arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.12477eess.AScs.AIcs.CL
收藏

探索用于语音分类任务的无文本语音语言模型的上下文学习

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

National Taiwan University(台湾大学);Meta AI

Ming-Hao Hsu, Kai-Wei Chang, Shang-Wen Li, Hung-yi Lee

AI总结:

本文针对无文本语音语言模型缺乏上下文学习能力的问题,通过热身训练赋予其示例学习能力,首次实现以 ICL 方式完成未见过的语音分类任务。

摘要:

自自然语言处理(NLP)领域开发出 GPT-3 以来,上下文学习(ICL)在利用大型语言模型(LLM)方面一直发挥着重要作用。通过在输入中向语言模型呈现话语-标签示例,该语言模型无需依赖梯度下降,也无需显式修改其参数,即可完成少样本学习。这使语言模型能够以黑盒方式执行各种下游任务。尽管 ICL 在 NLP 中取得了成功,但探索 ICL 在语音处理中可能性的工作仍然很少。本研究是首个利用无文本语音语言模型探索面向语音分类任务的 ICL 的工作。我们首先表明,当前的语音语言模型缺乏 ICL 能力。随后,我们对语音语言模型执行热身训练,使该语言模型具备示例学习能力。本文探索并提出了首个能够以 ICL 方式执行未见过分类任务的语音语言模型。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