• Journal of Clinical Otolaryngology Head and Neck Surgery
• /
• v.29 no.2
• /
• pp.212-222
• /
• 2018

Background and Objectives : The purpose of this study was to compare the measured values of acoustic and auditory perceptual assessments between normal and functional dysphonia (FD) groups. Materials and Methods : 102 subjects with FD and 59 normal voice groups were participated in this study. Mid-vowel portion of the sustained vowel /a/ and two sentences of 'Sanchaek' were edited, concatenated, and analyzed by Praat script. And then auditory-perceptual (AP) rating was completed by three listeners. Results : The FD group showed higher acoustic voice quality index version 2.02 and version 3.01 (AVQIv2 and AVQIv3), slope, Hammarberg index (HAM), grade (G) and overall severity (OS), values than normal group. Additionally, smoothed cepstral peak prominence in Praat (PraatCPPS), tilt, low-to high spectral band energies (L/H ratio), long-term average spectrum (LTAS) in FD group were lower than normal voice group. And the correlation among measured values ranged from -0.250 to 0.960. In ROC curve analysis, cutoff values of AVQIv2, AVQIv3, PraatCPPS, slope, tilt, L/H ratio, HAM, and LTAS were 3.270, 2.013, 13.838, -22.286, -9.754, 369.043, 27.912, and 34.523, respectively, and the AUC of each analysis was over .890 in AVQIv2, AVQIv3, and PraatCPPS, over 0.731 in HAM, tilt, and slope, over 0.605 in LTAS and L/H ratio. Conclusions : In conclusion, AVQI and CPPS showed the highest predictive power for distinguishing between normal and FD groups. Acoustic analyses and AP rating as noninvasive examination can reinforce the screening capability of FD and help to establish efficient diagnosis and treatment process plan for FD.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.1
• /
• pp.48-55
• /
• 2010

It has a falling off in speech quality, especially when consecutive packet loss occurs, even if a vocoder implemented in the packet network has its own packet loss concealment (PLC) algorithm. PLC algorithm is divided into transmitter and receiver algorithm. Algorithm in the transmitter gives superior quality by additional information. however it is impossible to provide mutual compatibility and it occurs extra delay and transmission rate. The method applied in the receiver does not require additional delay. However, it sets limits to improve the speech quality. In this paper, we propose a new method that puts extra information for PLC in a part of Extension Header Data which is not used in RTP Header. It can solve the problem and obtain enhanced speech quality. There is no extra delay occurred by the proposed algorithm because there is a jitter buffer to adjust network delay in a receiver. Extra information, 16 bits each frame for G.729 PLC, is allocated for MA filter index in LP synthesis, excitation signal, excitation signal gain and residual gain reconstruction. It is because a transmitter sends speech data each 20 ms when it transfers RTP payload. As a result, the proposed method shows superior performance about 13.5%.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.155-163
• /
• 2009

In text-to-speech systems, the conversion of text into prosodic parameters is necessarily composed of three steps. These are the placement of prosodic boundaries. the determination of segmental durations, and the specification of fundamental frequency contours. Prosodic boundaries. as the most important and basic parameter. affect the estimation of durations and fundamental frequency. Break prediction is an important step in text-to-speech systems as break indices (BIs) have a great influence on how to correctly represent prosodic phrase boundaries, However. an accurate prediction is difficult since BIs are often chosen according to the meaning of a sentence or the reading style of the speaker. In Japanese, the prediction of an accentual phrase boundary (APB) and major phrase boundary (MPB) is particularly difficult. Thus, this paper presents a method to complement the prediction errors of an APB and MPB. First, we define a subtle BI in which it is difficult to decide between an APB and MPB clearly as a variable break (VB), and an explicit BI as a fixed break (FB). The VB is chosen using the classification and regression tree, and multiple prosodic targets in relation to the pith and duration are then generated. Finally. unit-selection is conducted using multiple prosodic targets. In the MOS test result. the original speech scored a 4,99. while proposed method scored a 4.25 and conventional method scored a 4.01. The experimental results show that the proposed method improves the naturalness of synthesized speech.

