• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.253-256
• /
• 2017

This paper deals with the implementation of speech disorder detection system based on machine learning classification. Problems with speech are a common early symptom of a stroke or other brain injuries. Therefore, detection of speech disorder may lead to correction and fast medical treatment of strokes or cerebrovascular accidents. The speech disorder system can be implemented by extracting features from the input speech and classifying the features using machine learning algorithms. Ten machine learning algorithms with various scaling methods were used to discriminate speech disorder from normal speech. The detection system was evaluated by the TORGO database which contains dysarthric speech collected from speakers with either cerebral palsy or amyotrophic lateral sclerosis.

• Phonetics and Speech Sciences
• /
• v.8 no.1
• /
• pp.63-69
• /
• 2016

The aims of the present study are two-fold: 1) to explore differences on speech perception between younger and older adults according to noise conditions; and 2) to investigate which cognitive domains are correlated with speech perception. Data were acquired from 15 younger adults and 15 older adults. Sentence recognition test was conducted in four noise conditions(i.e., in-quiet, +5 dB SNR, 0 dB SNR, -5 dB SNR). All participants completed auditory and cognitive assessment. Upon controlling for hearing thresholds, the older group revealed significantly poorer performance compared to the younger adults only under the high noise condition at -5 dB SNR. For older group, performance on Seoul Verbal Learning Test(immediate recall) was significantly correlated with speech perception performance, upon controlling for hearing thresholds. In older adults, working memory and verbal short-term memory are the best predictors of speech-in-noise perception. The current study suggests that consideration of cognitive function for older adults in speech perception assessment is necessary due to its adverse effect on speech perception under background noise.

• Phonetics and Speech Sciences
• /
• v.4 no.4
• /
• pp.71-77
• /
• 2012

Sasang constitution experts utilize voice characteristics as an auxiliary measure for deciding a person's constitutional group. This study aims at establishing a relationship between speech features and the constitutional groups by subjective listening evaluation of voice characteristics. A speech database of 841 speakers whose constitutional groups have been already diagnosed by Sasang constitution experts was constructed. Speech features related to speech source and vocal tract filter were extracted from five vowels and one sentence. Statistically significant speech features for classifying the groups were analyzed using SPSS. The features contributed to constitution classification were speaking rate, Energy, A1, A2, A3, H1, H2, H4, CPP for males in their 20s, F0_mean, CPP, SPI, HNR, Shimmer, Energy, A1, A2, A3, H1, H2, H4 for females in their 20s, Energy, A1, A2, A3, H1, H2, H4, CPP for male in the 60s, and Jitter, HNR, CPP, SPI for females in their 60s. Experimental results show that speech technology is useful in classifying constitutional groups.

• Phonetics and Speech Sciences
• /
• v.3 no.3
• /
• pp.19-26
• /
• 2011

Previous laboratory studies have shown that prosodic structures are encoded in the modulations of phonetic patterns of speech including suprasegmental as well as segmental features. Drawing on a prosodically annotated large-scale speech data from the Buckeye corpus of conversational speech of American English, the current study first evaluated the reliability of prosody annotation by a large number of ordinary listeners and later examined whether and how prosodic prominence influences the phonetic realization of multiple acoustic parameters in everyday conversational speech. The results showed that all the measures of acoustic parameters including pitch, loudness, duration, and spectral balance are increased when heard as prominent. These findings suggest that prosodic prominence enhances the phonetic characteristics of the acoustic parameters. The results also showed that the degree of phonetic enhancement vary depending on the types of the acoustic parameters. With respect to the formant structure, the findings from the present study more consistently support Sonority Expansion Hypothesis than Hyperarticulation Hypothesis, showing that the lexically stressed vowels are hyperarticulated only when hyperarticulation does not interfere with sonority expansion. Taken all into account, the present study showed that prosodic prominence modulates the phonetic realization of the acoustic parameters to the direction of the phonetic strengthening in everyday conversational speech and ordinary listeners are attentive to such phonetic variation associated with prosody in speech perception. However, the present study also showed that in everyday conversational speech there is no single dominant acoustic measure signaling prosodic prominence and listeners must attend to such small acoustic variation or integrate acoustic information from multiple acoustic parameters in prosody perception.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3166-3168
• /
• 2000

