TEXT NORMALIZATION FOR AUTOMATIC SPEECH RECOGNITION SYSTEMS

被引：0
|
作者：
Vasile, Alin-Florentin [1 ]
Boros, Tiberiu [1 ]
机构：
[1] Romanian Acad, Ctr Artificial Intelligence, Bucharest, Romania
来源：
PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE 'LINQUISTIC RESOURCES AND TOOLS FOR PROCESSING THE ROMANIAN LANGUAGE' | 2016年
关键词：
Automatic Speech Recognition (ASR); Natural Language Processing (NLP);
D O I：
暂无
中图分类号：
H0 [语言学];
学科分类号：
030303 ; 0501 ; 050102 ;
摘要：
The results of automatic speech recognition (ASR) systems are not directly usable in Natural Language Processing Applications. The main reason is that an ASR system does not output upper/lower word forms (except when the dictionary and language model contain a word explicitly written in its true case) and it does not include any punctuation marks. Though sometimes speech reflects punctuation (speakers do not always embed punctuation in their speech), there are several cases where pauses and pitch discontinuities are randomly added by the speaker. Also it is not straight forward if a pause is added because of a comma, a parenthesis or a full sentence stop. In our experiments we have obtained an F-score of 0.81 for capitalized/uppercase words and an F-score of 0.71 for comma and dot.
引用
收藏
页码：121 / 128
页数：8
相关论文
共 50 条
  • [1] Transformer-Based Joint Learning Approach for Text Normalization in Vietnamese Automatic Speech Recognition Systems
    Viet The Bui
    Tho Chi Luong
    Oanh Thi Tran
    [J]. CYBERNETICS AND SYSTEMS, 2024, 55 (07) : 1614 - 1630
  • [2] Energy Normalization in Automatic Speech Recognition
    Jakovljevic, Niksa
    Janev, Marko
    Pekar, Darko
    Miskovic, Dragisa
    [J]. TEXT, SPEECH AND DIALOGUE, PROCEEDINGS, 2008, 5246 : 341 - +
  • [3] NORMALIZATION AND ADAPTATION OF SPEECH DATA FOR AUTOMATIC SPEECH RECOGNITION
    SCARR, RWA
    [J]. INTERNATIONAL JOURNAL OF MAN-MACHINE STUDIES, 1970, 2 (01): : 41 - 59
  • [4] IMPROVED TEXT NORMALIZATION AND LANGUAGE MODELS FOR SPEED'S AUTOMATIC SPEECH RECOGNITION SYSTEM
    Manolache, Cristian
    Georgescu, Alexandru-Lucian
    Cucu, Horia
    Mititelu, Verginica Barbu
    Burileanu, Corneliu
    [J]. PROCEEDINGS OF THE 15TH INTERNATIONAL CONFERENCE LINGUISTIC RESOURCES AND TOOLS FOR NATURAL LANGUAGE PROCESSING, 2020, : 115 - 128
  • [5] STREAMING, FAST AND ACCURATE ON-DEVICE INVERSE TEXT NORMALIZATION FOR AUTOMATIC SPEECH RECOGNITION
    Gaur, Yashesh
    Kibre, Nick
    Xue, Jian
    Shu, Kangyuan
    Wang, Yuhui
    Alphanso, Issac
    Li, Jinyu
    Gong, Yifan
    [J]. 2022 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT, 2022, : 237 - 244
  • [6] Automatic Speech Recognition Used for Intelligibility Assessment of Text-to-Speech Systems
    Vich, Robert
    Nouza, Jan
    Vondra, Martin
    [J]. VERBAL AND NONVERBAL FEATURES OF HUMAN-HUMAN AND HUMAN-MACHINE INTERACTIONS, 2008, 5042 : 136 - +
  • [7] Almost Unsupervised Text to Speech and Automatic Speech Recognition
    Ren, Yi
    Tan, Xu
    Qin, Tao
    Zhao, Sheng
    Zhao, Zhou
    Liu, Tie-Yan
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [8] Correlation Networks for Speaker Normalization in Automatic Speech Recognition
    Sharon, Rini A.
    Kothinti, Sandeep Reddy
    Umesh, Srinivasan
    [J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 882 - 886
  • [9] A Robust Feature Normalization Algorithm for Automatic Speech Recognition
    Lei, Jianjun
    Yang, Zhen
    Wang, Jian
    [J]. FIRST IITA INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2009, : 473 - +
  • [10] Improved automatic speech recognition through speaker normalization
    Giuliani, D
    Gerosa, M
    Brugnara, F
    [J]. COMPUTER SPEECH AND LANGUAGE, 2006, 20 (01): : 107 - 123
12345