In this paper, we propose an end-to-end Mandarin tone classification method from continuous speech utterances utilizing both the spectrogram and the short-term context information as the input. Both spectrograms and context segment features are used to train the tone classifier. We first divide the spectrogram frames into syllable segments using force alignment results produced by an ASR model. Then we extract the short-term segment features to capture the context information across multiple syllables. Feeding both the spectrogram and the short-term context segment features into an end-to-end model could significantly improve the performance. Experiments are performed on a large-scale open-source Mandarin speech dataset to evaluate the proposed method. Results show that this method improves the classification accuracy from 79.5% to 92.6% on the AISHELL3 database.
AMNet: An Acoustic Model Network for Enhanced Mandarin Speech Synthesis
Xinjiang University（新疆大学）；School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center（新疆多模态智能处理与信息安全工程技术研究中心）
Attentive batch normalization for lstm-based acoustic modeling of speech recognition
National Engineering Laboratory for Speech and Language Information Processing（国家语音与语言信息处理工程实验室）；University of Science and Technology of China（中国科学技术大学）
Unimodal Aggregation for CTC-based Speech Recognition
Zhejiang University（浙江大学）；School of Engineering, Westlake University（西湖大学工程学院）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院先进技术研究所）
Segment-Level Mandarin Chinese Speech-Based Cognitive Impairment Detection via an Autoencoder with Contrastive Learning
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院）；Key Laboratory of System Control and Information Processing, Ministry of Education of China（教育部系统控制与信息处理重点实验室）；Shanghai Key Laboratory of Perception and Control in Industrial Network Systems（上海市工业网络系统感知与控制重点实验室）；Department of Computer Science and Engineering, University of Bologna（博洛尼亚大学计算机科学与工程系）；Department of Mathematical, Physical and Computer Sciences, University of Parma（帕尔马大学数学、物理与计算机科学系）
Language Identification with Deep Bottleneck Features
Pattern Recognition and Intelligent System Lab., Beijing University of Posts and Telecommunications（北京邮电大学模式识别与智能系统实验室）
提出了一种基于长短期记忆（Long Short Term Memory，LSTM）神经网络的端到端短话语语音语言识别（SLD）方法，该方法特别适用于智能车辆中的SLD应用。用于LSTM学习的特征由迁移学习方法生成。利用深度神经网络（DNN）的瓶颈特征对普通话语音进行分类，并将其用于LSTM训练。为了提高短话语的SLD精度，采用了基于相位声码器的时间尺度修正（TSM）方法来降低和提高测试话语的语音等级。通过对正常语音、降低速率语音和提高速率语音进行拼接，可以延长测试语音的长度，从而提高SLD系统的性能。在AP 17-OLR语料库上的实验结果表明，本文提出的方法能够有效地提高SLD的性能，尤其是对时长为1 s和3 s的短话语的识别效果更好。
