• The Journal of the Acoustical Society of Korea
• /
• 제23권4E호
• /
• pp.112-119
• /
• 2004

This paper presents a method for the automatic recognition of pitch accents with no prior knowledge about the phonetic content of the signal (no knowledge of word or phoneme boundaries or of phoneme labels). The recognition algorithm used in this paper is a time-delay recurrent neural network (TDRNN). A TDRNN is a neural network classier with two different representations of dynamic context: delayed input nodes allow the representation of an explicit trajectory F0(t), while recurrent nodes provide long-term context information that can be used to normalize the input F0 trajectory. Performance of the TDRNN is compared to the performance of a MLP (multi-layer perceptron) and an HMM (Hidden Markov Model) on the same task. The TDRNN shows the correct recognition of $91.9{\%}\;of\;pitch\;events\;and\;91.0{\%}$ of pitch non-events, for an average accuracy of $91.5{\%}$ over both pitch events and non-events. The MLP with contextual input exhibits $85.8{\%},\;85.5{\%},\;and\;85.6{\%}$ recognition accuracy respectively, while the HMM shows the correct recognition of $36.8{\%}\;of\;pitch\;events\;and\;87.3{\%}$ of pitch non-events, for an average accuracy of $62.2{\%}$ over both pitch events and non-events. These results suggest that the TDRNN architecture is useful for the automatic recognition of pitch accents.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2000년도 하계학술발표대회 논문집 제19권 1호
• /
• pp.87-90
• /
• 2000

문-음성 합성기의 자연감을 높이기 위해 주로 자연음에 존재하는 운률 법칙을 정확히 구현해 주어야 한다. 일반적으로 언어학적 정보를 이용하거나 자연음으로부터 추출한 운률 정보를 추출한 운률 법칙을 합성에 이용하고 있다. 이와 같이 구한 운률 법칙이 자연음에 존재하는 모든 운률 법칙을 포함할 수 있으면, 자연스러운 합성음을 들을 수 있겠으나, 실질적으로는 모든 법칙을 구현한다는 것은 어려운 실정이고, 자연음으로부터 추출한 운률 법칙이 잘못 구현되는 경우 합성음의 자연성이 떨어지는 것을 피할 수 없을 것이다. 이런 점을 고려하여 우리는 자연음에 내재하는 운율 법칙을 훈련을 통해 학습할 수 있는 인공 신경망을 제안하였다 운률의 세 가지 요소는 피치, 지속시간, 크기 변화가 있는데, 인공 신경망은 문장이 입력되면, 각 해당 음소의 지속시간에 따른 피치 변화와 크기 변화를 학습할 수 있도록 설계하였다. 신경망을 훈련시키기 위해 고립 단어군과 음소균형 문장군을 화자로 하여금 발성하게 하여, 녹음하고, 분석하여 운률 데이터베이스를 구축하였다. 자연음의 각 음소에 대해 지속시간과 피치변화 그리고 크기 변화를 구하여 곡선 적응 방법을 이용하여 각 변화 곡선에 대한 계수를 구해 데이터베이스를 구축한다. 이렇게 구축한 데이터베이스를 이용해 인공 신경망을 훈련시켜 평가한 결과 훈련용 데이터를 계속 확장하면 좀 더 자연스러운 운률을 발생시킬 수 있음을 관찰하였다.

• 말소리와 음성과학
• /
• 제10권1호
• /
• pp.15-22
• /
• 2018

Stressed vowels in English are usually produced using longer duration, higher pitch, and greater intensity than unstressed vowels. However, many English as a foreign language (EFL) learners have difficulty producing English lexical stress because their mother tongues do not have such features. In order to investigate if certain non-native English speakers (Korean, Japanese, and Taiwanese-Chinese native speakers) are able to produce English lexical stress in a native-like manner, speech samples were extracted from the L2 learners' corpus known as AESOP (the Asian English Speech cOrpus Project). Sixteen disyllabic words were analyzed in terms of the ratio of duration, pitch, and intensity. The results demonstrate that non-native English speakers are able to produce English stress in a similar way to native English speakers, and all speakers (both native and non-native) show a tendency to use duration as the strongest cue in producing stress. The results also show that the duration ratio of native English speakers was significantly higher than that of non-native speakers, indicating that native speakers produce a bigger difference in duration between stressed and unstressed vowels.

