This study examined the speech intelligibility of one-syllable words with phonetic contrasts and analyzed segmental factors that can predict the overall speech intelligibility in hearing-impaired adults. To identify the speech error characteristics, a Korean word list was audio-recorded by 7 hearing-impaired adults, and 35 listeners selected the heard word out of 5 choices. Based in part on previous studies of speech of the hearing impaired, the word list consisted of monosyllabic consonant-vowel-consonant (CVC) real word pairs. Stimulus words included 77 phonetic contrast pairs. The results showed that the percentage of errors in final position (coda) contrast was higher than in any other position in syllable. And the intelligibility deficit factors of phonetic contrast in the hearing-impaired were analyzed through stepwise regression analysis. The overall intelligibility was predicted by the error rate of manner contrast at coda, voicing contrast (homorganic triplets) at onset and high-low contrast at nucleus.

In this study, children with MR were compared with normal children in overall production rate and production types of six semantic categories of negation. For this purpose, 10 children with MR and another 10 language-age matched normal children were selected. The results of this study were as the following: First, the children with MR showed significantly low overall production rate, compared with normal children. Two groups demonstrated signifiant differences in denial, disability, ignorance, prohibition and rejection except nonexistence. Second, in production type, the children with MR tended to use more gestures, and in comparison, normal children used more 'mixed types'.

Investigating and comparing English vowels $/{\varepsilon}/\;and\;/{\ae}/$, and their-supposedly- corresponding vowels in Korean /ㅔ/ and /ㅐ/, this study addresses the following questions: Do Koreans pronounce/ㅔ/ and /ㅐ/ differently? Do they pronounce English $/{\varepsilon}/\;and\;/{\ae}/$ differently? And what is the relationship between the Korean vowels and the English vowels? Is the conventional correspondence (/ㅔ:${\varepsilon}/$, and /ㅐ/:${\ae)/$ appropriate? The results showed that 24 Korean male college students distinguish neither Korean /ㅔ/ and /ㅐ/ nor English $/{\varepsilon}/\;and\;/{\ae}/$, thus suggesting that their inability to distinguish the two vowels in their native tongue has an effect on their production of the English vowels. While not distinguishable within a language, Korean /ㅔ/ and /ㅐ/ still form a separate group from English $/{\varepsilon}/\;and\;/{\ae}/$. But Korean-Produced $/{\varepsilon}/\;and\;/{\ae}/$ are significantly different from American-produced $/{\varepsilon}/\;and\;/{\ae}/:$ Korean-produced $/{\varepsilon}/\;and\;/{\ae}/$ have much lower F1 and F2 than American-produced counterparts. Accordingly it is advised that, in learning English pronunciation, Korean students should be instructed to take the English vowel system as a separate system from Korean one, and thus, not to substitute Korean vowels for English vowels. And students should be provided with specific instructions on the articulatory differences between English vowels and Korean vowels. For example, Cey should be instructed to lower their jaws more for English $/{\varepsilon}/\;and\;/{\ae}/$ than for Korean /ㅔ/ and /ㅐ/.

This study explores the most important temporal cues in the perception of the voiced/voiceless distinction of English plosives in terms of newly defined measures of perception: original signal to response agreement, unit signal to response agreement, and robustness. Seven native speakers of English and three leveled groups of Korean English learners participated in the present study. The results showed that both native speakers of English and Korean groups failed to successfully perceive the voiced/voiceless distinction of English plosives, particularly alveolar plosives, in word-medial trochaic positions. The results also showed that in word-initial and word-medial iambic positions both native speakers of English and Korean groups employ the information in the release burst and aspiration in the perception of the voiced/voiceless distinction, of English plosives, and that in word-final positions native speakers of English employ the information in the preceding vowel, while Korean groups employ the information in the closure interval.

This study investigated the articulatory and acoustic correlates of Korean /1/. In particular, direct comparison between Korean /1/ and English /1/ was made to evaluate the current assumption about Korean /1/ such that Korean /1/ is phonetically similar to English clear /1/. The present study revealed that Korea /1/ is different from English /1/ in several properties. First, F2 for Korean /1/ is around 600-700 Hz higher than F2 for English /1/. The overall higher F2 for Korean /1/ is attributed to the fact that Korean /1/ involves tongue body raising while it lacks a dorsal gesture. Second, F3 value for Korean /1/ becomes significantly lower when the preceeding vowel is a back vowel. This kind of variable F3 pattern was not observed in English /1/. The current study relates the F3 lowering to the retroflexion of Korean /1/ in the back vowel context.

We present a new method of measuring the volume and cross-sectional area of the vocal tract from magnetic resonance images. The vocal tract was divided by the 2 constriction points on the horizontal and vertical planes. The ratios of the volumes of the segment vocal tracts to that of the entire vocal tract play a crucial role in discriminating Korean monophthongs in that vowels were successfully discriminated by the ratios. The discriminant analysis also demonstrated that the acoustic parameters F1 and F2, in addition to the segment volumes, serve as significant parameters in discriminating Korean monophthongs.

