition in Romanian language
Gavat, I
Grigore, O
Zirra, M
Cula, O
1997 ANNUAL MEETING OF THE NORTH AMERICAN FUZZY INFORMATION PROCESSING SOCIETY - NAFIPS, 1997, : 172 - 176
[25] Vowel recognition in Romanian language
Grigore, O
Gavat, I
Zirra, M
CAS '97 PROCEEDINGS - 1997 INTERNATIONAL SEMICONDUCTOR CONFERENCE, 20TH EDITION, VOLS 1 AND 2, 1997, : 589 - 592
[26] Hybrid NN/HMM-based speech recognition with a discriminant neural feature extraction
Willett, D
Rigoll, G
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 10, 1998, 10 : 763 - 769
[27] Speech synthesis module for Romanian language
Gavat, I
Zirra, M
Grigore, M
CAS '97 PROCEEDINGS - 1997 INTERNATIONAL SEMICONDUCTOR CONFERENCE, 20TH EDITION, VOLS 1 AND 2, 1997, : 593 - 596
[28] A comparative study of feature extraction methods applied to continuous speech recognition in Romanian language
Dumitru, Corneliu Octavian
Gavat, Inge
PROCEEDINGS ELMAR-2006, 2006, : 115 - +
[29] HMM/NN hybrids for continuous speech recognition
Alim, OAA
Elboghdadly, N
El Shaar, NM
PROCEEDINGS OF THE EIGHTEENTH NATIONAL RADIO SCIENCE CONFERENCE, VOLS 1 AND 2, 2001, : 509 - 516
[30] Hybrid HMM-NN modeling of stationary-transitional units for continuous speech recognition
Albesano, D
Gemello, R
Mana, F
PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 1112 - 1115

← 1 2 3 4 5 →