• MALSORI
• /
• no.63
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.84-88
• /
• 1999

The accurate estimation of segmental duration is crucial for natural-sounding text-to-speech synthesis. For predicting Korean segmental durations, conventional methods utilized phonemic context, part-of-speech context and locational information in prosodic phrase. In this paper, the tonal information of phonemes is employed for more accurate prediction. After defining two non-boundary tones and six boundary tones, we annotated the tonal label on each syllable of 400 sentences. To predict segmental duration using tonal information, we constructed neural networks with a real-valued output node predicting phonemic duration and trained them by backpropagation algorithm. Experimental results showed that the proposed features are effective for predicting Korean segmental durations, and we got 0.863 correlation coefficient of the observed durations and predicted ones.

• Speech Sciences
• /
• v.1
• /
• pp.213-223
• /
• 1997

This paper deals with a general review of Mieko S. Han, who made a significant contribution to the studies of Korean phonetics during the 1960' s and early 1970' s. As both a single and joint author, Dr. Han published important papers in both quantity and quality, which have been cited among Korean phoneticians until today. Before Dr. M. Han' s work, professor of USC in the department of East Asian Languages & Cultures, there were only a few phonetics-related publications in Korea, most of which are papers or books based on non-experimental traditional approach. It is known that there was coexistence between traditionalism and structuralism in the field of Korean linguistics. It was, however, fortunate that we had two important phoneticians (M. Han and Chin-W Kim) abroad at that time. Mieko Han' s concern was to investigate experimental characteristics of the system of Korean vowels and consonants using a Spectrograph, which was the single most important tool for analysing phonetic data at that time. Dr. Han conducted her experimental studies on Korean phonetics, mostly funded by the Office of Naval Research, in terms of duration, fundamental frequency, Voice Onset Time (VOT), intensity, and so on. This paper aims to re-appreciate Dr. Han's specific contribution to the study of Korean phonetics since she played an important role as a pioneer of early Korean phonetics. Further, it is highly recommended that Dr. Han's works can be extremely useful for a graduate student, who seriously would like to specialize in Korean phonetics in the first step.

• Phonetics and Speech Sciences
• /
• v.2 no.4
• /
• pp.3-10
• /
• 2010

The present study aims to investigate neural activations according to the level of code switching in English proficient bilinguals and to find the relationship between the performance of language switching and proficiency level using ERPs (event-related potentials). First, when comparing high-proficient (HP) with low-proficient (LP) bilingual performance in a native language environment, the activation level of N2 was observed to be higher in the HP group than in the LP group, but only under two conditions: 1) the language switching (between-language) condition known as indexing attention of code switching and 2) the inhibition of current language for L1. Another effect of N400 can be shown in both groups only in the language non-switching (within-language) condition. This effect suggests that both groups completed the semantic acceptability task well in their native language environment without the burden of language switching, irrespective of high or low performance. The latencies of N400 are only about 100ms earlier in the HP group than in the LP group. This difference can be interpreted as facilitation of the given task. These results suggest that HP showed the differential activation in inhibitory system for L1 in switching condition of L1-to-L2 to be contrary to inactivation of inhibitory system for the LP group. Despite the absence of an N400 effect at the given task in both groups, differential latencies between the peaks were attributed to the differences of efficiency in semantic processing.

• Phonetics and Speech Sciences
• /
• v.10 no.4
• /
• pp.31-37
• /
• 2018

Pitch trajectories reflect a continuous variation of vocal fold movements over time. This study examined the pitch trajectories of English vowels produced by 139 American English speakers, statistically analyzing their trajectories using the Generalized Additive Mixed Models (GAMMs). First, Praat was used to read the sound data of Hillenbrand et al. (1995). A pitch analysis script was then prepared, and six pitch values at the corresponding time points within each vowel segment were collected and checked. The results showed that the group of men produced the lowest pitch trajectories, followed by the groups of women, boys, then girls. The density line showed a bimodal distribution. The pitch values at the six corresponding time points formed a single dip, which changed gradually across the vowel segment from 204 to 193 to 196 Hz. The normality tests performed on the pitch data rejected the null hypothesis. Nonparametric tests were therefore conducted to discover the significant differences in the values among the four groups. The GAMMs, which analyzed all the pitch data, produced significant results among the pitch values at the six corresponding time points but not between the two groups of boys and girls. The GAMMs also revealed that the two groups were significantly different only at the first and second time points. Accordingly, the methodology of this study and its findings may be applicable to future studies comparing curvilinear data sets elicited by experimental conditions.

