The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper describes three methods for multiple fundamental frequencies estimation based on the multi-scale product analysis. The three methods use the autocorrelation of the multi-scale product analysis for the target pitch estimation. For the intrusion pitch, each one has its techniques. The first one uses the classic comb filtering. The second method employs the rectangular comb filter followed...
The fundamental frequency is one of the prosodic parameters, and many algorithms have been developed for estimating the fundamental frequency of speech signals. Most of them provide good results on good quality speech signals, but their performance degrades when dealing with noisy signals. Moreover, although some provide a probability for the voicing decision, none of them indicate how reliable the...
This paper proposes a novel method for estimation of strength of excitation (SoE) from speech signal. Using lowpass filtering to remove the effect of relatively high frequency vocal tract characteristics, we estimate epoch locations. Using these epoch locations we estimate SoE. The database used for evaluation purpose is CMU-ARCTIC database consisting of electroglottograph (EGG) signals. In addition,...
Speaker recognition is the process of identifying a speaker by his/her speech samples. By extracting the speaker-specific features from the speech samples, the recognition task can be done. The formant estimation of speech sample of specific speaker is important for feature extraction in speaker recognition, because the formants are unique and reflect the vocal tract information of a speaker. In the...
It is possible to divine a speaker's age, gender and emotion through his pitch independently of what he is saying. However, the same words can lead to different meanings with variations intonation. Meanwhile, precise pitch estimation is more or less difficult because tracked pitch contours are not perfectly smooth curves. In this paper, we introduce a new post-processing algorithm for the tracking...
The objective of present work is to improve the epoch estimation performance in high pass filtered (HPF) speech using conventional zero frequency filtering (ZFF) approach. The strength of impulse at zero frequency is significantly attenuated in case of HPF speech and hence shows significant degradation in epoch estimation performance by ZFF approach. Since linear prediction (LP) residual of speech...
This work proposes a modified zero frequency filtering (ZFF) method for epoch extraction from emotional speech. Epochs refers the instants of maximum excitation of the vocal tract. In the conventional ZFF method, the epochs are estimated by trend removing the output of the zero frequency resonator (ZFR) using the window length equal to the average pitch period of the utterance. Use of this fixed window...
A novel Discrete Fractional Cosine Transform implementation for pitch estimation of noisy speech using dominant harmonic is introduced in this paper. The basic idea is to preprocess the speech signal with discrete fractional cosine transform before using the rectified dominant harmonic for signal reshaping. The performance of the proposed method is tested and compared with the latest previous method...
In order to eliminate the musical noise remained in the results enhanced by short-time spectral attenuation techniques, this paper proposes a novel a priori SNR estimator. The proposed estimator is built on Burg-based power spectral estimation, which takes into account the properties in estimator of smoothness, accuracy and resolution, with the emphasis on their relationships and influences on de-noising...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.