Nonlinear analysis and classification of speech under stressed conditions

نویسندگان

  • Douglas A. Cairns
  • John H. L. Hansen
چکیده

The speech production system is capable of conveying an abundance of information with regards to sentence text, speaker identity, prosodics, as well as emotion and speaker stress. In an effort to better understand the mechanism of human voice communication, researchers have attempted to determine reliable acoustic indicators of stress using such speech production features as fundamental frequency (F0), intensity, spectral tilt, the distribution of spectral energy, and others. Their findings indicate that more work is necessary to propose a general solution. In this study, we hypothesize that speech consists of a linear and nonlinear component, and that the nonlinear component changes markedly between normal and stressed speech. To quantify the changes between normal and stressed speech, a classification procedure was developed based on the nonlinear Teaget Energy operator. The Teaget Energy operator provides an indirect means of evaluating the nonlinear component of speech. The system was tested using VC and CVC utterances from native speakers of English across the following speaking styles; neutral, loud, angry, Lombard effect, and clear. Results of the system evaluation show that loud and angry speech can be differentiated from neutral speech, while clear speech is more difficult to differentiate. Results also show that reliable classification of Lombard effect speech is possible, but system performance varies across speakers.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Nonlinear Analysis of Interaction with SVC in Stressed Power Systems: Effect of SVC Controller Parameters

In this paper, the effect of Static VAr Compensator (SVC) parameters on the nonlinear interaction of steam power plant turbine-generator set is studied using the Modal Series (MS) method. A second order representation of a power system equipped with SVC is developed and then by MS method the nonlinear interaction of torsional modes is assessed under various conditions and the most influencing f...

متن کامل

Classification of speech under stress based on features derived from the nonlinear Teager energy operator

Studies have shown that distortion introduced by stress or emotion can severely reduce speech recognition accuracy. Techniques for detecting or assessing the presence of stress could help neutralize stressed speech and improve robust-ness of speech recognition systems. Although some acoustic variables derived from linear speech production theory have been investigated as indicators of stress, t...

متن کامل

Recognition of stress in speech using wavelet analysis and Teager energy operator

The automatic recognition and classification of speech under stress has applications in behavioural and mental health sciences, human to machine communication and robotics. The majority of recent studies are based on a linear model of the speech signal. In this study, the nonlinear Teager Energy Operator (TEO) analysis was used to derive the classification features. Moreover, the TEO analysis w...

متن کامل

Nonlinear Analysis and Classiication of Speech under Stressed Conditions

The speech production system is capable of conveying an abundance of information with regards to sentence text, speaker identity, prosodics, as well as emotion and speaker stress. In an eeort to better understand the mechanism of human voice communication, researchers have attempted to determine reliable acoustic indicators of stress using such speech production features as fundamental frequenc...

متن کامل

Nonlinear feature based classification of speech under stress

Studies have shown that variability introduced by stress or emotion can severely reduce speech recognition accuracy. Techniques for detecting or assessing the presence of stress could help improve the robustness of speech recognition systems. Although some acoustic variables derived from linear speech production theory have been investigated as indicators of stress, they are not always consiste...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004