• MALSORI
• /
• no.21_24
• /
• pp.43-89
• /
• 1992

In this thesis, the prominent aspect of word accent in standard Korean is studied by auditory test and acoustic analysis experiment. The definition of 'accent' is, following Hoyoung Lee's discussion(1990), to be described as 'the means whereby a focused part of an utterance is made to stand out in order to concentrate the hearer's attention on it.' That is to say, the ten of 'accent' may be described in terms of phonological phenomenon and the accented syllable can be phonetically prominent as the result of those phonological process. Prosodic features may have different characteristics in different languages whether they contain linguistically important functions or not. Thus the characteristics of word accent in standard Korean will be determined as the content and trait of prosodic features. Following this viewpoint, present study looked over prosodic features which may effect the characteristics of word accent in standard Korean, through systematic experimental procedure. And the result of this experiment has been verified by statistical method, the T-test, for the purpose of identifying the relatedness among prosodic features(parameters). This thesis, therefore, aimed to investigate the intrinsic acoustic and physical qualities of the word accent in standard Korean. Nonsense words composed by 'mal' and 'ma' which can be divided into 'heavy syllable' and 'light syllable' quoted from Hyman(1975) have been classified into 28 types with respect to syllable numbers(2 syl., 3 sy1., 4 syl.) and these words have become the target of auditory test and acoustic experiment. As the result of those experimental Procedures, the word accent in standard Korean may be said that it has a tendency of fixing first two syllables regardless of syllable numbers. The syllable types of HH, HL, LL in the first two syllables may be prominent at first syllable and the type of H may be at second syllable. Various prosodic features(parameters) including duration, intensity, and Fo(purely phonetic terms) were also strengthened in those positions. The result of this experiment can be cleared up like these : 1. The most important feature is proved as 'duration', the feature of intensity resulted in more subsidiary one than the feature of duration. 2. Fo( fundamental frequency) could be observed as having some coherent contour through almost all syllable types(99 ％), that is, in 2 syllable types, it had rising contour, in 2 syllable types, rising-falling contour, and in 4 syllable types, it contained rising-falling-rising contour. The result of auditory test was different with those contour forms of all Fo surveyed. With respect to these results, the discuss for Fo is determined' to be excluded comparing other features. 3. Finally, this thesis resulted in a decision that the word accent in standard Korean may has fixed(somewhat weaker) accent, especially fixed at first two syllables in almost all words. 4. Various kinds of syllable types related with 2,3,4 syllables, therefore, can be reclassified into 4 types of HH, HL, LH, LL following the concept of accent fixing placement(i.e. first two syllables). In these 4 types, the types of HH, HL, LL were prominent at the position of the first syllable , and the type of LH was prominent at the second syllable otherwise.

• Journal of Sasang Constitutional Medicine
• /
• v.12 no.1
• /
• pp.144-156
• /
• 2000

Purpose of this study is to help classifying Sasang Constitution through correlation with Larynx waveform. This study was done it under the suppose that Sasang Constitution would be correlation with Larynx waveform. The following result were obtained about correlation between Erectroglottograph waveform and Sasang Constitution by analysis EGG program. 1. Taeumin was lower than Soyangin in Open Std Deviation, Contact Std Deviation of male/a/(0.5sec) 2. Soeyangin was high compared with the others in Pitch range of maie/a/(2.5sec) 3. Taeumin was higher than Soeumin in Pitch range, Soeyangin in pitch Maximum, and the others in Pitch Std Deviation of female/e/(0.5sec) 4. Taeumin was higher than Soeumin in Contact Maximum and lower than Soeumin in Contact Maximum of female/a/(2.5sec) 5. There was no significantly difference in male/e/(0.5sec), male/e/(2.5sce), female/a/(0.5sec), female/e/(2.5sec) 6. The percent of correctly classified in Soeoumin and Taeumin was high in CART Algolism. The risk estimate of Soyangin was relatively high. The study may be use on of the method to make objective diagnosis in Sasang constitution.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.57-63
• /
• 1997