• 음성과학
• /
• 제11권1호
• /
• pp.105-116
• /
• 2004

The fundamental frequency of a vowel is known to be affected by the identity of the preceding consonant. The general agreement is that strong consonants trigger higher F0 than weak consonants. However, there has been a disagreement on the shape of this segmentally affected F0 contours. Some studies report that shapes of contours are differentiated based on the consonant type, but others regard this observation as misleading. This research attempts to resolve this controversy by investigating shapes and slopes of F0 contours of Korean word level speech data produced by four male speakers. Instead of entirely relying on traditional human intuition and judgment, I employed an automatic F0 contour analysis technique known as tilt parameterisation (Taylor 2000). After necessary manipulation of an F0 contour of each data token, various parameters are collapsed into a single tilt value which directly indicates the shape of the contour. The result, in terms of statistical inference, shows that it is not viable to conclude that the type of consonant is significantly related to the shape of F0 contour. A supplementary measurement is also made to see if the slope of each contour bears meaningful information. Unlike shapes themselves, slopes are suspected to be practically more practical for consonantal differentiation, although confirmation is required through further refined experiments.

• 한국영어학회지:영어학
• /
• 제1권4호
• /
• pp.509-536
• /
• 2001

The traditional typology of English poetic meters makes a binary division between strong-stress (or accentual) meters and accentual-syllabic (or syllable-stress or syllable-accent) meters. According to this typology, Old and Middle English alliterative poetry was composed in strong-stress meter; the iambic pentameter from Chaucer to Yeats and on to the present has been an accentual-syllabic meter. Intersecting with this literary typology is a linguistic typology that classifies languages of the world as stress-timed or syllable-timed or some mix of the two. English is a clear example of a stress-timed language. Whereas most descriptions of strong-stress meter focus on the counting of stresses, the present study focuses on the patterns of unstressed syllables between the stresses (possibly at isochronous intervals). The implications of this analysis suggest a new typology in which certain forms of English verse follow strict grammatical stress (mainly Old and Middle English, but for reasons different from “strong-stress” expectations) and other forms are shaped by a compromise of grammatical stress and the metrical template. Within this later group, iambic pentameter contrasts with trochaic, anapestic, and dipodic meters in lending itself more readily to modulation. Some of this modulation comes from an easy incorporation into iambic pentameter of elements associated with Old and Middle English meters.

• 음성과학
• /
• 제14권1호
• /
• pp.37-62
• /
• 2007

The current study examines the role of post-lexical tonal patterns of a prosodic phrase in word segmentation. In a word spotting experiment, native Korean listeners were asked to spot a disyllabic or trisyllabic word from twelve syllable speech stream that was composed of three Accentual Phrases (AP). Words occurred with various post-lexical intonation patterns. The results showed that listeners spotted more words in phrase-initial than in phrase-medial position, suggesting that the AP-final H tone from the preceding AP helped listeners to segment the phrase-initial word in the target AP. Results also showed that listeners' error rates were significantly lower when words occurred with initial rising tonal pattern, which is the most frequent intonational pattern imposed upon multisyllabic words in Korean, than with non-rising patterns. This result was observed both in AP-initial and in AP-medial positions, regardless of the frequency and legality of overall AP tonal patterns. Tonal cues other than initial rising tone did not positively influence the error rate. These results not only indicate that rising tone in AP-initial and AP_final position is a reliable cue for word boundary detection for Korean listeners, but further suggest that phrasal intonation contours serve as a possible word boundary cue in languages without lexical prominence.

