• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.93-102
• /
• 2022

Dependency parsing is a decision problem of the syntactic relation between words in a sentence. Recently, deep learning models are used for dependency parsing based on the word representations in a continuous vector space. However, it causes a mislabeled tagging problem for the proper nouns that rarely appear in the training corpus because it is difficult to express out-of-vocabulary (OOV) words in a continuous vector space. To solve the OOV problem in dependency parsing, we explored the proper noun embedding method according to the embedding unit. Before representing words in a continuous vector space, we replace the proper nouns with a special token and train them for the contextual features by using the multi-layer bidirectional LSTM. Two models of the syllable-based and morpheme-based unit are proposed for proper noun embedding and the performance of the dependency parsing is more improved in the ensemble model than each syllable and morpheme embedding model. The experimental results showed that our ensemble model improved 1.69%p in UAS and 2.17%p in LAS than the same arc-eager approach-based Malt parser.

• Journal of Korea Multimedia Society
• /
• v.9 no.1
• /
• pp.23-32
• /
• 2006

This paper describes the optimization of a language model and an acoustic model to improve speech recognition using Korean unit digits. Since the model is composed of a finite state network (FSN) with a disyllable, recognition errors of the language model were reduced by analyzing the grammatical features of Korean unit digits. Acoustic models utilize a demisyllable pair to decrease recognition errors caused by inaccurate division of a phone or monosyllable due to short pronunciation time and articulation. We have used the K-means clustering algorithm with the transformed successive state splitting in the feature level for the efficient modelling of feature of the recognition unit. As a result of experiments, 10.5% recognition rate is raised in the case of the proposed language model. The demi-syllable fair with an acoustic model increased 12.5% recognition rate and 1.5% recognition rate is improved in transformed successive state splitting.

• Phonetics and Speech Sciences
• /
• v.1 no.2
• /
• pp.15-22
• /
• 2009

Prominence of speech, which is often called 'accent,' affects the fluency of speaking American English greatly. In this paper, we present an accurate prominence detection method that can be utilized in computer-aided language learning (CALL) systems. We employed pitch movement, overall syllable energy, 300-2200 Hz band energy, syllable duration, and spectral and temporal correlation as features to model the prominence of speech. After the features for vowel syllables of speech were extracted, prominent syllables were classified by SVM (Support Vector Machine). To further improve accuracy, the differences in characteristics of neighboring syllables were added as additional features. We also applied a speech recognizer to extract more precise syllable boundaries. The performance of our prominence detector was measured based on the Intonational Variation in English (IViE) speech corpus. We obtained 84.9% accuracy which is about 10% higher than previous research.

• Korean Journal of English Language and Linguistics
• /
• v.2 no.2
• /
• pp.287-304
• /
• 2002

Truncated forms (truncata) in English hypocoristic words have been argued to be faithful to their bases. This means that “ ... the base of truncation is an output form"”(Benua 1995:6,12). For example, in some non-rhotic dialects where syllable-final [r]s are deleted, the [r]s of truncated names such as Gar [gær] (truncated form of Garry [gæri]) are not deleted although they are syllable-final. This is an example of base-truncatum identity. That is, the syllable-final [r] is retained to make the truncatum more faithful to its base. However, there are many English hypocoristic names which are not faithful to their base forms. For example, Letty [equation omitted] (hypocoristic form of Latitia [equation omitted]) is not faithful to its base; the first vowel and the second consonant of the truncatum are not identical to the corresponding segments of the base. It will be argued, therefore, that some truncated forms are more faithful to the inputs than the bases. It will also be argued that McCarthy and Prince's (1995) Full Model is needed to deal successfully with all the phenomena related to truncation.

• Speech Sciences
• /
• v.6
• /
• pp.83-101
• /
• 1999

The aim of this study is to provide a learning method of prosodic rhythm for Taegu North Kyungsang Korean speakers to learn French rhythm more effectively. The rhythmic properties of spoken French and Taegu North Kyungsang Korean dialect are different from each other. Therefore, we try to provide a basic rhythmic model of the two languages by dividing into three parts: syllable, rhythmic unit and accent, and intonation. To do so, we recorded French of Taegu Kyungsang Korean speakers, and then analysed and compared the rhythmic properties of Korean and French by spectrograph. We tried to find rhythmic mistakes in their French pronunciation, and then established a learning model to modify them. After training with the CSL Macro learning model, we observed the output result. However, although learners understand the method we have proposed, an effective method which is possible by repeating practice must be arranged to be actually used in direct verbal communications in a well-developed learning programme. Hence, this study may play an important role at the level of preparation in the setting of an effective rhythmic learning programme.

