• 말소리와 음성과학
• /
• 제1권2호
• /
• 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.

• 한국어교육
• /
• 제29권3호
• /
• pp.345-363
• /
• 2018

The purpose of this study is to compare the speech rate of advanced Korean(L2) learners and Korean native speakers in spontaneous utterances. Specifically, the current study investigated the difference of the two groups' speech pattern according to utterance length. Eight advanced Korean(L2) learners and eight Korean native speakers participated in this study. The data were collected by recording their conversation and physical measurements (speaking rate, articulatory rates, pause and several types of speech disfluency) were taken on extracted 120 utterances from 12 out of the 16 participants. The findings show that advanced Korean learners' speech pattern is similar to that of Koreans in the short-length utterance. However, in the long-length utterance, two groups show different speech patterns; while the articulatory rate of Korean native speakers increased in the long-length utterance, that of Korean learners decreased. This suggests that the frequency of speech disfluency factors might affect this result.

• 말소리와 음성과학
• /
• 제15권1호
• /
• pp.55-64
• /
• 2023

본 연구에서는 직업군인의 말더듬 성인에 대한 군대 적응 예측 정도와 이러한 인식에 유의한 영향을 미치는 요인들이 무엇인지를 알아보았다. 이를 위해 89명의 직업군인을 대상으로 발화 유창성 정도와 관련해 세 가지 버전[유창한 발화(23명), 덜 심한 말더듬(34명), 심한 말더듬(32명)] 중 무작위로 배정된 하나의 음성샘플을 들려주고 발화 관련 요인(유창성, 명료도, 자연스러움, 말속도), 성격 관련 요인(호감, 지적 수준, 불안, 사교성), 그리고 군대 적응 예측 정도를 평가하였다. 연구 결과, 군대 적응 예측 정도에서 유창한 발화와 심한 말더듬 간, 그리고 덜 심한 말더듬과 심한 말더듬 간에서 유의한 차이가 나타났다. 반면, 유창한 발화와 덜 심한 말더듬 간에서는 유의한 차이가 나타나지 않았다. 상관관계 분석 결과, 군대 적응 예측 정도에 있어 발화 특성 요인 중에서는 발화 유창성, 명료도, 자연스러움, 말속도 순으로, 성격 관련 인상 요인 중에서는 호감, 사교성, 불안, 지적 수준의 순으로 높은 상관관계가 나타났다. 발화 유창성이 군대 적응 예측 정도에 있어 상대적으로 높은 상관관계를 보이고 있는 것이다. 발화 관련 특성 요인과 군대 적응 예측 정도와의 관련성에 대해 추가적인 논의를 기술하였다.

• 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.

• 대한후두음성언어의학회지
• /
• 제16권2호
• /
• pp.158-164
• /
• 2005

Melody intonation therepy (MIT) is to improve the linguistic aspects of the verbal utterance for aphasic patients utilizing the intact right brain. It is applied to the aphasic patients with good comprehension, poor fluency, and little available speech are thought to be ideal candidates. The purpose of the study was to investigate the effects of Korean Melody intonation therapy (kMIT) in patients with non-fluent aphasia. Five male non-fluent aphasic patients were participated in this study. Average ages were 49.9 years old. Each therapy took 45-50minutes once a week for six months. Aphasic Screen lest (RISS) was used to assess language parameter such as Auditory comprehension, oral expression, reading, writing and calculation ability before and after kMIT. Mean of Length Utterance, verbal intelligibility and articulation disorder were assessed also. Computerized Speech Lab was used to assess the acoustic characteristics of aphasic patients before and after kMIT. The results are as follows : 1) Auditory comprehension, oral expression, reading, writing and calculation ability of the subjects increased after UH'. However, only oral expression showed significant difference (p<0.05). 2) Mean of Length Utterance of five patients generally increased after Un. 3) After kMIT, verbal intelligibility increased and showed significant difference (p<0.05). 4) Misarticulation rate generally decreased after m. 5) Voice Onset Time of the alveolar lenis /t/ and velar lenis /k/ gradually decreased after kMIT. 6) However, intonation pattern were increased gradually in yes'no question after kMIT.

• 말소리와 음성과학
• /
• 제4권2호
• /
• pp.121-126
• /
• 2012

This study deals with how stuttering changes in its frequency in a situation where adult participants who stutter are exposed to one type of background noise, that is, multi-talker babble noise. Eight American English-speaking adults who stutter participated in this study. Each of the subjects read aloud sentences under each of three speaking conditions (i.e., typical solo reading (TSR), typical choral reading (TCR), and multi-talker babble noise reading (BNR)). Speech fluency was computed based on a percentage of syllables stuttered (%SS) and speaking rate was also assessed to examine if there was significant change in rates as a measure of vocal change under each of the speaking conditions. The study found that participants read more fluently both during BNR and during TCR than during TSR. The study also found that participants did not show significant changes in speaking rate across the three speaking conditions. Some discussion was provided in relation to the effect of multi-talker babble noise on the frequency of stuttering and its further speculation.

