Page 73 - 《应用声学》2024年第6期

第 43 卷 第 6 期 苌文涵等： 结合改进 DRSE-GCNN 的电力调度语声识别模型 1249

and CTC[J]. Computer Engineering and Design, 2020, 2020, 47(S2): 78–82, 91.
41(9): 2650–2654. [27] 卢麒仰, 徐超林, 杨育, 等. 基于改进 YOLOv5 网络的印刷电
[18] 张晓旭, 马志强, 刘志强, 等. Transformer 在语音识别任务 路板缺陷检测 [J]. 电子器件, 2023, 46(6): 1504–1508.
中的研究现状与展望 [J]. 计算机科学与探索, 2021, 15(9): Lu Qiyang, Xu Chaolin, Yang Yu, et al. Printed circuit
1578–1594. board defect detection based on improved YOLOv5 net-
Zhang Xiaoxu, Ma Zhiqiang, Liu Zhiqiang, et al. The work[J]. Chinese Journal of Electron Devices, 2023, 46(6):
current research status and prospects of Transformer in 1504–1508.
speech recognition tasks[J]. Journal of Frontiers of Com- [28] 曾伟, 武华, 冯秀平, 等. 一种低反向恢复电流的无电压回跳
puter Science and Technology, 2021, 15(9): 1578–1594. RC-IGBT 设计 [J]. 电子器件, 2023, 46(6): 1480–1483.
[19] 吕坤儒, 吴春国, 梁艳春, 等. 融合语言模型的端到端中文语 Zeng Wei, Wu Hua, Feng Xiuping, et al. A voltage free
音识别算法 [J]. 电子学报, 2021, 49(11): 2177–2185. rebound RC-IGBT design with low reverse recovery cur-
Lyu Kunru, Wu Chunguo, Liang Yanchun, et al. End rent[J]. Chinese Journal of Electron Devices, 2023, 46(6):
to end Chinese speech recognition algorithm integrating 1480–1483.
language models[J]. Acta Electronica Sinica, 2021, 49(11): [29] 邵良杉, 周玉. 基于语义规则与 RNN 模型的在线评论情感分
2177–2185. 类研究 [J]. 中文信息学报, 2019, 33(6): 124–131.
[20] 于蒙, 李雄, 杨海潮, 等. 基于图像识别的苹果的等级分级研 Shao Liangshan, Zhou Yu. Research on sentiment classi-
究 [J]. 自动化与仪表, 2019, 34(7): 39–43, 47. fication of online comments based on semantic rules and
Yu Meng, Li Xiong, Yang Haichao, et al. Research on RNN model[J]. Journal of Chinese Information Process-
apple grading based on image recognition[J]. Automation ing, 2019, 33(6): 124–131.
& Instrumentation, 2019, 34(7): 39–43, 47. [30] 陈佳伟, 韩芳, 王直杰. 基于自注意力门控图卷积网络的特定
[21] 李云红, 梁思程, 贾凯莉, 等. 一种改进的 DNN-HMM 的语 目标情感分析 [J]. 计算机应用, 2020, 40(8): 2202–2206.
音识别方法 [J]. 应用声学, 2019, 38(3): 371–377. Chen Jiawei, Han Fang, Wang Zhijie. Specific target sen-
Li Yunhong, Liang Sicheng, Jia Kaili, et al. An improved timent analysis based on self attention gated graph con-
DNN-HMM speech recognition method[J]. Journal of Ap- volutional network[J]. Journal of Computer Applications,
plied Acoustics, 2019, 38(3): 371–377. 2020, 40(8): 2202–2206.
[22] 王晶晶, 姜明, 张旻. 基于上下文感知的方面类别情感分类 [J]. [31] 王阁藩, 刘博, 李恺, 等. 一种低回踢噪声低失调高频 CMOS
计算机应用研究, 2021, 38(6): 1770–1774. 比较器 [J]. 电子器件, 2023, 46(6): 1474–1479.
Wang Jingjing, Jiang Ming, Zhang Min. Context aware Wang Gefan, Liu Bo, Li Kai, et al. A low bounce noise,
aspect category sentiment classification[J]. Computer Ap- low offset high-frequency CMOS comparator[J]. Chinese
plication Research, 2021, 38(6): 1770–1774. Journal of Electron Devices, 2023, 46(6): 1474–1479.
[23] 王智超, 徐及, 张鹏远, 等. 卷积神经网络声学模型的结构 [32] 陈蕾, 郑伟彦, 余慧华, 等. 基于 BERT 的电网调度语音识别
优化和加速计算 [J]. 重庆邮电大学学报 (自然科学版), 2018, 语言模型研究 [J]. 电网技术, 2021, 45(8): 2955–2961.
30(3): 416–422. Chen Lei, Zheng Weiyan, Yu Huihua, et al. Research
Wang Zhichao, Xu Ji, Zhang Pengyuan, et al. Struc- on speech recognition language model for power grid dis-
tural optimization and accelerated computation of con- patching based on BERT[J]. Power System Technology
volutional neural network acoustic model[J]. Journal Technology, 2021, 45(8): 2955–2961.
of Chongqing University of Posts and Telecommunica- [33] Sultana S, Iqbal M Z, Selim M R, et al. Bangla speech
tions(Natural Science Edition), 2018, 30(3): 416–422. emotion recognition and cross-lingual study using deep
[24] Singh A, Kabra R, Kumar R, et al. On-device sys- CNN and BLSTM networks[J]. IEEE Access, 2022, 10:
tem for device directed speech detection for improving 564–578.
human computer interaction[J]. IEEE Access, 2021, 9: [34] 胡章芳, 蹇芳, 唐珊珊, 等. DFSMN-T: 结合强语言模型
131758–131766. Transformer 的中文语音识别 [J]. 计算机工程与应用, 2022,
[25] 杜永萍, 刘杨, 贺萌. 基于对抗式分布对齐的跨域方面级情感 58(9): 187–194.
分析 [J]. 模式识别与人工智能, 2021, 34(1): 87–94. Hu Zhangfang, Jian Fang, Tang Shanshan, et al. DFSMN-
Du Yongping, Liu Yang, He Meng. Cross domain aspect T: Chinese speech recognition combined with strong lan-
level sentiment analysis based on adversarial distribution guage model Transformer[J]. Computer Engineering and
alignment[J]. Pattern Recognition and Artificial Intelli- Applications, 2022, 58(9): 187–194.
gence, 2021, 34(1): 87–94. [35] 张威, 刘晨, 费鸿博, 等. 基于 DL-T 及迁移学习的语音识别
[26] 景丽, 李曼曼, 何婷婷. 结合扩充词典与自监督学习的网络评 研究 [J]. 工程科学学报, 2021, 43(3): 433–441.
论情感分类 [J]. 计算机科学, 2020, 47(S2): 78–82, 91. Zhang Wei, Liu Chen, Fei Hongbo, et al. Research on
Jing Li, Li Manman, He Tingting. Combining extended speech recognition based on DL-T and transfer learn-
dictionaries with self supervised learning for sentiment ing[J]. Chinese Journal of Engineering, 2021, 43(3):
classification in online comments[J]. Computer Science, 433–441.