In this paper, we study the efficient feature vector extraction method and front-end processing to improve the performance of the speech recognition system using KT(Korea Telecommunication) database collected through various telephone channels. First of all, we compare the recognition performances of the feature vectors known to be robust to noise and environmental variation and verify the performance enhancement of the recognition system using weighted cepstral distance measure methods. The experiment result shows that the recognition rate is increasedby using both PLP(Perceptual Linear Prediction) and MFCC(Mel Frequency Cepstral Coefficient) in comparison with LPC cepstrum used in KT recognition system. In cepstral distance measure, the weighted cepstral distance measure functions such as RPS(Root Power Sums) and BPL(Band-Pass Lifter) help the recognition enhancement. The application of the spectral subtraction method decrease the recognition rate because of the effect of distortion. However, RASTA(RelAtive SpecTrAl) processing, CMS(Cepstral Mean Subtraction) and SBR(Signal Bias Removal) enhance the recognition performance. Especially, the CMS method is simple but shows high recognition enhancement. Finally, the performances of the modified methods for the real-time implementation of CMS are compared and the improved method is suggested to prevent the performance degradation.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.1
• /
• pp.1-8
• /
• 2011

This paper presents a method for improving the performance of ISF coefficients quantizer through compensating the defect of the split structure vector quantization using the ordering property of ISF coefficients. And design the ISF coefficients quantizer for wideband speech codec using proposed method. The wideband speech codec uses split structure vector quantizer which could not use the correlation between ISF coefficients fully to reduce complexity and the size of codebook. The proposed algorithm uses the ordering property of ISF coefficients to overcome the defect. Using the ordering property, the codebook redundancy could be figured out. The codebook redundancy is replaced by the adaptive-extended codebook to improve the performance of the quantizer through using the ordering property, ISF coefficient prediction and interpolation of existing codebook. As a result, the proposed algorithm shows that the adaptive-extended codebook algorithm could get about 2 bit gains in comparison with the existing split structure ISF quantizer of AMR-WB (G.722.2) in the points of spectral distortion.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.5
• /
• pp.38-43
• /
• 1996

This paper compares the recognition performances of feature vectors known to be robust to the environmental noise. And, the speech subtraction technique is combined with the noise robust feature to get more performance enhancement. The experiments using SMC(Short time Modified Coherence) analysis, root cepstral analysis, LDA(Linear Discriminant Analysis), PLP(Perceptual Linear Prediction), RASTA(RelAtive SpecTrAl) processing are carried out. An isolated word recognition system is composed using semi-continuous HMM. Noisy environment experiments usign two types of noises:exhibition hall, computer room are carried out at 0, 10, 20dB SNRs. The experimental result shows that SMC and root based mel cepstrum(root_mel cepstrum) show 9.86% and 12.68% recognition enhancement at 10dB in compare to the LPCC(Linear Prediction Cepstral Coefficient). And when combined with spectral subtraction, mel cepstrum and root_mel cepstrum show 16.7% and 8.4% enhanced recognition rate of 94.91% and 94.28% at 10dB.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.27-34
• /
• 2001

Utterance verification is used in variable vocabulary word recognition to reject the word that does not belong to in-vocabulary word or does not belong to correctly recognized word. Utterance verification is an important technology to design a user-friendly speech recognition system. We propose a new utterance verification algorithm for no-training utterance verification system based on the minimum verification error. First, using PBW (Phonetically Balanced Words) DB (445 words), we create no-training anti-phoneme models which include many PLUs(Phoneme Like Units), so anti-phoneme models have the minimum verification error. Then, for OOV (Out-Of-Vocabulary) rejection, the phoneme-based confidence measure which uses the likelihood between phoneme model (null hypothesis) and anti-phoneme model (alternative hypothesis) is normalized by null hypothesis, so the phoneme-based confidence measure tends to be more robust to OOV rejection. And, the word-based confidence measure which uses the phoneme-based confidence measure has been shown to provide improved detection of near-misses in speech recognition as well as better discrimination between in-vocabularys and OOVs. Using our proposed anti-model and confidence measure, we achieve significant performance improvement; CA (Correctly Accept for In-Vocabulary) is about 89％, and CR (Correctly Reject for OOV) is about 90％, improving about 15-21％ in ERR (Error Reduction Rate).