摘要
人工智能的飞速发展带给人们日益智慧的生活,智能语音识别技术在智能终端的应用已覆盖现有互联网生活服务;其次,语音识别内容不再局限于普通话识别,带口音的普通话和部分方言也逐渐被人工智能学习。本论文探讨在复杂噪声环境中,智能终端语音识别用户体验关键指标的测试方案、实施过程及数据分析。
The rapid development of artificial intelligence brings people an increasingly intelligent life. The application of intelligent speech recognition technology in intelligent terminals has covered existing Internet life services. Secondly, the content of speech recognition is no longer limited to Mandarin recognition, and the accented Mandarin and some dialects are also Gradually learned by artificial intelligence, this paper discusses the test plan, implementation process and result analysis of key indicators of the speech recognition user experience of intelligent terminals in complex environments.
引文
[1]张海波,周民伟,刘晓辉,等. 智能语音识别技术在医院临床的探索与应用[J]. 中国卫生信息管理杂志, 2017(5):660-663.
[2]董桂官,刘云,徐楠. 智能电视中文语音识别测试研究[J]. 电声技术, 2014(11):57-59.
[3]张策,韦鹏程,陆晓燕,等. 重庆方言语音识别系统的设计与实现[J]. 计算机测量与控制, 2018(1):256-259+263.
[4]曹晶晶,许洁萍,邵聖淇. 多噪声环境下的层级语音识别模型[J]. 计算机应用, 2018(6):1790-1794.
[5]武剑虹,黄石磊,匡镜明. 语音识别系统测试平台设计[J]. 电信技术, 2003(4):102-105.
[6]王海坤,潘嘉,刘聪. 语音识别技术的研究进展与展望[J]. 电信科学,2018(2):1-11.