Abstract:In order to track a rapid transient of pitch, a required frame length of some conventional pitch detection methods is too long. Although there are wavelet based pitch detection methods which require only a few periods of pitch for a frame, they are not robust enough against noise. This paper proposes a new pitch detection method which can work properly under noisy environments even if a frame duration is short. The proposed method consists of a power level detector, a signal analyzer, an autocorrelator, a voic… Show more
“…According to the result, doubled pitch is estimated in some durations where a fundamental frequency is less than 90 Hz. The result has almost the same characteristics as that of simulation shown in the previous study [1]. Furthermore, result of pitch detection for speech is shown in Fig.…”
Section: Real-time Pitch Detection Using the Clustersupporting
confidence: 77%
“…The previous study with respect to the pitch detection method, called the harmonic wavelet transform method [1] showed that it takes a longer processing time because the method uses continuous wavelet transform which requires heavy calculation cost due to many convolutions. The harmonic wavelet transform method consists of 5 blocks; a power level detector, a signal analyzer, an autocorrelator, a voiced-unvoiced detector and a lag time interpolator.…”
Section: Parallel Pitch Detection Algorithm Based On Harmonic Waveletmentioning
confidence: 99%
“…Following the final step is the same procedure as the previous study [1]. It cannot be parallelized due to the algorithm.…”
Section: Parallel Pitch Detection Algorithm Based On Harmonic Waveletmentioning
confidence: 99%
“…One of the algorithms is the pitch detection algorithm, called harmonic wavelet transform [1]. Performance of the harmonic wavelet transform method is better than those of conventional methods [2,3].…”
A high performance pitch detection algorithm, called harmonic wavelet transform method, was proposed. Since the algorithm is based on a continuous wavelet transform, the cost of computation is high. However, real-time processing of the algorithm is required for some acoustical applications, such as multi-modal interface which can take into account of human emotion. Digital Signal Processor (DSP) is suitable for implementation due to its compactness. However, implementaion of the algorithm on DSP costs too much with respect to both time and funds. In order to release the issues, one of other devices is a cluster system. The cluster system can be constructed with ease because the computer node has recently becomes inexpensive. Moreover, software packages for parallel and distributed computing can be obtained without difficulty. From the viewpoint of acoustical signal processing services on the Internet, the implementaion on network connected systems, such as the cluster system, becomes an important issue for ubiquitous and grid computing. This paper proposes the parallel algorithm of the harmonic wavelet transform method. Furthermore, the proposed algorithm is implemented on a signal processing system based on cluster system. As a result, the proposed parallel algorithm is executed in real-time due to both the proposed parallel algorithm and the constructed real-time signal processing system.
“…According to the result, doubled pitch is estimated in some durations where a fundamental frequency is less than 90 Hz. The result has almost the same characteristics as that of simulation shown in the previous study [1]. Furthermore, result of pitch detection for speech is shown in Fig.…”
Section: Real-time Pitch Detection Using the Clustersupporting
confidence: 77%
“…The previous study with respect to the pitch detection method, called the harmonic wavelet transform method [1] showed that it takes a longer processing time because the method uses continuous wavelet transform which requires heavy calculation cost due to many convolutions. The harmonic wavelet transform method consists of 5 blocks; a power level detector, a signal analyzer, an autocorrelator, a voiced-unvoiced detector and a lag time interpolator.…”
Section: Parallel Pitch Detection Algorithm Based On Harmonic Waveletmentioning
confidence: 99%
“…Following the final step is the same procedure as the previous study [1]. It cannot be parallelized due to the algorithm.…”
Section: Parallel Pitch Detection Algorithm Based On Harmonic Waveletmentioning
confidence: 99%
“…One of the algorithms is the pitch detection algorithm, called harmonic wavelet transform [1]. Performance of the harmonic wavelet transform method is better than those of conventional methods [2,3].…”
A high performance pitch detection algorithm, called harmonic wavelet transform method, was proposed. Since the algorithm is based on a continuous wavelet transform, the cost of computation is high. However, real-time processing of the algorithm is required for some acoustical applications, such as multi-modal interface which can take into account of human emotion. Digital Signal Processor (DSP) is suitable for implementation due to its compactness. However, implementaion of the algorithm on DSP costs too much with respect to both time and funds. In order to release the issues, one of other devices is a cluster system. The cluster system can be constructed with ease because the computer node has recently becomes inexpensive. Moreover, software packages for parallel and distributed computing can be obtained without difficulty. From the viewpoint of acoustical signal processing services on the Internet, the implementaion on network connected systems, such as the cluster system, becomes an important issue for ubiquitous and grid computing. This paper proposes the parallel algorithm of the harmonic wavelet transform method. Furthermore, the proposed algorithm is implemented on a signal processing system based on cluster system. As a result, the proposed parallel algorithm is executed in real-time due to both the proposed parallel algorithm and the constructed real-time signal processing system.
“…Therefore, a wide variety of algorithms for pitch detection have been proposed in the speech processing literature, such as the autocorrelation, cepstrum-based methods LPC method and Average magnitude difference function and so on [6]. Since the glottal closure is marked by a sharp discontinuity in the speech signal, it can in some sense be related to the edge detection problem in image processing.…”
Automatic speaker gender identification based on the speech feature has important application in the audio processing and analysis field. In order to overcome the conventional linear parameters in the speaker feature lack of gender characteristics, in this paper, nonlinear parameters such as the fractal dimension and fractal complexity as feature space effective compensations are presented. Firstly, use lifting scheme to extract pitch; Then extract the speech fractal dimension; Finally, according Takens theorem, time delay method is used to reconstruct phase space of fractal dimension sequence, fractal dimension complexity is obtained by calculating Approximate Entropy. Three dimension feature vectors constructed by the pitch, the fractal dimension and the fractal dimension complexity are applied to speaker gender identification. Results show as the identification system based on the new method introduces the non-linear parameters, its accuracy and stability are effectively improved compared with the traditional linear method identification systems. The new nonlinear method provides new ideas for speaker gender identification of a new line of thought.
This paper describes pitch estimation of Marathi spoken numbers which are extracted the features from various speech signals. The speech frequencies of Marathi spoken numbers are acquired by various male and female speakers. The pitch frequencies are normalized using PRAAT tool. The pitch contours are compared with pitch detector. The autocorrelation and cepstral methods are used to estimate speech frequency. Pitch detection is calculated by statistical methods and similarity is measured by Euclidian distance. The pitch frequency results found to be satisfactory. The average mean of frequency varies from 1.48 to 2.03 and standard deviation varies from 0.84 to 1.38 in Hz.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.