• Journal of Genetic Medicine
• /
• 제18권2호
• /
• pp.75-82
• /
• 2021

Speech and language functions are highly cognitive and human-specific features. The underlying causes of normal speech and language function are believed to reside in the human brain. Developmental persistent stuttering, a speech and language disorder, has been regarded as the most challenging disorder in determining genetic causes because of the high percentage of spontaneous recovery in stutters. This mysterious characteristic hinders speech pathologists from discriminating recovered stutters from completely normal individuals. Over the last several decades, several genetic approaches have been used to identify the genetic causes of stuttering, and remarkable progress has been made in genome-wide linkage analysis followed by gene sequencing. So far, four genes, namely GNPTAB, GNPTG, NAGPA, and AP4E1, are known to cause stuttering. Furthermore, thegeneration of mouse models of stuttering and morphometry analysis has created new ways for researchers to identify brain regions that participate in human speech function and to understand the neuropathology of stuttering. In this review, we aimed to investigate previous progress, challenges, and future perspectives in understanding the genetics and neuropathology underlying persistent developmental stuttering.

• ETRI Journal
• /
• 제46권1호
• /
• pp.96-105
• /
• 2024

We propose a method to automatically predict Alzheimer's disease from speech data using the ChatGPT large language model. Alzheimer's disease patients often exhibit distinctive characteristics when describing images, such as difficulties in recalling words, grammar errors, repetitive language, and incoherent narratives. For prediction, we initially employ a speech recognition system to transcribe participants' speech into text. We then gather opinions by inputting the transcribed text into ChatGPT as well as a prompt designed to solicit fluency evaluations. Subsequently, we extract embeddings from the speech, text, and opinions by the pretrained models. Finally, we use a classifier consisting of transformer blocks and linear layers to identify participants with this type of dementia. Experiments are conducted using the extensively used ADReSSo dataset. The results yield a maximum accuracy of 87.3% when speech, text, and opinions are used in conjunction. This finding suggests the potential of leveraging evaluation feedback from language models to address challenges in Alzheimer's disease recognition.

• 아동학회지
• /
• 제26권5호
• /
• pp.205-216
• /
• 2005

This study investigated aspects of caregiver's input relating to the early development of nouns and verbs. Subjects were 34 Korean-Chinese children in Yanji, China. At 1 year of age each child's spontaneous speech during interaction with his/her caregiver was videotaped for about 30 minutes. The children's spontaneous utterances were transcribed and coded on the lexical level(nouns and verbs) and the pragmatic level. Children's speech was recorded, transcribed and coded again at 2 years of age. Results showed that children used more verbs when they were older; there were no differences between the two ages in mother's pragmatic utterances but when they were two-years-old children used more actionoriented utterances and object-described utterances. Mother's input was related to children's pragmatic utterances.

• 말소리와 음성과학
• /
• 제4권3호
• /
• pp.161-169
• /
• 2012

The purpose of this study was to investigate the characteristics of speech intelligibility of spontaneous speech and the vowel space parameters in patients with Parkinson's disease. Ten PD patients (M=5, F=5) and a corresponding control group of ten normal adults participated in this study. Firstly, subjects were asked to tell a story about their hometown and youth in order to analyze speech intelligibility. Secondly, the subjects were also asked to repeat four vowels (/a/, /i/, /u/, /e/) five times in order to compare their vowel spaces. The results were as follows: (1) the speech intelligibility of the PD group was lower than that of the control group. (2) Four parameters including vowel area, vowel articulatory index, formant centralization ratio, F2i/F1u ratio were significantly different in each group. For instance, vowel area and F2 ratio were wider and higher, respectively. As a result, a decrease in speech intelligibility of patients with PD is likely to show different types of errors from the normal group. The results of this research are meaningful in a sense that they could provide the objective standard of speech intelligibility and vowel space parameters.

• 말소리와 음성과학
• /
• 제7권4호
• /
• pp.103-110
• /
• 2015

The purpose of this study is to assess the vowel property by examining the vowel duration of the American English vowles found in the Buckeye corpus[6]. The vowel durations were analyzed in terms of various linguistic factors including the number of syllables of the word containing the vowel, the location of the vowel in a word, types of stress, function versus content word, the word frequency in the corpus and the speech rate calculated from the three consecutive words. The findings from this work agreed mostly with those from earlier studies, but with some exceptions. The relationship between the speech rate and the vowel duration proved non-linear.