• Phonetics and Speech Sciences
• /
• v.2 no.3
• /
• pp.101-113
• /
• 2010

The present study investigated how the kinematics of the /a/-to-/i/ tongue movement in Korean would be influenced by prosodic boundary. The /a/-to-/i/ sequence was used as 'transboundary' test materials which occurred across a prosodic boundary as in /ilnjəʃ$^h$a/ # / minsakwae/ ('일년차#민사과에' 'the first year worker' # 'dept. of civil affairs'). It also tested whether the V-to-V tongue movement would be further influenced by its syllable structure with /m/ which was placed either in the coda condition (/am#i/) or in the onset condition (/a#mi). Results of an EMA (Electromagnetic Articulagraphy) study showed that kinematical parameters such as the movement distance (displacement), the movement duration, and the movement velocity (speed) all varied as a function of the boundary strength, showing an articulatory strengthening pattern of a "larger, longer and faster" movement. Interestingly, however, the larger, longer and faster pattern associated with boundary marking in Korean has often been observed with stress (prominence) marking in English. It was proposed that language-specific prosodic systems induce different ways in which phonetics and prosody interact: Korean, as a language without lexical stress and pitch accent, has more degree of freedom to express prosodic strengthening, while languages such as English have constraints, so that some strengthening patterns are reserved for lexical stress. The V-to-V tongue movement was also found to be influenced by the intervening consonant /m/'s syllable affiliation, showing a more preboundary lengthening of the tongue movement when /m/ was part of the preboundary syllable (/am#i/). The results, together, show that the fine-grained phonetic details do not simply arise as low-level physical phenomena, but reflect higher-level linguistic structures, such as syllable and prosodic structures. It was also discussed how the boundary-induced kinematic patterns could be accounted for in terms of the task dynamic model and the theory of the prosodic gesture ($\pi$-gesture).

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3
• /
• pp.64-72
• /
• 1997

In this paper, study and experiments are performed for finding recognition unit fit which can be used in large vocabulary recognition system. Specifically, a phoneme that is currently used as recognition unit and a syllable in which Korean is well characterized are selected. From comparisons of recognition experiments, the study is performed whether a syllable can be considered as recognition unit of Korean recognition system. For report of an objective result of the comparison experiment, we collected speech data of a male speaker and processed them by hand-segmentation for phoneme boundary and labeling to construct speech database. And for training and recognition based on HMM, we used HTK (HMM Tool Kit) 2.0 of commercial tool from Entropic Co. to experiment in same condition. We applied two HMM model topologies, 3 emitting state of 5 state and 6 emitting state of 8 state, in Continuous HMM on training of each recognition unit. We also used 3 sets of PBW (Phonetically Balanced Words) and 1 set of POW(Phonetically Optimized Words) for training and another 1 set of PBW for recognition, that is "Speaker Dependent Medium Vocabulary Size Recognition." Experiments result reports that recognition rate is 95.65% in phoneme unit, 94.41% in syllable unit and decoding time of recognition in syllable unit is faster by 25% than in phoneme.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.160-166
• /
• 2002

In this paper, we implement a new vocabulary-independent speech recognition system that uses CV, VCCV, VC recognition unit. Since these recognition units are extracted in the trowel region of syllable, the segmentation is easy and robust. And in the case of not existing VCCV unit, the units are replaced by combining VC and CV semi-syllable model. Clustering of vowel group and applying combination rule to the substitution model in the case of not existing of VCCV model lead to 5.2% recognition performance improvement from 90.4% (Model A) to 95.6% (Model C) in the first candidate. The recognition results that is 98.8% recognition rate in the second candidate confirm the effectiveness of the proposed method.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.175-181
• /
• 2003

Because a word of Korean digits is a syllable and deeply coarticulatied in connected digits, some recognition models based on demisyllables have been proposed by researchers. However, they could not show an excellent recognition results yet. This paper proposes a recognition model based on extended and context-dependent demisyllables, such as a tri-demisyllable like a tri-phone, for the Korean 4-connected digits recognition. For experiments, we use a toolkit of HTK 3.0 for building this model of continuous HMMs using training Korean connected digits from SiTEC database and for recognizing unknown ones. The results show that the recognition rate is 92% and this model has an ability to improve the recognition performance of Korean connected digits.

• Journal of KIISE
• /
• v.41 no.9
• /
• pp.642-651
• /
• 2014

This paper proposes three probabilistic models for syllable-based Korean morphological analysis, and presents the performance of proposed probabilistic models. Probabilities for the models are acquired from POS-tagged corpus. The result of 10-fold cross-validation experiments shows that 98.3% answer inclusion rate is achieved when trained with Sejong POS-tagged corpus of 10 million eojeols. In our models, POS tags are assigned to each syllable before spelling recovery and morpheme generation, which enables more efficient morphological analysis than the previous probabilistic models where spelling recovery is performed at the first stage. This efficiency gains the speed-up of morphological analysis. Experiments show that morphological analysis is performed at the rate of 147K eojeols per second, which is almost 174 times faster than the previous probabilistic models for Korean morphology.