• 말소리와 음성과학
• /
• 제2권2호
• /
• pp.69-75
• /
• 2010

We propose an automatic pronunciation diagnosis system to evaluate the pronunciation of a foreign language without the uttered text. We recorded English utterances spoken by native and Korean speakers, and utterances spoken by Koreans are evaluated by native speakers based on three criteria: fluency, accuracy of phones and intonation. The system evaluates the utterances of test Korean speakers based on the differences of log-likelihood given two models: one is trained by English speech uttered by native speakers, and the other is trained by English speech uttered by Korean speakers. We also applied purification algorithm to increase class differentiability. The purification can detect and eliminate the non-speech frames such as short pauses, occlusive silences that do not help to discriminate between utterances. As the results, our proposed system has higher correlation with the human scores than the baseline system.

• 한국인터넷방송통신학회논문지
• /
• 제16권2호
• /
• pp.131-136
• /
• 2016

외국어 학습에서 발음학습은 가장 중요한 부분 중 하나이다. 발음학습 과정은 학습자의 발음에 대해 정확한 평가와 잘못된 발음이 있을 경우 적절한 피드백을 주어 이를 개선시키는 작업을 포함한다. 숙련된 평가자의 평가는 비용에서, 비숙련 원어민들의 평가는 일관성에서 문제가 있기 때문에 이를 보완할 수 있는 자동발음평가 시스템에 대한 연구가 진행되고 있으며 자동음성인식 기술의 활용이 각광받고 있다. 본 연구에서는 자동음성인식 기술과 비원어민 교수자의 음성 모델을 기반으로 단어 수준에서 학습자의 발음 정확성과 유창성을 평가하는 시스템을 구축하였고, 이를 통해 학습자들이 자신의 발음을 정확히 평가받고 평가결과에 따라 적절한 피드백을 받을 수 있도록 하였다. 또한 시스템의 성능평가를 통해 발음 정확성과 유창성에 대한 자동평가결과가 전반적으로 학습자의 실제 영어실력을 정확히 구분한다는 것을 확인하였다.

• 말소리와 음성과학
• /
• 제15권1호
• /
• pp.47-54
• /
• 2023

This study attempted to test the hypothesis that Korean evaluators can score L2 speech appropriately, even when speech rate features are unavailable. Two perception experiments-preliminary and main-were conducted sequentially. The purpose of the preliminary experiment was to categorize English-as-a-foreign-language (EFL) speakers into two groups-advanced learners and lower-level learners-based on the proficiency scores given by five human raters. In the main experiment, a set of stimuli was prepared such that the speech rate of all data tokens was modified to have a uniform speech rate. Ten human evaluators were asked to score the stimulus tokens on a 5-point scale. These scores were statistically analyzed to determine whether there was a significant difference in utterance production between the two groups. The results of the preliminary experiment confirm that higher-proficiency learners speak faster than lower-proficiency learners. The results of the main experiment indicate that under controlled speech-rate conditions, human raters can appropriately assess learner proficiency, probably thanks to the linguistic features that the raters considered during the evaluation process.

• 한국융합학회논문지
• /
• 제11권12호
• /
• pp.383-390
• /
• 2020

본 연구는 알츠하이머와 혈관성 치매 환자를 대상으로 구어유창성과 이야기이해 과제 수행능력의 차이 및 작업기억 처리수준과의 상관 그리고 언어능력 관련 요인선별을 위해 시행되었다. 전반적인 인지능력에서 차이를 보이지 않는 각기 15명의 환자를 대상으로 구어유창성 내 음소유창성 및 이야기이해 그리고 작업기억 하위과제인 지연회상과 재인과제에서 두 그룹 간 유의한 수행능력의 차이를 보였다. 상관 및 회귀분석에서는 알츠하이머 그룹이 작업기억 내역행 숫자기억 과제와 이야기이해 과제에서만 유의한 상관을 보인 반면, 혈관성 치매 그룹은 추가적으로 재인 점수에서도 이야기이해 능력과의 유의한 상관이 나타났다. 한편, 회귀분석에서는 혈관성 치매 그룹에서만 언어적 작업기억 능력이 이야기이해 능력의 예측 요인임을 확인하였다. 결론적으로 두 유형의 치매를 구분하는 데 있어 음소유창성 과제 외에 이야기이해 및 작업기억 과제가 유의한 도구임이 확인되었는데, 이를 통해 두 유형의 치매에 대한 분류기준을 제고함은 물론 적절한 치료계획 및 효율적인 중재에 부가적인 기여를 할 것으로 보인다.