• 말소리와 음성과학
• /
• 제4권2호
• /
• pp.33-40
• /
• 2012

The purpose of this paper is to investigate the voice onset time (VOT) of the English voiceless stops [p, t, k] found in the Buckeye Corpus of Conversational Speech [1]. Three young female speakers were chosen for this study and their VOT values were semi-automatically extracted along with other factors. The factors used for the analysis were place of articulation, location in word, syllabic stress, content word or not, word frequency calculated from the corpus, and the speech rate expressed in syllables per second. Results showed that, for the three places of articulation of each speaker, all the factors had a statistically significant effect on the VOT values. This paper has significance in that the materials used for the analysis were from a corpus of spontaneous natural English speech.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권8호
• /
• pp.365-370
• /
• 2023

사람은 노화과정에 따라 발화의 호흡, 조음, 높낮이, 주파수, 언어 표현 능력 등이 변화한다. 본 논문에서는 이러한 변화로부터 발생하는 음향적, 언어적 특징을 기반으로 발화 데이터를 성인과 노인 두 그룹으로 분류하는 성능을 비교하고자 한다. 음향적 특징으로는 발화 음성의 주파수 (frequency), 진폭(amplitude), 스펙트럼(spectrum)과 관련된 특징을 사용하였으며, 언어적 특징으로는 자연어처리 분야에서 우수한 성능을 보이고 있는 한국어 대용량 코퍼스 사전학습 모델인 KoBERT를 통해 발화 전사문의 맥락 정보를 담은 은닉상태 벡터 표현을 추출하여 사용하였다. 본 논문에서는 음향적 특징과 언어적 특징을 기반으로 학습된 각 모델의 분류 성능을 확인하였다. 또한, 다운샘플링을 통해 클래스 불균형 문제를 해소한 뒤 성인과 노인 두 클래스에 대한 각 모델의 F1 점수를 확인하였다. 실험 결과로, 음향적 특징을 사용하였을 때보다 언어적 특징을 사용하였을 때 성인과 노인 분류에서 더 높은 성능을 보이는 것으로 나타났으며, 클래스 비율이 동일하더라도 노인에 대한 분류 성능보다 성인에 대한 분류 성능이 높음을 확인하였다.

• 대한음성학회지:말소리
• /
• 제41호
• /
• pp.83-96
• /
• 2001

It is generally said that falling intonation is used at the end of a declarative sentence. However, this is not the case with all stretches of spontaneous speech which are marked in transcription as sentences. The present paper examines intonation patterns appearing at the end of declarative sentences in oral presentations, and discusses instances where falling intonation does not appear. The texts used for analysis are eight oral presentations collected at international conferences in the field of physics. Quantitative and qualitative analyses are carried out. Three major factors related to discourse structure have been found for non-occurrence of falling intonation at sentence boundaries.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2000년도 7월 학술대회지
• /
• pp.149-164
• /
• 2000

It is generally said that falling intonation is used at the end of a declarative sentence. However, this is not the case with all stretches of spontaneous speech which are marked in transcription as sentences. The present paper examines intonation patterns appearing at the end of declarative sentences in oral presentations, and discusses instances where falling intonation does not appear. The texts used for analysis are eight oral presentations collected at international conferences in the field of physics. Quantitative and qualitative analyses are carried out. Three major factors related to discourse structure have been found for nonoccurrence of falling intonation at sentence boundaries.

• 음성과학
• /
• 제9권2호
• /
• pp.59-68
• /
• 2002

This paper analyzes the prosodic features distinctively associated with Korean topic constructions (marked by nun or its variant un) and subject constructions (marked by ka or its variant i) as a way of explicating the role that prosody plays in differentially constituting their discourse messages. Using both spoken data elicited in controlled settings and spontaneous conversational data, an attempt is made to identify differentiating prosodic features and intonation contours associated with distinct meanings and functions of nun- and ka-constructions evoked in a variety of discourse contexts.