IMPROVING AUTOMATIC SPEECH RECOGNITION ROBUSTNESS FOR THE ROMANIAN LANGUAGE

被引：0
|
作者：
Buzo, Andi [1 ]
Cucu, Horia [1 ]
Burileanu, Corneliu [1 ]
机构：
[1] Univ Politehn Bucuresti, Fac Elect Telecommun & Informat Technol, Iuliu Maniu 1-3,Sect 6, Bucharest, Romania
来源：
19TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO-2011) | 2011年
关键词：
D O I：
暂无
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：
In this paper we propose an alternative way of improving speech recognition accuracy by analyzing the relevance of voice feature dimensions. A new measure is defined in order to quantify the feature distribution overlapping. Based on this measure, weights for voice feature dimensions are calculated and then applied to the hypotheses resulted from an N-best recognition process. Experiments are made with an Automatic Speech Recognition (ASR) system for the Romanian language. A relative improvement of 22% is obtained in terms of Word Error Rate (WER).
引用
收藏
页码：2119 / 2122
页数：4
相关论文
共 50 条
  • [1] On the Design of an Automatic Speech Recognition System for Romanian Language
    Caranica, Alexandru
    Cucu, Horia
    Buzo, Audi
    Burileanu, Corneliu
    [J]. CONTROL ENGINEERING AND APPLIED INFORMATICS, 2016, 18 (02): : 65 - 76
  • [2] IMPROVING ROBUSTNESS AGAINST REVERBERATION FOR AUTOMATIC SPEECH RECOGNITION
    Mitra, Vikramjit
    Van Hout, Julien
    Wang, Wen
    Graciarena, Martin
    McLaren, Mitchell
    Franco, Horacio
    Vergyri, Dimitra
    [J]. 2015 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2015, : 525 - 532
  • [3] PROTOLOGOS, SYSTEM FOR ROMANIAN LANGUAGE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU)
    Militaru, Diana
    Gavat, Inge
    Dumitru, Octavian
    Zaharia, Tiberiu
    Segarceanu, Svetlana
    [J]. FROM SPEECH PROCESSING TO SPOKEN LANGUAGE TECHNOLOGY, 2009, : 21 - 32
  • [4] Improving Language Modeling with an Adversarial Critic for Automatic Speech Recognition
    Zhang, Yike
    Zhang, Pengyuan
    Yan, Yonghong
    [J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 3348 - 3352
  • [5] Applications of speech recognition for Romanian language
    Chivu, Catalin
    [J]. ADVANCES IN ELECTRICAL AND COMPUTER ENGINEERING, 2007, 7 (01) : 29 - 33
  • [6] Robust Romanian language automatic speech recognizer
    Munteanu, Doru-Petru
    Vizitiu, Constantin-Iulian
    [J]. CIMMACS '07: PROCEEDINGS OF THE 6TH WSEAS INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, MAN-MACHINE SYSTEMS AND CYBERNETICS, 2007, : 251 - +
  • [7] Improving speech detection robustness for wireless speech recognition
    Karray, L
    Mauuary, L
    [J]. 1997 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, PROCEEDINGS, 1997, : 428 - 435
  • [8] Improving Automatic Speech Recognition with Dialect-Specific Language Models
    Gothi, Raj
    Rao, Preeti
    [J]. SPEECH AND COMPUTER, SPECOM 2023, PT I, 2023, 14338 : 57 - 67
  • [9] RSC: A Romanian Read Speech Corpus for Automatic Speech Recognition
    Georgescu, Alexandru-Lucian
    Cucu, Horia
    Buzo, Andi
    Burileanu, Corneliu
    [J]. PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020), 2020, : 6606 - 6612
  • [10] A STUDY ON BIAS-BASED SPEECH SIGNAL CONDITIONING TECHNIQUES FOR IMPROVING THE ROBUSTNESS OF AUTOMATIC SPEECH RECOGNITION
    Chowdhury, Md Foezur Rahman
    Selouani, Sid-Ahmed
    O'Shaughnessy, Douglas
    [J]. 2009 IEEE 22ND CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, VOLS 1 AND 2, 2009, : 366 - +
12345