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 2212.08704cs.AI
收藏

语音感知对话系统技术挑战赛(DSTC11)

Speech Aware Dialog System Technology Challenge (DSTC11)

Google Research(谷歌研究院)

Hagen Soltau, Izhak Shafran, Mingqiu Wang, Abhinav Rastogi, Jeffrey Zhao, Ye Jia, Wei Han, Yuan Cao, Aramys Miranda

摘要:

面向任务的对话框建模的研究大多基于书面文本输入。然而,用户通常使用语音作为输入与实际对话系统交互。通常,系统使用自动语音识别(ASR)系统将语音转换成文本,从而引入错误。此外,这些系统没有解决书面语言和口头语言的差异。由于缺乏公共语料库,这一主题的研究受到阻碍。出于这些考虑,我们举办语音感知对话状态跟踪挑战赛的目标是创建一个公共语料库或任务,可用于调查书面和口头形式的输入之间的性能差距,开发可以缓解这种差距的模型,并确定基于文本到语音(TTS)的系统是否是劳动密集型人类数据汇集的合理替代品。我们创建了流行的书面领域MultiWoz任务的三个口语版本-(a)TTS逐字:使用TTS系统将书面用户输入转换为语音波形,(b)Human-Verbatim:人类逐字说出用户输入,以及(c)Human-paraphrased:人类对用户输入进行释义。此外,我们提供了不同形式的ASR输出,以鼓励可能无法访问最先进的ASR系统的团队更广泛地参与。这些包括ASR转录,单词时间戳和音频的潜在表示(音频编码器输出)。在本文中,我们描述了语料库,报告的结果,从参与团队,提供初步的分析,他们的结果,并总结了目前的国家在这一领域的最先进的。

英文摘要:

Most research on task oriented dialog modeling is based on written text input. However, users interact with practical dialog systems often using speech as input. Typically, systems convert speech into text using an Automatic Speech Recognition (ASR) system, introducing errors. Furthermore, these systems do not address the differences in written and spoken language. The research on this topic is stymied by the lack of a public corpus. Motivated by these considerations, our goal in hosting the speech-aware dialog state tracking challenge was to create a public corpus or task which can be used to investigate the performance gap between the written and spoken forms of input, develop models that could alleviate this gap, and establish whether Text-to-Speech-based (TTS) systems is a reasonable surrogate to the more-labor intensive human data collection. We created three spoken versions of the popular written-domain MultiWoz task -- (a) TTS-Verbatim: written user inputs were converted into speech waveforms using a TTS system, (b) Human-Verbatim: humans spoke the user inputs verbatim, and (c) Human-paraphrased: humans paraphrased the user inputs. Additionally, we provided different forms of ASR output to encourage wider participation from teams that may not have access to state-of-the-art ASR systems. These included ASR transcripts, word time stamps, and latent representations of the audio (audio encoder outputs). In this paper, we describe the corpus, report results from participating teams, provide preliminary analyses of their results, and summarize the current state-of-the-art in this domain.

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。

↑