The cognitive performance-based dimensional emotion recognition in whispered speech is studied.First,the whispered speech emotion databases and data collection methods are compared, and the character of emotion expres...The cognitive performance-based dimensional emotion recognition in whispered speech is studied.First,the whispered speech emotion databases and data collection methods are compared, and the character of emotion expression in whispered speech is studied,especially the basic types of emotions.Secondly,the emotion features for whispered speech is analyzed,and by reviewing the latest references,the related valence features and the arousal features are provided. The effectiveness of valence and arousal features in whispered speech emotion classification is studied.Finally,the Gaussian mixture model is studied and applied to whispered speech emotion recognition. The cognitive performance is also considered in emotion recognition so that the recognition errors of whispered speech emotion can be corrected.Based on the cognitive scores,the emotion recognition results can be improved.The results show that the formant features are not significantly related to arousal dimension,while the short-term energy features are related to the emotion changes in arousal dimension.Using the cognitive scores,the recognition results can be improved.展开更多
An improved method based on minimum mean square error-short time spectral amplitude （MMSE-STSA） is proposed to cancel background noise in whispered speech. Using the acoustic character of whispered speech, the algor...An improved method based on minimum mean square error-short time spectral amplitude （MMSE-STSA） is proposed to cancel background noise in whispered speech. Using the acoustic character of whispered speech, the algorithm can track the change of non-stationary background noise effectively. Compared with original MMSE-STSA algorithm and method in selectable mode Vo-coder （SMV）, the improved algorithm can further suppress the residual noise for low signal-to-noise radio （SNR） and avoid the excessive suppression. Simulations show that under the non-stationary noisy environment, the proposed algorithm can not only get a better performance in enhancement, but also reduce the speech distortion.展开更多
The Autoregressive Moving Average （ARMA） model for whispered speech is proposed. with normal speech, whispered speech has no fundamental frequency because of the glottis being semi-opened and turbulent flow being cr...The Autoregressive Moving Average （ARMA） model for whispered speech is proposed. with normal speech, whispered speech has no fundamental frequency because of the glottis being semi-opened and turbulent flow being created, and formant shifting exists in the lower frequency region due to the narrowing of the tract in the false vocal fold regions and weak acoustic coupling with the aubglottal system. Analysis shows that the effect of the subglottal system is to introduce additional pole-zero pairs into the vocal tract transfer function. Theoretically, the method based on an ARMA process is superior to that based on an AR process in the spectral analysis of the whispered speech. Two methods, the least squared modified Yule-Walker likelihood estimate （LSMY） algorithm and the Frequency-Domain Steiglitz-Mcbide （FDSM） algorithm, are applied to the ARMA mfldel for the whispered speech. The performance evaluation shows that the ARMA model is much more appropriate for representing the whispered speech than the AR model, and the FDSM algorithm provides a name acorate estimation of the whispered speech spectral envelope than the LSMY algorithm with higher conputational complexity.展开更多
A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize...A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize the enhanced whisper. A novel noise robust feature called Gammatone feature cosine coefficients （GFCCs） extracted by an auditory periphery model is derived and used for the binary mask estimation. The intelligibility performance of the proposed method is evaluated and compared with the traditional speech enhancement methods. Objective and subjective evaluation results indicate that the proposed method can effectively improve the intelligibility of whispered speech which is contaminated by noise. Compared with the power subtract algorithm and the log-MMSE algorithm, both of which do not improve the intelligibility in lower signal-to-noise ratio （SNR） environments, the proposed method has good performance in improving the intelligibility of noisy whisper. Additionally, the intelligibility of the enhanced whispered speech using the proposed method also outperforms that of the corresponding unprocessed noisy whispered speech.展开更多
Some factors influencing the intelligibility of the enhanced whisper in the joint time-frequency domain are evaluated. Specifically, both the spectrum density and different regions of the enhanced spectrum are analyze...Some factors influencing the intelligibility of the enhanced whisper in the joint time-frequency domain are evaluated. Specifically, both the spectrum density and different regions of the enhanced spectrum are analyzed. Experimental results show that for a spectrum of some density, the joint time-frequency gain-modification based speech enhancement algorithm achieves significant improvement in intelligibility. Additionally, the spectrum region where the estimated spectrum is smaller than the clean spectrum, is the most important region contributing to intelligibility improvement for the enhanced whisper. The spectrum region where the estimated spectrum is larger than twice the size of the clean spectrum is detrimental to speech intelligibility perception within the whisper context.展开更多
基金The National Natural Science Foundation of China(No.11401412)
文摘The cognitive performance-based dimensional emotion recognition in whispered speech is studied.First,the whispered speech emotion databases and data collection methods are compared, and the character of emotion expression in whispered speech is studied,especially the basic types of emotions.Secondly,the emotion features for whispered speech is analyzed,and by reviewing the latest references,the related valence features and the arousal features are provided. The effectiveness of valence and arousal features in whispered speech emotion classification is studied.Finally,the Gaussian mixture model is studied and applied to whispered speech emotion recognition. The cognitive performance is also considered in emotion recognition so that the recognition errors of whispered speech emotion can be corrected.Based on the cognitive scores,the emotion recognition results can be improved.The results show that the formant features are not significantly related to arousal dimension,while the short-term energy features are related to the emotion changes in arousal dimension.Using the cognitive scores,the recognition results can be improved.
