RESEARCH ON THE ANALYSES OF THE INFORMATION IN BABY CRIES AND THE DEVELOPMENT OF THE AUTOMATIC RECOGNITION SYSTEM

婴儿哭声信息分析及自动识别系统开发研究

• 批准号: 13650430
• 负责人: ARAKAWA Kaoru
• 金额: $ 2.62万
• 依托单位: MEIJI UNIVERSITY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2001
• 资助国家: 日本
• 起止时间: 2001 至 2002
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-13650430/
• 关键词: baby cries; speech analysis; babies and infants; signal processing; childcare; state estimation; nonlinear filter; noise reduction; 音声解析; 泣き声; 非線形ディジタルフィルタ; ルールベースシステム; 意味情報解析; サウンドスペクトログラム

A way of computer analyses is proposed for crying babies' voice in order to recognize their mental status.Since babies do not have language, they just cry when they are in some uncomfortable situation. Mothers try to avoid the cause for the uncomfortableness, but it is sometimes difficult to recognize why the babies are crying by just observing them. In this case, mothers cannot stop the babies crying and then get into great trouble. Such a problem in taking care of babies can be solved, if the mental situation of babies is recognized automatically by analyzing some signs from them.In this research, a method for recognizing the mental status of crying babies is proposed by analyzing their voice in the frequency domain. Especially, a signal processing and rule-base system is developed to classify the crying voice when they are hungry and that when they are sleepy. Applying the system to some real babies voice, we showed that about 80% of the data were classified correctly by this system, although they cannot be classified correctly by human audition. The baby cries when they had pain are also examined. Moreover, a new type of nonlinear digital filter is proposed to reduce the noise from environment which is added to speech signal. The high performance of this filter is also verified for actual speech signals. This filter is effective as a pre-processing system of the baby cries classifier.

提出了一种对哭闹婴儿的声音进行计算机分析的方法，以识别婴儿的心理状态。由于婴儿没有语言，当他们处于不舒服的情况时，他们只会哭。母亲们试图避免造成不适的原因，但有时很难仅仅通过观察婴儿来识别婴儿哭泣的原因。在这种情况下，母亲们无法让婴儿停止哭泣，然后陷入大麻烦。如果通过分析婴儿的一些体征来自动识别婴儿的心理状态，就可以解决这一问题。本研究提出了一种通过对哭闹婴儿的声音进行频域分析来识别婴儿心理状态的方法。特别是，开发了一个信号处理和规则库系统，对饥饿和困倦时的哭声进行分类。将该系统应用于一些真实的婴儿语音，我们发现该系统对大约80%的数据进行了正确的分类，尽管这些数据不能通过人的听觉来正确地分类。婴儿在疼痛时会哭，也会进行检查。此外，还提出了一种新型的非线性数字滤波器，以消除环境噪声对语音信号的影响。实际语音信号也验证了该滤波器的高性能。该过滤器作为婴儿哭声分类器的一个预处理系统是有效的。

项目成果

Kaoru Arakawa, Hiroaki Watabe, Yasuhiko Arakawa: "Nonlinear digital filters which are suitable for hardware implementation"Systems, Control and Information. vol.47, no.1, Jan. 2003. 44-49

Kaoru Arakawa、Hiroaki Watabe、Yasuhiko Arakawa：“适合硬件实现的非线性数字滤波器”系统、控制和信息。

Takuya Okada, Shigeyuki Miyazaki, Kaoru Arakawa, Hiroaki Watabe, and Yasuhiko Arakaw: "Nonlinear Filter Bank Using ε-Filters and Its Application to Face Image Processing"Proc. IEEE ISPACS2002. B3-2, Nov. 2002.

Takuy​​a Okada、Shigeyuki Miyazaki、Kaoru Arakawa、Hiroaki Watabe 和 Yasuhiko Arakawa：“使用 ε 滤波器的非线性滤波器组及其在人脸图像处理中的应用”Proc. IEEE ISPACS2002，2002 年 11 月。

J.Hirose, S.Ito et al. (2nd/6): ""Occurrence of a major food allergen", ovomucoid, in human breast milk as an immune complex"Biosci.Biotechnol Biochem.. 65. 1438-1440 (2001)

J.Hirose、S.Ito 等人。

荒川 薫: "ハードウェアでの実装に適した非線形ディジタルフィルタ"システム制御情報学会誌. 47・1. 44-49 (2003)

荒川薰：“适合硬件实现的非线性数字滤波器”系统、控制和信息工程师学会杂志47・1（2003）。

Kaoru Arakawa, Kohei Matsuura, Hiroaki Watabe, Yasuhiko Arakawa: "A method to reduce noise on speech signal by a component-separating ε-filter"Trans. IEICE, vol.J85-A, no10, Oct. 2002. 1059-1069

Kaoru Arakawa、Kohei Matsuura、Hiroaki Watabe、Yasuhiko Arakawa：“一种通过分量分离 ε 滤波器降低语音信号噪声的方法”Trans。IEICE，第 J85-A 卷，第 10 期，2002 年 10 月。1059-1069