Although the narrative development and the acquisition of the Korean grammatical morphemes by monolingual Korean-speaking children have been studied extensively, little is known about the narrative characteristics and the processes through which native speakers of other languages (L2 speakers) use the Korean grammatical morphemes. To understand the similarities and differences between L1 and L2 narrative skills and Korean grammatical morpheme use, 13 native Chinese-speaking college students who are learning Korean as a second language were studied. L2 participants used significantly fewer words, subordinate clauses, connective morphological endings, and pronouns per T-unit. Their speech also illustrated significantly more omission and confusion (substitution) errors in the use of auxiliary words and verb endings. Some of the syntactic and morphological factors need to be considered for the intervention of speakers with limited Korean proficiency.

In this paper, a WiFi phone system with distributed speech recognition is implemented. The WiFi phone with voice-activated dialing and its functions are explained. Features of the input speech are extracted and are sent to the interactive voice response (IVR) server according to the real-time transport protocol (RTP). Feature extraction is based on the European Telecommunication Standards Institute (ETSI) standard front-end, but is modified to reduce the processing time. The time for front-end processing on a WiFi phone is compared with that in a PC.

In this paper, we are focused to develop the simplified speaker verification algorithm without background speaker models, which will be adopted in the portable speaker verification system equipped in portable terminals such as mobile phone and PMP. According to the tolerance interval analysis, the population of someone's speaker model can be represented by a suitable number of selected independent samples of speaker model. So we can make the representative speaker model and threshold under the specified confidence level and coverage. Using proposed algorithm with the number of samples is 40, the experiments show that the false rejection rate is $3.0\%$ and the false acceptance rate $4.3\%$, worth comparing to conventional method's results, $5.4\%\;and\;5.5\%$, respectively. Next step of research will be on the suitable adaptation methods to overcome speech variation problems due to aging effect and operating environments.

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.

We propose a speech emotion recognition method for affective human-robot interface. In the Proposed method, emotion is classified into 6 classes: Angry, bored, happy, neutral, sad and surprised. Features for an input utterance are extracted from statistics of phonetic and prosodic information. Phonetic information includes log energy, shimmer, formant frequencies, and Teager energy; Prosodic information includes Pitch, jitter, duration, and rate of speech. Finally a pattern classifier based on Gaussian support vector machines decides the emotion class of the utterance. We record speech commands and dialogs uttered at 2m away from microphones in 5 different directions. Experimental results show that the proposed method yields $48\%$ classification accuracy while human classifiers give $71\%$ accuracy.

In this paper, we present POSSDM (POSTECH Situation-Based Dialogue Manager) for a spoken dialogue system using a new example and situation-based dialogue management technique for effective generation of appropriate system responses. Spoken dialogue system should generate cooperative responses to smoothly control dialogue flow with the users. We introduce a new dialogue management technique incorporating dialogue examples and situation-based rules for EPG (Electronic Program Guide) domain. For the system response inference, we automatically construct and index a dialogue example database from dialogue corpus, and the best dialogue example is retrieved for a proper system response with the query from a dialogue situation including a current user utterance, dialogue act, and discourse history. When dialogue corpus is not enough to cover the domain, we also apply manually constructed situation-based rules mainly for meta-level dialogue management.

Discrimination between speech and music is important in many multimedia applications. In this paper, focusing on the spectral change characteristics of speech and music, we propose a new method of speech/music discrimination based on cepstral distance. Instead of using cepstral distance between the frames with fixed interval, the minimum of cepstral distances among neighbor frames is employed to increase discriminability between fast changing music and speech. And, to prevent misclassification of speech segments including short pause into music, short pause segments are excluded from computing cepstral distance. The experimental results show that proposed method yields the error rate reduction of$68\%$, in comparison with the conventional approach using cepstral distance.

The goal of language model adaptation is to improve the background language model with a relatively small adaptation corpus. This study presents a language model adaptation technique where additional text data for the adaptation do not exist. We propose the information retrieval (IR) technique with N-gram language modeling to collect the adaptation corpus from baseline text data. We also propose to use a dynamic language model interpolation coefficient to combine the background language model and the adapted language model. The interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech data reserved for held-out validation data. This allows the final adapted model to improve the performance of the background model consistently The proposed approach reduces the word error rate by $13.6\%$ relative to baseline 4-gram for two-hour broadcast news speech recognition.

Speech unit concatenation with a large database is presently the most popular method for speech synthesis. In this approach, the mismatches at the unit boundaries are unavoidable and become one of the reasons for quality degradation. This paper proposes an algorithm to reduce undesired discontinuities between the subsequent units. Optimal matching points are calculated in two steps. Firstly, the fullback-Leibler distance measurement is utilized for the spectral matching, then the unit sliding and the overlap windowing are used for the waveform matching. The proposed algorithm is implemented for the corpus-based unit concatenating Korean text-to-speech system that has an automatically labeled database. Experimental results show that our algorithm is fairly better than the raw concatenation or the overlap smoothing method.