文摘An improved method based on minimum mean square error-short time spectral amplitude （MMSE-STSA） is proposed to cancel background noise in whispered speech. Using the acoustic character of whispered speech, the algorithm can track the change of non-stationary background noise effectively. Compared with original MMSE-STSA algorithm and method in selectable mode Vo-coder （SMV）, the improved algorithm can further suppress the residual noise for low signal-to-noise radio （SNR） and avoid the excessive suppression. Simulations show that under the non-stationary noisy environment, the proposed algorithm can not only get a better performance in enhancement, but also reduce the speech distortion.
基金supported by the Independent Innovation Foundation of Shandong University(No.2009JC004)the Natural Science Foundation of Shandong Province(No.Y2007G31)
文摘The Autoregressive Moving Average （ARMA） model for whispered speech is proposed. with normal speech, whispered speech has no fundamental frequency because of the glottis being semi-opened and turbulent flow being created, and formant shifting exists in the lower frequency region due to the narrowing of the tract in the false vocal fold regions and weak acoustic coupling with the aubglottal system. Analysis shows that the effect of the subglottal system is to introduce additional pole-zero pairs into the vocal tract transfer function. Theoretically, the method based on an ARMA process is superior to that based on an AR process in the spectral analysis of the whispered speech. Two methods, the least squared modified Yule-Walker likelihood estimate （LSMY） algorithm and the Frequency-Domain Steiglitz-Mcbide （FDSM） algorithm, are applied to the ARMA mfldel for the whispered speech. The performance evaluation shows that the ARMA model is much more appropriate for representing the whispered speech than the AR model, and the FDSM algorithm provides a name acorate estimation of the whispered speech spectral envelope than the LSMY algorithm with higher conputational complexity.
基金The National Natural Science Foundation of China (No.61231002,61273266,51075068,60872073,60975017, 61003131)the Ph.D.Programs Foundation of the Ministry of Education of China(No.20110092130004)+1 种基金the Science Foundation for Young Talents in the Educational Committee of Anhui Province(No. 2010SQRL018)the 211 Project of Anhui University(No.2009QN027B)
文摘A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize the enhanced whisper. A novel noise robust feature called Gammatone feature cosine coefficients （GFCCs） extracted by an auditory periphery model is derived and used for the binary mask estimation. The intelligibility performance of the proposed method is evaluated and compared with the traditional speech enhancement methods. Objective and subjective evaluation results indicate that the proposed method can effectively improve the intelligibility of whispered speech which is contaminated by noise. Compared with the power subtract algorithm and the log-MMSE algorithm, both of which do not improve the intelligibility in lower signal-to-noise ratio （SNR） environments, the proposed method has good performance in improving the intelligibility of noisy whisper. Additionally, the intelligibility of the enhanced whispered speech using the proposed method also outperforms that of the corresponding unprocessed noisy whispered speech.
基金The National Natural Science Foundation of China(No.61301295,61273266,61301219,61201326,61003131)the Natural Science Foundation of Anhui Province(No.1308085QF100,1408085MF113)+2 种基金the Natural Science Foundation of Jiangsu Province(No.BK20130241)the Natural Science Foundation of Higher Education Institutions of Jiangsu Province(No.12KJB510021)the Doctoral Fund of Anhui University
文摘Some factors influencing the intelligibility of the enhanced whisper in the joint time-frequency domain are evaluated. Specifically, both the spectrum density and different regions of the enhanced spectrum are analyzed. Experimental results show that for a spectrum of some density, the joint time-frequency gain-modification based speech enhancement algorithm achieves significant improvement in intelligibility. Additionally, the spectrum region where the estimated spectrum is smaller than the clean spectrum, is the most important region contributing to intelligibility improvement for the enhanced whisper. The spectrum region where the estimated spectrum is larger than twice the size of the clean spectrum is detrimental to speech intelligibility perception within the whisper context.