This paper proposed variable threshold dual rate ADPCM coding method which is modified from the standard ADPCM of ITU G.726 for speech quality improvement. The speech quality of variable threshold dual rate ADPCM is better than single rate ADPCM at noisy environment without increasing the complexity by using ZCR(Zero Crossing Rate). In this case, ZCR is used to divide input signal samples into two categories(noisy & speech). The samples with higher ZCR is categorized as the noisy region and the samples with lower ZCR is categorized as the speech region. Noisy region uses higher threshold value to be compressed by 16Kbps for reduced bit rates and the speech region uses lower threshold value to be compressed by 40Kbps for improved speech quality. Comparing with the conventional ADPCM, which adapts the fixed coding rate. the proposed variable threshold dual rate ADPCM coding method improves noise character without increasing the bit rate. For real time applications, ZCR calculation was considered as a simple method to obtain the background noise information for preprocess of speech analysis such as FFT and the experiment showed that the simple calculation of ZCR can be used without complexity increase. Dual rate ADPCM can decrease the amount of transferred data efficiently without increasing complexity nor reducing speech quality. Therefore result of this paper can be applied for real-time speech application such as the internet phone or VoIP.

• Journal of Audiology & Otology
• /
• v.24 no.3
• /
• pp.140-148
• /
• 2020

Background and Objectives: The aim of this study is to evaluate the effect of music training on the characteristics of auditory perception of speech and music. The perception of speech and music stimuli was assessed across their respective stimulus continuum and the resultant plots were compared between musicians and non-musicians. Subjects and Methods: Thirty musicians with formal music training and twenty-seven non-musicians participated in the study (age: 20 to 30 years). They were assessed for identification of consonant-vowel syllables (/da/ to /ga/), vowels (/u/ to /a/), vocal music note (/ri/ to /ga/), and instrumental music note (/ri/ to /ga/) across their respective stimulus continuum. The continua contained 15 tokens with equal step size between any adjacent tokens. The resultant identification scores were plotted against each token and were analyzed for presence of categorical boundary. If the categorical boundary was found, the plots were analyzed by six parameters of categorical perception; for the point of 50% crossover, lower edge of categorical boundary, upper edge of categorical boundary, phoneme boundary width, slope, and intercepts. Results: Overall, the results showed that both speech and music are perceived differently in musicians and non-musicians. In musicians, both speech and music are categorically perceived, while in non-musicians, only speech is perceived categorically. Conclusions: The findings of the present study indicate that music is perceived categorically by musicians, even if the stimulus is devoid of vocal tract features. The findings support that the categorical perception is strongly influenced by training and results are discussed in light of notions of motor theory of speech perception.

