Neural Architecture Search For Keyword Spotting

被引:16
|
作者
Mo, Tong [1 ]
Yu, Yakun [1 ]
Salameh, Mohammad [2 ]
Niu, Di [1 ]
Jui, Shangling [2 ]
机构
[1] Univ Alberta, Edmonton, AB, Canada
[2] Huawei Technol, Shenzhen, Peoples R China
来源
INTERSPEECH 2020 | 2020年
关键词
Keyword Spotting; Neural Architecture Search;
D O I
10.21437/Interspeech.2020-3132
中图分类号
R36 [病理学]; R76 [耳鼻咽喉科学];
学科分类号
100104 ; 100213 ;
摘要
Deep neural networks have recently become a popular solution to keyword spotting systems, which enable the control of smart devices via voice. In this paper, we apply neural architecture search to search for convolutional neural network models that can help boost the performance of keyword spotting based on features extracted from acoustic signals while maintaining an acceptable memory footprint. Specifically, we use differentiable architecture search techniques to search for operators and their connections in a predefined cell search space. The found cells are then scaled up in both depth and width to achieve competitive performance. We evaluated the proposed method on Google's Speech Commands Dataset and achieved a state-of-the-art accuracy of over 97% on the setting of 12-class utterance classification commonly reported in the literature.
引用
收藏
页码:1982 / 1986
页数:5
相关论文
共 50 条
  • [31] Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting
    Arik, Sercan O.
    Kliegl, Markus
    Child, Rewon
    Hestness, Joel
    Gibiansky, Andrew
    Fougner, Chris
    Prenger, Ryan
    Coates, Adam
    18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 1606 - 1610
  • [32] Context Dependent Acoustic Keyword Spotting Using Deep Neural Network
    Wang, Guangsen
    Sim, Khe Chai
    2013 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2013,
  • [33] Evaluating Robustness to Noise and Compression of Deep Neural Networks for Keyword Spotting
    Pereira, Pedro H.
    Beccaro, Wesley
    Ramirez, Miguel A.
    IEEE ACCESS, 2023, 11 : 53224 - 53236
  • [34] Low-Latency Convolutional Recurrent Neural Network for Keyword Spotting
    Du, Hu
    Li, Ruohan
    Kim, Donggyun
    Hirota, Kaoru
    Dai, Yaping
    2018 JOINT 10TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS (SCIS) AND 19TH INTERNATIONAL SYMPOSIUM ON ADVANCED INTELLIGENT SYSTEMS (ISIS), 2018, : 802 - 807
  • [35] A RECURRENT NEURAL NETWORKS APPROACH FOR KEYWORD SPOTTING APPLIED ON ROMANIAN LANGUAGE
    Pipa, Sonia
    Boros, Tiberiu
    PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE 'LINQUISTIC RESOURCES AND TOOLS FOR PROCESSING THE ROMANIAN LANGUAGE', 2016, : 111 - 120
  • [36] AN EXPERIMENTAL ANALYSIS OF THE POWER CONSUMPTION OF CONVOLUTIONAL NEURAL NETWORKS FOR KEYWORD SPOTTING
    Tang, Raphael
    Wang, Weijie
    Tu, Zhucheng
    Lin, Jimmy
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5479 - 5483
  • [37] DyConvMixer: Dynamic Convolution Mixer Architecture for Open-Vocabulary Keyword Spotting
    Gharbieh, Waseem
    Huang, Jinmiao
    Wan, Qianhui
    Shim, Han Suk
    Lee, Chul
    INTERSPEECH 2022, 2022, : 5205 - 5209
  • [38] A two-step keyword spotting method using fuzzy search algorithm
    Zhang Pengyuan
    Shao Jian
    Yan Yonghong
    CHINESE JOURNAL OF ELECTRONICS, 2008, 17 (01): : 33 - 36
  • [39] Discriminative keyword spotting using triphones information and N-best search
    Tabibian, Shima
    Akbari, Ahmad
    Nasersharif, Babak
    INFORMATION SCIENCES, 2018, 423 : 157 - 171
  • [40] METRIC LEARNING FOR KEYWORD SPOTTING
    Huh, Jaesung
    Lee, Minjae
    Heo, Heesoo
    Mun, Seongkyu
    Chung, Joon Son
    2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT), 2021, : 133 - 140