开具论文收录证明 >>

文献数据库（团队版） cqvip:为进一步提高智能电网调度语音识别的准确率,本文将深度学习技术引入了电力调度语音识别领域,提出了基于深度神经网络(deep neural network,DNN)的电力调度语音识别技术。针对电力调度专用术语以及某区域电网习惯调度用语,建立了电力调度语音识别基础语料库。通过应用深度神经网络-隐马尔可夫模型(deep neural network-hidden markov model,DNN-HMM)进行声学模型训练,并对电力调度语音材料制作,语音模型训练过程、端点检测、与D5000系统交互以及语音转文字的整套流程进行了论述。实践结果表明,采用DNN-HMM的电力调度语音识别性能要显著优于传统语音识别框架,即高斯混合-隐马尔可夫模型(gaussian mixture model-hidden markov model,GMM-HMM),采用所提方法进行电力调度语音识别准确率达94.63%。基于所提方法开发的电力调度语音识别系统在某区域电网调控中心的应用实例表明了所提方法的可行性与优良性。 1. Dual-input Control Interface for Deep Neural Network Based on Image/Speech Recognition [J] . Pai Neng-Sheng, Chen Yi-Hsun, Hung Chin-Pao, Sensors and materials 2019 ,第11期 2. Discriminative Learning of Filterbank Layer within Deep Neural Network Based Speech Recognition for Speaker Adaptation [J] . Hiroshi SEKI, Kazumasa YAMAMOTO, Tomoyosi AKIBA, IEICE transactions on information and systems 2019 ,第2期 3. Auxiliary Features from Laser-Doppler Vibrometer Sensor for Deep Neural Network Based Robust Speech Recognition [J] . Lei Sun, Jun Du, Zhipeng Xie, Journal of VLSI signal processing systems for signal, image, and video technology 2018 ,第7期 4. Exemplar-based speech enhancement for deep neural network based automatic speech recognition [C] . Baby Deepak, Gemmeke Jort F., Virtanen Tuomas, IEEE International Conference on Acoustics, Speech and Signal Processing 5. Non-linguistic Vocalization Recognition Based on Convolutional, Long Short-term Memory, Deep Neural Networks Qiu, Liang. 6. Multi-resolution speech analysis for automatic speech recognition using deep neural networks: Experiments on TIMIT Doroteo T. Toledano, María Pilar Fernández-Gallego, Alicia Lozano-Diez 7. Exemplar-based speech enhancement for deep neural network based automatic speech recognition Baby Deepak, Gemmeke Jort, Virtanen Tuomas, 3. SOUND MODELING AND VOICE RECOGNIZING METHOD FOR LONG-DISTANCE VOICE RECOGNITION BASED ON MULTI-INPUT DEEP NEURAL NETWORK [P] . 外国专利： KR20180084464A . 2018-07-25 机译：基于多输入深度神经网络的长途语音识别的声音建模与语音识别方法 4. Ensemble of Jointly Trained Deep Neural Network-based Acoustic Models for Reverberant Speech Recognition and Method for Recognizing Speech using the same [P] . 外国专利： KR101807948B1 . 2017-12-11 机译：联合训练的基于深度神经网络的混响语音识别声学模型的集成以及使用该模型的语音识别方法 5. Ensemble of Jointly Trained Deep Neural Network-based Acoustic Models for Reverberant Speech Recognition and Method for Recognizing Speech using the same [P] . 外国专利： KR20170119152A . 2017-10-26 机译：联合训练的基于深度神经网络的混响语音识别声学模型的集成以及使用该模型的语音识别方法