• 음성과학
• /
• 제15권1호
• /
• pp.7-23
• /
• 2008

This paper investigates tonal patterns of the prosodic constituents of an AP and a PWD in Korean and their relation with the morphological/syntactic structure. Specifically, this paper asks the following questions: First, if there are more than one PWD in an AP, how is each PWD specified in terms of tones? Secondly, in case that there is only one PWD in an AP that consists of several morphemes, is there any preference of the association between tones and the morphemes that constitute that PWD? Thirdly, if an AP dominates a PWD and if a PWD contains at least one morpheme of the lexical category, it follows that an AP should contain at least one morpheme of the lexical category. Can this be verified with the experimental data? In order to answer these questions, Experiment I and II were conducted with the target material consisting of a stem and suffixes that varied in length. The results of this preliminary test show that as the number of syllables in the target material increases, the more number of an AP tonal pattern occurs in it and as a result, in some cases, an AP consisting of suffixes only may occur.

• 말소리와 음성과학
• /
• 제8권4호
• /
• pp.31-38
• /
• 2016

The purpose of the current study was to examine the acquisition of the second language prosody by Korean learners of English. Specifically, this study investigated Korean learners' patterns of prosodic phrasing and their use of edge tones (i.e., phrase accents and boundary tones) in English, and then compared the patterns with those of native English speakers. Eight Korean learners and 8 native speakers of English read 5 different English passages. Both groups' patterns of tones and prosodic phrasing were analyzed using the Mainstream American English Tones and Break Indices (MAE_ToBI) transcription conventions. The results indicated that the Korean learners chunked their speech into prosodic phrases more frequently than the native speakers did. This frequent prosodic phrasing pattern was especially noticeable in sentence-internal prosodic phrases, often where there was no punctuation mark. Tonal analyses revealed that the Korean learners put significantly more High phrase accents (H-) on their sentence-internal intermediate phrase boundaries than the native speakers of English. In addition, compared with the native speakers, the Korean learners used significantly more High boundary tones (both H-H% and L-H%) for the sentence-internal intonational phrases, while they used similar proportion of High boundary tones for the sentence-final intonational phrases. Overall, the results suggested that Korean learners of English successfully acquired the meanings and functions of prosodic phrasing and edge tones in English as well as that they are able to efficiently use these prosodic features to convey their own discourse intention.

• 말소리와 음성과학
• /
• 제8권4호
• /
• pp.89-95
• /
• 2016

The purpose of this work is to analyze and synthesize the pseudo-periodicity of voice using a source model. A speech signal has periodic characteristics; however, it is not completely periodic. While periodicity contributes significantly to the production of prosody, emotional status, etc., pseudo-periodicity contributes to the distinctions between normal and abnormal status, the naturalness of normal speech, etc. Measurement of pseudo-periodicity is typically performed through parameters such as jitter and shimmer. For studying the pseudo-periodic nature of voice in a controlled environment, through collected natural voice, we can only observe the distributions of the parameters, which are limited by the size of collected data. If we can generate voice samples in a controlled manner, experiments that are more diverse can be conducted. In this study, the probability distributions of vowel pitch variation are obtained from the speech signal. Based on the probability distribution of vocal folds, pulses with a designated jitter value are synthesized. Then, the target and re-analyzed jitter values are compared to check the validity of the method. It was found that the jitter synthesis method is useful for normal voice synthesis.

• 대한후두음성언어의학회지
• /
• 제30권2호
• /
• pp.87-94
• /
• 2019

The purpose of this study was to investigate the speech characteristics and speech therapy of Parkinson disease (PD). This study selected 28 papers published in Korea from 1998 to 2018 after searching the terms 'Parkinson voice' and 'Parkinson speech therapy.' Literature review had been conducted in the two aspects of speech characteristics and speech therapy. The speech characteristics were divided into respiration, phonation, articulation, prosody, vowel production, and voice questionnaire. Speech therapy was divided into Lee Sliverman voice treatment (LSVT) and other voice therapy. PD patients did not differ in respiration function compared to normal elderly people, but their speech and articulation function were poorer. There was also a difference in the speech rate, frequency of pause, and accuracy of vowel production compared with normal elderly people. PD had a lower VHI score and their voice related quality of life was a little poorer. The LSVT was typically used in speech therapy for PD. The methods of speech therapy for PD have been shown to improve respiration and phonation. It is necessary to establish voice norms in PD patients and develop effective speech therapy in the following study.