• Proceedings of the KSPS conference
• /
• 1996.10a
• /
• pp.337-342
• /
• 1996

In prevoius works we have repored phonetic similarities between Japanese and Spanish voweis and syiiabic sounds. (1) (2) (3) (4). In the present communication we explore the relative importance of duration of the consonantal segment to elicit Spanish /l/ - /r/ distinction by native j Japanese talkers. Three Argentine and three trained native Japanese talkers recorded /l-r/ combined with /a/ in VCV sequences. Modifications of consonant duration and vowel context with transitions were m made by editing natural /ala/ sounds. Mixed VCV were produced by combining sounds of both languages. Perceptual tests were produced by combining sounds of both languages perceptual performed presenting the speech material, to native t trained and non trained Japanese listeners. In a tirst sessIOn a d discrimination procedure was applied. The items were arranged in pairs a and listeners Nere told to indicate the pair that sounded different. In the f following session they were asked to identify and type the letter corresponding to each one of the items. Responses arc examined in tenns of critical duration of the interval between vowels. Preliminary results indicate that the duration of intervocalic intervais was a relevant cue for the identification of /l/ and /r/. It seems that to differentiate the two sounds, Japanese listeners required relatively longer interval steps than the argentine suhjects. There was a tendency to conhlse more frequently /l/ for /r/ than viceversa.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.1
• /
• pp.76-81
• /
• 2010

In this paper, we propose a novel approach to improve the performance of a statistical model-based voice activity detection (VAD) which is based on the second-order conditional maximum a posteriori (CMAP). In our approach, the VAD decision rule is expressed as the geometric mean of likelihood ratios (LRs) based on adapted threshold according to the speech presence probability conditioned on both the current observation and the speech activity decisions in the pervious two frames. Experimental results show that the proposed approach yields better results compared to the statistical model-based and the CMAP-based VAD using the LR test.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.25-31
• /
• 2024

This study examines the perceptual motivation behind dissimilation. Consistent with previous arguments suggesting that dissimilation originates from perception rather than production (Coetzee, 2005; Kiparsky, 2003; Scheer, 2013), we hypothesized that an oral stop with short of voice onset time (VOT) would be recognized as non-aspirated more often when it is followed by an aspirated stop with a long VOT. This hypothesis was tested through a perception experiment in which 32 Korean listeners made judgments on the first consonant of C₁VC₂V words manipulated with C₁ VOT and C₂ types. The results revealed that aspirated-based C₁ was recognized as aspirated or tense depending on the duration of VOT, while lenis-based C₁ was consistently recognized as lenis. The dissimilatory effect of aspirated C₂ was confirmed as anticipated, and furthermore, tense C₂ increased the ratio of tense responses more than aspirated C₂. These results provide evidence of a perceptual bias against recurrent aspirated stops, which may play a role in activating a dissimilatory rule or constraint in a language. The assimilatory effect of tense C₂ is in consistent with findings indicating that word-initial tensification is facilitated by the following tense stop in Korean (Kang & Oh, 2016; H. Kim, 2016).

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.99-106
• /
• 2004

The syllable restoration is a process restoring a phonetic value recognized in a speech recognition device with the notation form that a vocalization is former. In this paper a syllable restoration rule was composed of a based on standard pronunciation for a syllable restoration process. A syllable restoring regulation was used, and a generation method of a notation candidate set was researched. Also, A study is held to reduce the number of created notation candidate. Three phases of reduction processes were suggested. Reduction of a notation candidate has the non-notation syllable, non-vocabulary syllable and non-stem syllable. As a result of experiment, an average of 74％ notation candidate decrease rates were shown.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.5
• /
• pp.255-261
• /
• 2005

In this paper. experiments are conducted to extract a set of non-Parametric warping functions to examine the characteristics of the warping among speakers' utterances. For this Purpose. we made use of MFCC and LP spectra of vowels in choosing reference spectrum of each vowel as well as representative spectra of each speaker. These spectra are compared by DTW to give the warping functions of each speaker. The set of warping functions are then defined by clustering the warping functions of all the speakers. Noting that male and female warping functions have shapes similar to Piecewise linear function and Power function respectively, a new hybrid set of warping functions is defined. The effectiveness of the extracted warping functions are evaluated by conducting phone level recognition experiments, and improvements in accuracy rate are observed in both warping functions.