INTENT RECOGNITION AND UNSUPERVISED SLOT IDENTIFICATION FOR LOW-RESOURCED SPOKEN DIALOG SYSTEMS

被引:1
|
作者
Gupta, Akshat [1 ]
Deng, Olivia [1 ]
Kushwaha, Akruti [1 ]
Mittal, Saloni [1 ]
Zeng, William [1 ]
Rallabandi, Sai Krishna [1 ]
Black, Alan W. [1 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
关键词
Intent Recognition; Spoken Language Understanding; Transformers; low-resourced; Multilingual;
D O I
10.1109/ASRU51503.2021.9688264
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Intent Recognition and Slot Identification are crucial components in spoken language understanding (SLU) systems. In this paper, we present a novel approach towards both these tasks in the context of low-resourced and unwritten languages. We use an acoustic based SLU system that converts speech to its phonetic transcription using a universal phone recognition system. We build a word-free natural language understanding module that does intent recognition and slot identification from these phonetic transcription. Our proposed SLU system performs competitively for resource rich scenarios and significantly outperforms existing approaches as the amount of available data reduces. We train both recurrent and transformer based neural networks and test our system on five natural speech datasets in five different languages. We observe more than 10% improvement for intent classification in Tamil and more than 5% improvement for intent classification in Sinhala. Additionally, we present a novel approach towards unsupervised slot identification using normalized attention scores. This approach can be used for unsupervised slot labelling, data augmentation and to generate data for a new slot in a one-shot way with only one speech recording.
引用
收藏
页码:853 / 860
页数:8
相关论文
共 29 条
  • [1] Common latent representation learning for low-resourced spoken language identification
    Chen, Chen
    Bu, Yulin
    Chen, Yong
    Chen, Deyun
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (12) : 34515 - 34535
  • [2] Common latent representation learning for low-resourced spoken language identification
    Chen, Chen
    Bu, Yulin
    Chen, Yong
    Chen, Deyun
    [J]. Multimedia Tools and Applications, 2024, 83 (12) : 34515 - 34535
  • [3] Common latent representation learning for low-resourced spoken language identification
    Chen Chen
    Yulin Bu
    Yong Chen
    Deyun Chen
    [J]. Multimedia Tools and Applications, 2024, 83 : 34515 - 34535
  • [4] Enabling Spoken Dialogue Systems for Low-Resourced Languages-End-to-End Dialect Recognition for North Sami
    Trung Ngo Trong
    Jokinen, Kristiina
    Hautamaki, Ville
    [J]. 9TH INTERNATIONAL WORKSHOP ON SPOKEN DIALOGUE SYSTEM TECHNOLOGY, 2019, 579 : 221 - 235
  • [5] Speaker independent recognition of low-resourced multilingual Arabic spoken words through hybrid fusion
    Mehra, Sunakshi
    Ranga, Virender
    Agarwal, Ritu
    Susan, Seba
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024,
  • [6] Multilingual broad phoneme recognition and language-independent spoken term detection for low-resourced languages
    Deekshitha, G.
    Mary, Leena
    [J]. JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2022, 34 (09) : 7313 - 7323
  • [7] Improving the Performance of Low-resourced Speaker Identification with Data Preprocessing
    Phyu, Win Lai Lai
    Naing, Hay Mar Soe
    Pa, Win Pa
    [J]. JOURNAL OF ICT RESEARCH AND APPLICATIONS, 2023, 17 (03) : 275 - 291
  • [8] Two-Stage Data Augmentation for Low-Resourced Speech Recognition
    Hartmann, William
    Ng, Tim
    Hsiao, Roger
    Tsakalidis, Stavros
    Schwartz, Richard
    [J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 2378 - 2382
  • [9] Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems
    Chen, Yun-Nung
    [J]. 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING: PROCEEDINGS OF THE STUDENT RESEARCH WORKSHOP (ACL-IJCNLP 2015), 2015, : 1 - 7
  • [10] Deep Models for Low-Resourced Speech Recognition: Livvi-Karelian Case
    Kipyatkova, Irina
    Kagirov, Ildar
    [J]. MATHEMATICS, 2023, 11 (18)