• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.391-400
• /
• 2007

An interactive Hangul input method using the numeric phone keypad, which is applicable for mobile devices is introduced. In the proposed method, user only selects the corresponding keys by single tapping, for the alphabet of Korean letter which is desired to enter. The interface generates the subset of eligible letters for the key sequence, then the user selects the desired letter in the set. Such an interactive approach transforms the text entry interface into a multi-level interactive letter-oriented style, from the preexisting passive and single-level alphabet-oriented interface. The annoyance of key-operations, the major disadvantage of the previous methods, derived from multi-tap to clear the ambiguity of multi-assigned alphabets for the Hangul automata, can be eliminated permanently, while the additional letter selection procedure to finalize the desired letter is essential. Also the complexity of Hangul text entry is reduced since all letters can be compounded from basic alphabet selection of the writing sequence order. The advantage and disadvantage of the proposed method are analyzed through comparing with pre-existing method by experiments.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.670-677
• /
• 2019

As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.

• Phonetics and Speech Sciences
• /
• v.7 no.3
• /
• pp.139-149
• /
• 2015

This paper aims to analyze pronunciation variations of loanwords produced by Korean and improve the performance of pronunciation modeling of loanwords in Korean by using syllable-based segmentation and phonological knowledge. The loanword text corpus used for our experiment consists of 14.5k words extracted from the frequently used words in set-top box, music, and point-of-interest (POI) domains. At first, pronunciations of loanwords in Korean are obtained by manual transcriptions, which are used as target pronunciations. The target pronunciations are compared with the standard pronunciation using confusion matrices for analysis of pronunciation variation patterns of loanwords. Based on the confusion matrices, three salient pronunciation variations of loanwords are identified such as tensification of fricative [s] and derounding of rounded vowel [ɥi] and [$w{\varepsilon}$]. In addition, a syllable-based segmentation method considering phonological knowledge is proposed for loanword pronunciation modeling. Performance of the baseline and the proposed method is measured using phone error rate (PER)/word error rate (WER) and F-score at various context spans. Experimental results show that the proposed method outperforms the baseline. We also observe that performance degrades when training and test sets come from different domains, which implies that loanword pronunciations are influenced by data domains. It is noteworthy that pronunciation modeling for loanwords is enhanced by reflecting phonological knowledge. The loanword pronunciation modeling in Korean proposed in this paper can be used for automatic speech recognition of application interface such as navigation systems and set-top boxes and for computer-assisted pronunciation training for Korean learners of English.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.35-43
• /
• 2001

Many speech recognition systems have used pronunciation lexicon with possible multiple phonetic transcriptions for each word. The pronunciation lexicon is of often manually created. This process requires a lot of time and efforts, and furthermore, it is very difficult to maintain consistency of lexicon. To handle these problems, we present a model based on morphophon-ological analysis for automatically generating Korean pronunciation variants. By analyzing phonological variations frequently found in spoken Korean, we have derived about 700 phonemic contexts that would trigger the multilevel application of the corresponding phonological process, which consists of phonemic and allophonic rules. In generating pronunciation variants, morphological analysis is preceded to handle variations of phonological words. According to the morphological category, a set of tables reflecting phonemic context is looked up to generate pronunciation variants. Our experiments show that the proposed model produces mostly correct pronunciation variants of phonological words. Then we estimated how useful the pronunciation lexicon and training phonetic transcription using this proposed systems.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.401-406
• /
• 2002

Each Korean digit is composed of only a syllable, so recognizers as well as Korean often have difficulty in recognizing it. When digit strings are pronounced, the original pronunciation of each digit is largely changed due to the co-articulation effect. In addition to these problems, the distortion caused by various channels and noises degrades the recognition performance of Korean connected digit string. This paper dealt with some techniques to improve recognition performance of it, which include defining a set of PLUs by considering phonemic variations in Korean digit and constructing a recognizer to handle speakers various speaking styles. In the speaker-independent connected digit recognition experiments using telephone speech, the proposed techniques with 1-Gaussian/state gave string accuracy of 83.2%, i. e., 7.2% error rate reduction relative to baseline system. With 11-Gaussians/state, we achieved the highest string accuracy of 91.8%, i. e., 4.7% error rate reduction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.7
• /
• pp.3267-3274
• /
• 2011

