• Phonetics and Speech Sciences
• /
• v.6 no.3
• /
• pp.139-145
• /
• 2014

The paper describes methods of conducting vowel analysis from a large-scale corpus with the aids of forced alignment and optimal formant ceiling methods. 'Read Style Corpus of Standard Korean' is used for building the forced alignment system and a subset of the corpus for the processing and extraction of features for vowel analysis based on optimal formant ceiling. The results of the vowel analysis are reliable and comparable to the results obtained using traditional analytical methods. The findings indicate that the methods adopted for the analysis can be extended and be used for more fine-grained analysis without time-consuming manual labeling without losing accuracy and reliability.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.4E
• /
• pp.31-38
• /
• 2001

A large-scale synthesis database for a unit selection based synthesis method usually retains redundant synthesis unit instances, which are useless to the synthetic speech quality. In this paper, to eliminate those instances from the synthesis database, we proposed a new pruning method called weighted vector quantization (WVQ). The WVQ reflects relative importance of each synthesis unit instance when clustering the similar instances using vector quantization (VQ) technique. The proposed method was compared with two conventional pruning methods through the objective and subjective evaluations of the synthetic speech quality: one to simply limit maximum number of instance, and the other based on normal VQ-based clustering. The proposed method showed the best performance under 50% reduction rates. Over 50% of reduction rates, the synthetic speech quality is not seriously but perceptibly degraded. Using the proposed method, the synthesis database can be efficiently reduced without serious degradation of the synthetic speech quality.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.02a
• /
• pp.1-1
• /
• 2002

This talk provides an overview of current work in my research group on the syntactic annotation of the T bingen corpus of spoken German and of the German Reference Corpus (Deutsches Referenzkorpus: DEREKO) of written texts. Morpho-syntactic and syntactic annotation as well as annotation of function-argument structure for these corpora is performed automatically by a hybrid architecture that combines robust symbolic parsing with finite-state methods ("chunk parsing" in the sense Abney) with memory-based parsing (in the sense of Daelemans). The resulting robust annotations can be used by theoretical linguists, who lire interested in large-scale, empirical data, and by computational linguists, who are in need of training material for a wide range of language technology applications. To aid retrieval of annotated trees from the treebank, a query tool VIQTORYA with a graphical user interface and a logic-based query language has been developed. VIQTORYA allows users to query the treebanks for linguistic structures at the word level, at the level of individual phrases, and at the clausal level.

• Phonetics and Speech Sciences
• /
• v.7 no.1
• /
• pp.139-150
• /
• 2015

The data accumulated in this database will be used to develop a speaker identification system. This may also be applied towards, but not limited to, fields of phonetic studies, sociolinguistics, and language pathology. We plan to supplement the large-scale speech corpus next year, in terms of research methodology and content, to better answer the needs of diverse fields. The purpose of this study is to develop a speech corpus for standard Korean speech. For the samples to viably represent the state of spoken Korean, demographic factors were considered to modulate a balanced spread of age, gender, and dialects. Nine separate regional dialects were categorized, and five age groups were established from individuals in their 20s to 60s. A speech-sample collection protocol was developed for the purpose of this study where each speaker performs five tasks: two reading tasks, two semi-spontaneous speech tasks, and one spontaneous speech task. This particular configuration of sample data collection accommodates gathering of rich and well-balanced speech-samples across various speech types, and is expected to improve the utility of the speech corpus developed in this study. Samples from 639 individuals were collected using the protocol. Speech samples were collected also from other sources, for a combined total of samples from 1,012 individuals.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.