• Speech Sciences
• /
• v.10 no.3
• /
• pp.7-27
• /
• 2003

Esophageal Speech uses the esophageal air during phonation. Fluent esophageal speakers frequently intake air in oral communication, but unskilled esophageal speakers are difficult with swallowing lots of air. The purpose of this study was to investigate the difference of acoustic characteristics of vowel and consonants production according to the speech proficiency level in esophageal speech. 13 normal male speakers and 13 male esophageal speakers (5 unskilled esophageal speakers, 8 skilled esophageal speakers) with age ranging from 50 to 70 years old. The stimuli were sustained /a/ vowel and 36 meaningless two syllable words. Used vowel is /a/ and consonants were 18 : /k, n, t, m, p, s, c, $C^{h},\;k^{h},\;t^{h},\;p^{h}$, h, I, k', t', p', s', c'/. Fundermental frequency (Fx), Jitter, shimmer, HNR, MPT were measured with by electroglottography using Lx speech studio (Laryngograph Ltd, London, UK). 36 meaningless words produced by esophageal speakers were presented to 3 speech-language pathologists who phonetically transcribed their responses. Fx, Jitter, HNR parameters is significant different between skilled esophageal speakers and unskilled esophageal speakers (P<.05). Considering manner of articulation, ANOVA showed that differences in two esophageal speech groups on speech proficiency were significant; Glide had the highest number of confusion with the other phoneme class, affricates are the most intelligible in the unskilled esophageal speech group, whereas in the skilled esophageal speech group fricatives resulted highest number of confusions, nasals are the most intelligible. In the place of articulation, glottal /h/ is the highest confusion consonant in both groups. Bilabials are the most intelligible in the skilled esophageal speech, velars are the most intelligible in the unskilled esophageal speech. In the structure of syllable, 'CV+V' is more confusion in the skilled esophageal group, unskilled esophageal speech group has similar confusion in both structures. In unskilled esophageal speech, significantly different Fx, Jitter, HNR acoustic parameters of vowel and the highest confusions of Liquid, Nasals consonants could be attributed to unstable, improper contact of neoglottis as vibratory source and insufficiency in the phonatory air supply, and higher motoric demand of remaining articulation due to morphological characteristics of vocal tract after laryngectomy.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.39-48
• /
• 2018

A typical statistical parametric speech synthesis (text-to-speech, TTS) system consists of separate modules, such as a text analysis module, an acoustic modeling module, and a speech synthesis module. This causes two problems: 1) expert knowledge of each module is required, and 2) errors generated in each module accumulate passing through each module. An end-to-end TTS system could avoid such problems by synthesizing voice signals directly from an input string. In this study, we implemented an end-to-end Korean TTS system using Google's Tacotron, which is an end-to-end TTS system based on a sequence-to-sequence model with attention mechanism. We used 4392 utterances spoken by a Korean female speaker, an amount that corresponds to 37% of the dataset Google used for training Tacotron. Our system obtained mean opinion score (MOS) 2.98 and degradation mean opinion score (DMOS) 3.25. We will discuss the factors which affected training of the system. Experiments demonstrate that the post-processing network needs to be designed considering output language and input characters and that according to the amount of training data, the maximum value of n for n-grams modeled by the encoder should be small enough.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2E
• /
• pp.43-50
• /
• 2009

To get more natural synthetic speech generated by a Korean TTS (Text-To-Speech) system, we have to know all the possible prosodic rules in Korean spoken language. We should find out these rules from linguistic, phonetic information or from real speech. In general, all of these rules should be integrated into a prosody-generation algorithm in a TTS system. But this algorithm cannot cover up all the possible prosodic rules in a language and it is not perfect, so the naturalness of synthesized speech cannot be as good as we expect. ANNs (Artificial Neural Networks) can be trained to learn the prosodic rules in Korean spoken language. To train and test ANNs, we need to prepare the prosodic patterns of all the phonemic segments in a prosodic corpus. A prosodic corpus will include meaningful sentences to represent all the possible prosodic rules. Sentences in the corpus were made by picking up a series of words from the list of PB (phonetically Balanced) isolated words. These sentences in the corpus were read by speakers, recorded, and collected as a speech database. By analyzing recorded real speech, we can extract prosodic pattern about each phoneme, and assign them as target and test patterns for ANNs. ANNs can learn the prosody from natural speech and generate prosodic patterns of the central phonemic segment in phoneme strings as output response of ANNs when phoneme strings of a sentence are given to ANNs as input stimuli.

• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.115-118
• /
• 2002

Neural networks have been known to have great discriminative power in pattern classification problems. In this paper, the multilayer perceptron neural networks are employed to automatically detect laryngeal pathology in speech. Also new feature parameters are introduced which can reflect the periodicity of speech and its perturbation. These parameters and cepstral coefficients are used as input of the multilayer perceptron neural networks. According to the experiment using Korean disordered speech database, incorporation of new parameters with cepstral coefficients outperforms the case with only cepstral coefficients.