Recently, speech recognition technology has dramatically developed, with the increase in the user environment of various mobile devices and influence of a variety of speech recognition software. However, for speech recognition for multi-language, lack of understanding of multi-language lexical model and limited capacity of systems interfere with the improvement of the recognition rate. It is not easy to embody speech expressed with multi-language into a single acoustic model and systems using several acoustic models lower speech recognition rate. In this regard, it is necessary to research and develop a multi-language speech recognition system in order to embody speech comprised of various languages into a single acoustic model. This paper studied a system that can recognize Korean and English as International Phonetic Language (IPA), based on the research for using a multi-language acoustic model in mobile devices. Focusing on finding an IPA model which satisfies both Korean and English phonemes, we get 94.8% of the voice recognition rate in Korean and 95.36% in English.

• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.387-394
• /
• 2004

In this paper, we propose a modified unsupervised linear alignment algorithm for building an aligned corpus. The original algorithm inserts null characters into both of two aligned strings (source string and target string), because the two strings are different from each other in length. This can cause some difficulties like the search space explosion for applications using the aligned corpus with null characters and no possibility of applying to several machine learning algorithms. To alleviate these difficulties, we modify the algorithm not to contain null characters in the aligned source strings. We have shown the usability of our approach by applying it to different areas such as Korean-English back-trans literation, English grapheme-phoneme conversion, and Korean morphological analysis.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.8 no.2
• /
• pp.139-144
• /
• 2014

Speech discrimination is affected by the speed of speech. The speed of speech can be adjusted at the pause duration, the pause duration can take the resting time to avoid in overloading information. The study will be examine the effects of aging and audiological rehabilitation, and the auditory processing as basic research to investigate the normative data. 7 boys and 8 girls were participated. They have no problem with speech language pathologically and audiologically. There are 4 sets of test implement, and each test set was made out with 20 3-syllable words. Pause duration of all of these words are adjusted in normal(250 ms), slow(500 ms) and very slow(1000 ms). There are 4 words for a multiple-choice that including one word with written correctly and three words with written 1 phoneme wrong. Participant hear the word, and then have to choose one. Speech discrimination score in 250, 500, 1,000 ms of pause duration were $73{\pm}19.4%$, $84{\pm}12.2%$, $88{\pm}8.8%$, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.37-43
• /
• 2021

Using the acoustic features of speech, important social and linguistic information about the speaker can be obtained, and one of the key features is the dialect. A speaker's use of a dialect is a major barrier to interaction with a computer. Dialects can be distinguished at various levels such as phonemes, syllables, words, phrases, and sentences, but it is difficult to distinguish dialects by identifying them one by one. Therefore, in this paper, we propose a lightweight Korean dialect classification model using only MFCC among the features of speech data. We study the optimal method to utilize MFCC features through Korean conversational voice data, and compare the classification performance of five Korean dialects in Gyeonggi/Seoul, Gangwon, Chungcheong, Jeolla, and Gyeongsang in eight machine learning and deep learning classification models. The performance of most classification models was improved by normalizing the MFCC, and the accuracy was improved by 1.07% and F1-score by 2.04% compared to the best performance of the classification model before normalizing the MFCC.

• 재활복지
• /
• v.17 no.4
• /
• pp.371-382
• /
• 2013

Recently, the number of those who were transplanted cochlear implants increased as health insurance increases has expanded. Last six years between 2005 to 2009, patients who received a cochlear implant surgery were about 3,300 and number of cochlear implants in adults of them have shown growing aspects. In the case of young children, they actively participated auditory training program after cochlear implant surgery and the studies related to auditory training in child are many, but the studies related to auditory training in adults is insufficient. In this study, we perform the auditory training for the female adult (age 54) received cochlear implant after language acquisition used Ling 6 sounds test, standardized consonants, vowels and sentences listening test and word recognition and confirmation test. As a result after auditory training for 10 weeks, she identified all phonemes in Ling 6 sound test and performed close to 100% in standardized consonants, vowels and sentences listening tests. Also, she improved the ability of real-world environmental sound and real-world words identifications by 57-95%. The results of this study showed the need of auditory training program with systematic and effective planning and considering the characteristics of the individual for adults.