• MALSORI
• /
• no.56
• /
• pp.159-172
• /
• 2005

This paper analyzes the vocal tract area estimation algorithm used as a part of a speech analysis program to help deaf children correct their pronunciations by comparing their vocal tract shape with normal children's. Assuming that a vocal tract is a concatenation of cylinder tubes with a different cross section, we compute the relative vocal tract area of each tube using the reflection coefficients obtained from linear predictive coding. Then, we obtain the absolute vocal tract area by computing the height of lip opening with a formula modified for children's speech. Using the speech data for five Korean vowels (/a/, /e/, /i/, /o/, and /u/), we investigate the effects of the sampling frequency, frame size, and model order on the estimated vocal tract shape. We compare the vocal tract shapes obtained from deaf and normal children's speech.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• pp.51-54
• /
• 2005

This paper analyzes the vocal tract area estimation algorithm used as a part of a speech analysis program to help deaf children correct their pronunciations by comparing their vocal tract shape with normal children's. Assuming that a vocal tract is a concatenation of cylinder tubes with a different cross section, we compute the relative vocal tract area of each tube using the reflection coefficients obtained from linear predictive coding. Then, obtain the absolute vocal tract area by computing the height of lip opening with a formula modified for children's speech. Using the speech data for five Korean vowels (/a/, /e/, /i/, /o/, and /u/), we investigate the effects of the sampling frequency, frame size, and model order. We compare vocal tract shapes obtained from deaf and normal children's speech.

• Speech Sciences
• /
• v.14 no.4
• /
• pp.179-200
• /
• 2007

In voice pathology, various measurements calculated from pitch values are proposed to show voice quality. However, those measurements frequently seem to be inaccurate and unreliable because they are based on some wrong pitch values determined from pathological voice data. In order to solve the problem, we compared several pitch estimation methods to propose a better one in pathological voices. From the database of 99 pathological voice and 30 normal voice data, errors derived from pitch estimation were analyzed and compared between pathological and normal voice data or among the vowels produced by patients with benign vocal fold lesions. Results showed that gross pitch errors were observed in the cases of pathological voice data. From the types of pathological voices classified by the degree of aperiodicity in the speech signals, we found that pitch errors were closely related to the number of aperiodic segments. Also, the autocorrelation approach was found to be the most robust pitch estimation in the pathological voice data. It is desirable to conduct further research on the more severely pathological voice data in order to reduce pitch estimation errors.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.1
• /
• pp.49-54
• /
• 2016

In this paper, we propose a vocal separation method using weighted ${\beta}$-order minimum mean wquare error estimation (WbE) based on kernel back-fitting algorithm. In spoken speech enhancement, it is well-known that the WbE outperforms the existing Bayesian estimators such as the minimum mean square error (MMSE) of the short-time spectral amplitude (STSA) and the MMSE of the logarithm of the STSA (LSA), in terms of both objective and subjective measures. In the proposed method, WbE is applied to a basic iterative kernel back-fitting algorithm for improving the vocal separation performance from monaural music signal. The experimental results show that the proposed method achieves better separation performance than other existing methods.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.3
• /
• pp.227-236
• /
• 2013

In this paper, we present a vocal suppression algorithm that can enhance the quality of music signal coded using Spatial Audio Object Coding (SAOC) in Karaoke mode. The residual vocal component in the coded music signal is estimated by using a cross prediction method in which the music signal coded in Karaoke mode is used as the primary input and the vocal signal coded in Solo mode is used as a reference. However, the signals are extracted from the same downmix signal and highly correlated, so that the music signal can be severely damaged by the cross prediction. To prevent this, a psycho-acoustic disturbance rule is proposed, in which the level of disturbance to the reference input of the cross prediction filter is adapted according to the auditory masking property. Objective and subjective test were performed and the results confirm that the proposed algorithm offers improved quality.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.4
• /
• pp.261-266
• /
• 2017

In this paper, we propose a vocal and nonvocal separation method which uses a combination of kernel model and LSTM (Long-Short Term Memory) networks. Conventional vocal and nonvocal separation methods estimate the vocal component even in sections where only non-vocal components exist. This causes a problem of the source estimation error. Therefore we combine the existing kernel based separation method with the vocal/nonvocal classification based on LSTM networks in order to overcome the limitation of the existing separation methods. We propose a parallel combined separation algorithm and series combined separation algorithm as combination structures. The experimental results verify that the proposed method achieves better separation performance than the conventional approaches.

• Speech Sciences
• /
• v.12 no.4
• /
• pp.43-52
• /
• 2005

The common form of pre-emphasis filter is $H(z)\;=\;1\;- az^{-1}$, where a typically lies between 0.9 and 1.0 in voiced signal. Also, this value reflects the degree of filter and equals R(1)/R(0) in Auto-correlation method. This paper proposes a new flattening algorithm to compensate the weaked high frequency components that occur by vocal cord characteristic. We used interval information of LSP to estimate formant frequency. After obtaining the value of slope and inverse slope using linear interpolation among formant frequency, flattening process is followed. Experimental results show that the proposed algorithm flattened the weaked high frequency components effectively. That is, we could improve the flattened characteristics by using interval information of LSP as flattening factor at the process that compensates weaked high frequency components.

• Journal of Internet Computing and Services
• /
• v.4 no.3
• /
• pp.9-14
• /
• 2003

The method of vocal tract normalization is a successful method for improving the accuracy of inter-speaker normalization. In this paper, we present an intra-speaker warping factor estimation based on pitch alteration utterance. The feature space distributions of untransformed speech from the pitch alteration utterance of intra-speaker would vary due to the acoustic differences of speech produced by glottis and vocal tract. The variation of utterance is two types: frequency and amplitude variation. The vocal tract normalization is frequency normalization among inter-speaker normalization methods. Therefore, we have to consider amplitude variation, and it may be possible to determine the amplitude warping factor by calculating the inverse ratio of input to reference pitch. k, the recognition results, the error rate is reduced from 0.4% to 2.3% for digit and word decoding.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.4
• /
• pp.383-391
• /
• 2009

In speech signal processing, speech signal corrupted by noise should be enhanced to improve quality. Usually noise estimation methods need flexibility for variable environment. Noise profile is renewed on silence region to avoid effects of speech properties. So we have to preprocess finding voice region before noise estimation. However, if received signal does not have silence region, we cannot apply that method. In this paper, we proposed SNR estimation method for continuous speech signal. The waveform which is stationary region of voiced speech is very correlated by pitch period. So we can estimate the SNR by correlation of near waveform after dividing a frame for each pitch. For unvoiced speech signal, vocal track characteristic is reflected by noise, so we can estimate SNR by using spectral distance between spectrum of received signal and estimated vocal track. Lastly, energy of speech signal is mostly distributed on voiced region, so we can estimate SNR by the ratio of voiced region energy to unvoiced.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.407-408
• /
• 2007

Robust pitch estimation is an important study in many areas of speech processing. In voice pathology, diverse statistics extracted form pitch were commonly used to test voice quality. In this study, we compared several established pitch detection algorithms (PDAs) for verification of adequacy of the PDAs. In the database of total pathological voices of 99 and normal voices of 30, an analysis of errors related with pitch detection was evaluated between pathological and normal voices, or among the types of pathological voices such as benign vocal fold lesions; polyp, nodule, and cysts. Consequently, it is required to survey the severity of tested voice in order to obtain accurate pitch estimates.