정민화 교수

One of the first cues for many neurological disorders are impairments in speech. The traditional method of diagnosing speech disorders such as dysarthria involves a perceptual evaluation from a trained speech therapist. However, this approach is known to be difficult to use for assessing speech impairments due to the subjective nature of the task. As prosodic impairments are one of the earliest cues of dysarthria, the current study presents an automatic method of assessing dysarthria in a range

This study acoustically examines the quality of fricatives produced by ten dysarthric speakers with cerebral palsy. Previous similar studies tend to focus only on sibilants, but to obtain a better understanding of how dysarthria affects fricatives we selected a range of samples with different places of articulation and voicing. The Universal Access (UA) Speech database was used to select thirteen words beginning with one of the English fricatives (/f/, /v/, /s/, /z/, /∫/, /ð/). The following fou

In this paper we will introduce the work of creation of a speech database to develop speech technology for disabled persons, which has been done as part of a national program to help better life for Korean people. We will report about the creation of speech database of a total of 160 persons: prompting items, designs, etc. for the creation of a database which is needed to develop an embedded key-word spotting speech recognition system tailored for the persons disabled in articulation. The create

This paper proposes a method for automatic pronunciation assessment of Korean spoken by L2 learners by selecting the best feature set from a collection of the most well-known features in the literature. The L2 Korean Speech Corpus is used for assessment modeling, where the native languages of the L2 learners are English, Chinese, Japanese, Russian, and Mongolian. In our system, learners' speech is forced-aligned and recognized using a native Korean acoustic model. Based on these results, various

This paper presents a parallel natural language processing system implemented on a marker-passing parallel AI computer, the Semantic Network Array Processor (SNAP). Our system uses a memory-based parsing approach in which parsing is viewed as a memory search process. Linguistic information is stored as phrasal patterns in a semantic network knowledge base distributed over the memory of the parallel computer. Parsing is performed by recognizing and linking phrasal patterns that reflect a sentence

Detection of children with autism spectrum disorder (ASD) based on speech has relied on predefined feature sets due to their ease of use and the capabilities of speech analysis. However, clinical impressions may not be adequately captured due to the broad range and the large number of features included. This paper demonstrates that the knowledge-driven speech features (KDSFs) specifically tailored to the speech traits of ASD are more effective and efficient for detecting speech of ASD children f

Massively parallel computers offer not only improved speed but also a new perspective on computer vision, production systems, neural networks, and other AI applications. However, not much work has been done to apply parallel processing to natural-language processing, even though most sequential natural-language systems slow down as knowledge bases grow to realistic sizes and as linguistic features are added to handle special cases. To demonstrate the potential of parallel systems for natural-lan

This paper examines variations of Korean segments produced by Japanese learners of Korean. For corpus-based statistical analysis, we have used Korean read speech corpus produced by Japanese learners. Contrastive analysis of the target language and the source language is performed to provide information for interpreting the results of corpus analysis. Segmental variations are analyzed by aligning canonical phonetic transcriptions with auditory phonetic transcriptions of the corpus. The results sh

This study focuses on the issue of automatic severity classification of dysarthric speakers based on speech intelligibility. Speech intelligibility is a complex measure that is affected by the features of multiple speech dimensions. However, most previous studies are restricted to using features from a single speech dimension. To effectively capture the characteristics of the speech disorder, we extracted features of multiple speech dimensions: voice quality, prosody, and pronunciation. Voice qu

This paper describes a method of building Korean conversational speech data in the emergency medical domain and proposes an annotation method for the collected data in order to improve speech recognition performance. To suggest future research directions, baseline speech recognition experiments were conducted by using partial data that were collected and annotated. All voices were recorded at 16-bit resolution at 16 kHz sampling rate. A total of 166 conversations were collected, amounting to 8 h

This paper proposes an economical and effective phonetic transcription method for dealing with a large amount of nonnative English speech corpus. The method provides a consistent transcription agreement, although the corpus is transcribed by non-natives. To minimize the possibility of confusion in transcription process, forced aligned phone sequences and a set of possible mispronunciation candidate phones that Korean L2 learners are expected to make are given to the Korean transcribers for refer

Presents a parallel memory-based parser called PARALLEL, which is implemented on a marker-passing parallel AI computer called the Semantic Network Array Processor (SNAP). In the PARALLEL memory-based parser, the parallelism in natural language processing is utilized by a memory search model of parsing. Linguistic information is stored as phrasal patterns in a semantic network knowledge base that is distributed over the memory of the parallel computer. Parsing is performed by recognizing and link