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 2202.00601eess.AScs.AIcs.CLcs.SD
收藏

BEA-Base:匈牙利自发性ASR的基准

BEA-Base: A Benchmark for ASR of Spontaneous Hungarian

Hungarian Research Centre for Linguistics(匈牙利语言研究中心);Budapest University of Technology and Economics(布达佩斯技术与经济大学);SpeechTex Inc.(SpeechTex 公司)

P. Mihajlik, A. Balog, T. E. Gráczi, A. Kohári, B. Tarján, K. Mády

摘要:

匈牙利语有1500万人使用,但易于访问的自动语音识别(ASR)基准数据集-特别是自发语音-实际上一直不可用。在本文中,我们介绍了BEA-Base,一个子集的spoken匈牙利语数据库,主要包括140个扬声器的自发语音。它专门用于评估ASR,主要用于对话式AI应用程序。在定义了语音识别子集和任务之后,使用开源工具包开发了几个基线-包括经典的HMM-DNN混合和通过跨语言迁移学习增强的端到端方法。获得的最佳结果是基于多语言自监督预训练,与经典方法相比,识别错误率降低了45%-无需应用外部语言模型或额外的监督数据。结果表明,使用BEA-Base的匈牙利语音识别系统的培训和评估的可行性。

英文摘要:

Hungarian is spoken by 15 million people, still, easily accessible Automatic Speech Recognition (ASR) benchmark datasets - especially for spontaneous speech - have been practically unavailable. In this paper, we introduce BEA-Base, a subset of the BEA spoken Hungarian database comprising mostly spontaneous speech of 140 speakers. It is built specifically to assess ASR, primarily for conversational AI applications. After defining the speech recognition subsets and task, several baselines - including classic HMM-DNN hybrid and end-to-end approaches augmented by cross-language transfer learning - are developed using open-source toolkits. The best results obtained are based on multilingual self-supervised pretraining, achieving a 45% recognition error rate reduction as compared to the classical approach - without the application of an external language model or additional supervised data. The results show the feasibility of using BEA-Base for training and evaluation of Hungarian speech recognition systems.

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。

↑