Affinity Maturation of Homophones in Word-Level Speech Recognition

被引：0
|
作者：
Ghosh, P. [1 ]
Chingtham, T. S. [2 ]
Ghose, M. K. [3 ]
机构：
[1] MAKAUT, Dept Comp Sci & Engn, SIEM, Siliguri, W Bengal, India
[2] SMU, SMIT, Dept Comp Sci & Engn, Majhitar, Sikkim, India
[3] Sikkim Univ, Dept Comp Applicat, Gangtok, Sikkim, India
来源：
RECENT DEVELOPMENTS IN MACHINE LEARNING AND DATA ANALYTICS | 2019年 / 740卷
关键词：
Human-Computer Speech Interaction (HCSI); Word-Level Speech Recognition (WLSR); Artificial Immune System (AIS); Affinity Maturation Artificial Immune Network (AINet);
D O I：
10.1007/978-981-13-1280-9_13
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Homophones are recognized in sentence-level speech recognition due to the dominating meaning and lexical analysis technique, but still it is a difficult ambiguity in word-level recognition where the uttered expression is either short or in a single string. To reduce the homophone ambiguity from the word-level recognition, an artificial immune system algorithm is proposed in the earlier part of this research where the recognition rate of a correct homophone word is minimal. In this paper, an affinity maturation technique is proposed to increase the correct recognition rate at the preliminary phase of the artificial immune algorithm.
引用
收藏
页码：137 / 142
页数：6
相关论文
共 50 条
  • [1] Word-level Speech Recognition with a Letter to Word Encoder
    Collobert, Ronan
    Hannun, Awni
    Synnaeve, Gabriel
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [2] Word-level Speech Recognition with a Letter to Word Encoder
    Collobert, Ronan
    Hannun, Awni
    Synnaeve, Gabriel
    [J]. 25TH AMERICAS CONFERENCE ON INFORMATION SYSTEMS (AMCIS 2019), 2019,
  • [3] WORD-LEVEL TONE MODELING FOR MANDARIN SPEECH RECOGNITION
    Lei, Xin
    Ostendorf, Mari
    [J]. 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 665 - +
  • [4] WORD-LEVEL RECOGNITION OF CURSIVE SCRIPT
    FARAG, RFH
    [J]. IEEE TRANSACTIONS ON COMPUTERS, 1979, 28 (02) : 172 - 175
  • [5] Word-Level Speech Dataset Creation for Sourashtra and Recognition System Using Kaldi
    Vancha, Punitha
    Nagarajan, Harshitha
    Inakollu, Vishnu Sai
    Gupta, Deepa
    Vekkot, Susmitha
    [J]. 2022 IEEE 19TH INDIA COUNCIL INTERNATIONAL CONFERENCE, INDICON, 2022,
  • [6] Modeling word-level rate-of-speech variation in large vocabulary conversational speech recognition
    Zheng, J
    Franco, H
    Stolcke, A
    [J]. SPEECH COMMUNICATION, 2003, 41 (2-3) : 273 - 285
  • [7] Preserving Word-Level Emphasis in Speech-to-Speech Translation
    Quoc Truong Do
    Toda, Tomoki
    Neubig, Graham
    Sakti, Sakriani
    Nakamura, Satoshi
    [J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2017, 25 (03) : 544 - 556
  • [8] Speech Emotion Recognition based on AttentionWeight Correction Using Word-level Confidence Measure
    Santoso, Jennifer
    Yamada, Takeshi
    Makino, Shoji
    Ishizuka, Kenkichi
    Hiramura, Takekatsu
    [J]. INTERSPEECH 2021, 2021, : 1947 - 1951
  • [9] WISE: Word-Level Interaction-Based Multimodal Fusion for Speech Emotion Recognition
    Shen, Guang
    Lai, Riwei
    Chen, Rui
    Zhang, Yu
    Zhang, Kejia
    Han, Qilong
    Song, Hongtao
    [J]. INTERSPEECH 2020, 2020, : 369 - 373
  • [10] AN EVALUATION OF WORD-LEVEL CONFIDENCE ESTIMATION FOR END-TO-END AUTOMATIC SPEECH RECOGNITION
    Oneata, Dan
    Caranica, Alexandru
    Stan, Adriana
    Cucu, Horia
    [J]. 2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT), 2021, : 258 - 265
12345