arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2303.00733eess.AScs.AIcs.CLcs.LGcs.SD
收藏

SpeechPrompt v2:语音分类任务的提示调优

SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks

National Taiwan University(台湾大学);Pennsylvania State University(宾夕法尼亚州立大学);Meta AI

Kai-Wei Chang, Yu-Kai Wang, Hua Shen, Iu-thing Kang, Wei-Cheng Tseng, Shang-Wen Li, Hung-yi Lee

摘要:

提示调优是一种调整一小组参数的技术,以引导预训练的语言模型(LM)直接为下游任务生成输出。最近,提示调谐已经在自然语言处理(NLP)和语音处理领域证明了其存储和计算效率。这些优点还揭示了作为以统一的方式为多个任务提供预训练LM的候选方法的及时调整。在语音处理方面,SpeechPrompt在一些语音分类任务上表现出了较高的参数效率和竞争力。然而,SpeechPrompt是否能够服务于大量任务还没有答案。在这项工作中,我们提出了SpeechPrompt v2,一个提示调整框架,能够执行各种各样的语音分类任务,涵盖多种语言和韵律相关的任务。实验结果表明,SpeechPrompt v2在统一的框架下,可训练参数小于0.15M,达到了与现有作品相当的性能。

英文摘要:

Prompt tuning is a technology that tunes a small set of parameters to steer a pre-trained language model (LM) to directly generate the output for downstream tasks. Recently, prompt tuning has demonstrated its storage and computation efficiency in both natural language processing (NLP) and speech processing fields. These advantages have also revealed prompt tuning as a candidate approach to serving pre-trained LM for multiple tasks in a unified manner. For speech processing, SpeechPrompt shows its high parameter efficiency and competitive performance on a few speech classification tasks. However, whether SpeechPrompt is capable of serving a large number of tasks is unanswered. In this work, we propose SpeechPrompt v2, a prompt tuning framework capable of performing a wide variety of speech classification tasks, covering multiple languages and prosody-related tasks. The experiment result shows that SpeechPrompt v2 achieves performance on par with prior works with less than 0.15M trainable parameters in a unified framework.

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。

↑