Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks

被引:0
|
作者
Chang, Kai-Wei [1 ]
Hsu, Ming-Hao [2 ]
Li, Shan-Wen [3 ]
Lee, Hung-yi [2 ]
机构
[1] Natl Taiwan Univ, Grad Inst Commun Engn, Taipei, Taiwan
[2] Natl Taiwan Univ, Dept Elect Engn, Taipei, Taiwan
[3] Meta AI, Menlo Pk, CA USA
来源
关键词
In-context learning; speech language model; prompt tuning; few-shot learning; speech classification;
D O I
10.21437/Interspeech.2024-1932
中图分类号
学科分类号
摘要
Ever since the development of GPT-3 in the natural language processing (NLP) field, in-context learning (ICL) has played an essential role in utilizing large language models (LLMs). By presenting the LM utterance-label demonstrations at the input, the LM can accomplish few-shot learning without relying on gradient descent or requiring explicit modification of its parameters. This enables the LM to perform various downstream tasks in a black-box manner. Despite the success of ICL in NLP, little work is exploring the possibility of ICL in speech processing. This study is the first work exploring ICL for speech classification tasks with textless speech LM. We first show that the current speech LM lacks the ICL capability. We then perform warmup training on the speech LM, equipping the LM with demonstration learning capability. This paper explores and proposes the first speech LM capable of performing unseen classification tasks in an ICL manner.
引用
收藏
页码:4139 / 4143
页数:5
相关论文
共 50 条
  • [1] COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning
    Pan, Jing
    Wu, Jian
    Gaur, Yashesh
    Sivasankaran, Sunit
    Chen, Zhuo
    Liu, Shujie
    Li, Jinyu
    INTERSPEECH 2024, 2024, : 4164 - 4168
  • [2] Customizing Language Model Responses with Contrastive In-Context Learning
    Gao, Xiang
    Das, Kamalika
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 16, 2024, : 18039 - 18046
  • [3] SINC: Self-Supervised In-Context Learning for Vision-Language Tasks
    Chen, Yi-Syuan
    Song, Yun-Zhu
    Yeo, Cheng Yu
    Liu, Bei
    Fu, Jianlong
    Shuai, Hong-Han
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 15384 - 15396
  • [4] Meta-learning via Language Model In-context Tuning
    Chen, Yanda
    Zhong, Ruiqi
    Zha, Sheng
    Karypis, George
    He, He
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 719 - 730
  • [5] IN-CONTEXT LANGUAGE LEARNING: ARCHITECTURES AND ALGORITHMS
    Akyürek, Ekin
    Wang, Bailin
    Kim, Yoon
    Andreas, Jacob
    arXiv,
  • [6] Exploring Conditional Language Model Based Data Augmentation Approaches for Hate Speech Classification
    D'Sa, Ashwin Geet
    Illina, Irina
    Fohr, Dominique
    Klakow, Dietrich
    Ruiter, Dana
    TEXT, SPEECH, AND DIALOGUE, TSD 2021, 2021, 12848 : 135 - 146
  • [7] SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks
    Chang, Kai-Wei
    Wu, Haibin
    Wang, Yu-Kai
    Wu, Yuan-Kuei
    Shen, Hua
    Tseng, Wei-Cheng
    Kang, Iu-Thing
    Li, Shang-Wen
    Lee, Hung-Yi
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2024, 32 : 3730 - 3744
  • [8] Meta In-Context Learning: Harnessing Large Language Models for Electrical Data Classification
    Zhou, Mi
    Li, Fusheng
    Zhang, Fan
    Zheng, Junhao
    Ma, Qianli
    ENERGIES, 2023, 16 (18)
  • [9] Learning a Language Model from Continuous Speech
    Neubig, Graham
    Mimura, Masato
    Mori, Shinsuke
    Kawahara, Tatsuya
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 1053 - 1056
  • [10] Playing speech backwards for classification tasks
    Hürst, W
    Lauer, T
    Bürfent, C
    2005 IEEE International Conference on Multimedia and Expo (ICME), Vols 1 and 2, 2005, : 913 - 916