Pre-Finetuning for Few-Shot Emotional Speech Recognition

被引:1
|
作者
Chen, Maximillian [1 ]
Yu, Zhou [1 ]
机构
[1] Columbia Univ, New York, NY 10027 USA
来源
INTERSPEECH 2023 | 2023年
关键词
emotion recognition; low-resource learning; pre-finetuning; transfer learning; CORPUS;
D O I
10.21437/Interspeech.2023-136
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production environments. We view speaker adaptation as a few-shot learning problem and propose investigating transfer learning approaches inspired by recent success with pre-trained models in natural language tasks. We propose pre-finetuning speech models on difficult tasks to distill knowledge into few-shot downstream classification objectives. We pre-finetune Wav2Vec2.0 on every permutation of four multiclass emotional speech recognition corpora and evaluate our pre-finetuned models through 33,600 few-shot fine-tuning trials on the Emotional Speech Dataset.
引用
收藏
页码:3602 / 3606
页数:5
相关论文
共 50 条
  • [41] Elastic temporal alignment for few-shot action recognition
    Pan, Fei
    Xu, Chunlei
    Zhang, Hongjie
    Guo, Jie
    Guo, Yanwen
    IET COMPUTER VISION, 2023, 17 (01) : 39 - 50
  • [42] Knowledge Graph Transfer Network for Few-Shot Recognition
    Chen, Riquan
    Chen, Tianshui
    Hui, Xiaolu
    Wu, Hefeng
    Li, Guanbin
    Lin, Liang
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 10575 - 10582
  • [43] CONTRASTIVE REPRESENTATION FOR FEW-SHOT VEHICLE FOOTPRINT RECOGNITION
    Wang, Yongxiong
    Hu, Chuanfei
    Wang, Guangpeng
    Lin, Xu
    2021 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW), 2021,
  • [44] Matching Compound Prototypes for Few-Shot Action Recognition
    Huang, Yifei
    Yang, Lijin
    Chen, Guo
    Zhang, Hongjie
    Lu, Feng
    Sato, Yoichi
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, 132 (09) : 3977 - 4002
  • [45] Few-shot learning for plant disease recognition: A review
    Sun, Jianqiang
    Cao, Wei
    Fu, Xi
    Ochi, Sunao
    Yamanaka, Takehiko
    AGRONOMY JOURNAL, 2024, 116 (03) : 1204 - 1216
  • [46] Radar target recognition based on few-shot learning
    Yang, Yue
    Zhang, Zhuo
    Mao, Wei
    Li, Yang
    Lv, Chengang
    MULTIMEDIA SYSTEMS, 2023, 29 (05) : 2865 - 2875
  • [47] Few-shot cotton pest recognition and terminal realization
    Li, Yang
    Yang, Jiachen
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 169
  • [48] Few-shot Image Recognition for UAV Sports Cinematography
    Patsiouras, Emmanouil
    Tefas, Anastasios
    Pitas, Ioannis
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 965 - 969
  • [49] Incremental Few-Shot Learning for Pedestrian Attribute Recognition
    Xiang, Liuyu
    Jin, Xiaoming
    Ding, Guiguang
    Han, Jungong
    Li, Leida
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3912 - 3918
  • [50] Few-shot classification in Named Entity Recognition Task
    Fritzler, Alexander
    Logacheva, Varvara
    Kretov, Maksim
    SAC '19: PROCEEDINGS OF THE 34TH ACM/SIGAPP SYMPOSIUM ON APPLIED COMPUTING, 2019, : 993 - 1000