• Korean Journal of Audiology
• /
• v.24 no.4
• /
• pp.180-190
• /
• 2020

Background and Objectives: Although many studies have evaluated the effect of the digital noise reduction (DNR) algorithm of hearing aids (HAs) on speech recognition, there are few studies on the effect of DNR on music perception. Therefore, we aimed to evaluate the effect of DNR on music, in addition to speech perception, using objective and subjective measurements. Subjects and Methods: Sixteen HA users participated in this study (58.00±10.44 years; 3 males and 13 females). The objective assessment of speech and music perception was based on the Korean version of the Clinical Assessment of Music Perception test and word and sentence recognition scores. Meanwhile, for the subjective assessment, the quality rating of speech and music as well as self-reported HA benefits were evaluated. Results: There was no improvement conferred with DNR of HAs on the objective assessment tests of speech and music perception. The pitch discrimination at 262 Hz in the DNR-off condition was better than that in the unaided condition (p=0.024); however, the unaided condition and the DNR-on conditions did not differ. In the Korean music background questionnaire, responses regarding ease of communication were better in the DNR-on condition than in the DNR-off condition (p=0.029). Conclusions: Speech and music perception or sound quality did not improve with the activation of DNR. However, DNR positively influenced the listener's subjective listening comfort. The DNR-off condition in HAs may be beneficial for pitch discrimination at some frequencies.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.338-338
• /
• 2000

This paper proposes a modified TD-PSOLA algorithm for Korean speech synthesis. A WSS (Weighted score search) algorithm is proposed for pitch detection and speech synthesis engine is designed using 46 phones database.

• Archives of Plastic Surgery
• /
• v.47 no.6
• /
• pp.542-550
• /
• 2020

Background This study aimed to identify the initial diagnostic characteristics and treatment status of children with submucous cleft palate (SMCP) and to examine the relationship between the timing of surgical correction and the degree of articulation and resonance improvement. Methods This retrospective study included 72 children diagnosed with SMCP between 2008 and 2016. The evaluation criteria were the age of the initial visit, total number of visits, age at the end of treatment, speech problems, resonance problems, and speech therapy. Results Children with SMCP first visited the hospital at an average age of 34.32 months, and speech problems were identified at an average age of 48.53 months. Out of 72 children, 46 underwent surgery at an average age of 49.74 months. Four of these children required secondary surgery at an average age of 83.5 months. Among the children who underwent surgery before 3 years of age, 70% exhibited articulation improvements, with mild-to-moderate hypernasality. Articulation improvements showed no statistically significant differences according to age at the time of surgery. However, children who underwent surgery before 4 years had a better hypernasality rating than those who underwent surgery after 4 years of age. Conclusions Children with SMCP tend to undergo delayed treatment because the anatomical symptoms in some children with SMCP are unclear, and surgical interventions are considered only after speech problems are clarified. Starting interventions as early as possible reduces the likelihood of receiving secondary surgery and speech therapy, while increasing expectations for positive speech function at the end.

• Phonetics and Speech Sciences
• /
• v.3 no.1
• /
• pp.125-134
• /
• 2011

The current study investigated the effects of experience of deaf speech, severity of speaker's articulation, and linguistic cues on speech intelligibility of congenitally deafened adults with cochlear implants. Speech intelligibility was judged by 28 experienced listeners and 40 inexperienced listeners using a word transcription task. A three-way (2 $\times$ 2 $\times$ 4) mixed design was used with the experience of deaf speech (experienced/inexperienced listener) as a between-subject factor, the severity of speaker's articulation (mild to moderate/moderate to severe), and linguistic cues (no/phonetic/semantic/combined) as within-subject factors. The dependent measure was the number of correctly transcribed words. Results revealed that three main effects were statistically significant. Experienced listeners showed better performance on the transcription than inexperienced listeners, and listeners were better in transcribing speakers who were mild to moderate than moderate to severe. There were significant differences in speech intelligibility among the four different types of cues, showing that the combined cues provided the greatest enhancement of the intelligibility scores (combined > semantic > phonological > no). Three two-way interactions were statistically significant, indicating that the type of cues and severity of speakers differentiated experienced listeners from inexperienced listeners. The current results suggested that the use of a combination of linguistic cues increased the speech intelligibility of congenitally deafened adults with cochlear implants, and the experience of deaf speech was critical especially in evaluating speech intelligibility of severe speakers compared to that of mild speakers.

• Journal of Broadcast Engineering
• /
• v.8 no.2
• /
• pp.198-203
• /
• 2003

We develop the method of estimating the endpoints of speech by jointly using the lip motion (visual speech) and speech being included in multimedia data and then propose a new speech recognition system (SRS) based on that method. The endpoints of noisy speech are estimated as follows : For each test word, two kinds of endpoints are detected from visual speech and clean speech, respectively Their difference is made and then added to the endpoints of visual speech to estimate those for noisy speech. This estimation method for endpoints (i.e. speech interval) is applied to form a new SRS. The SRS differs from the convention alone in that each word model in the recognizer is provided an interval of speech not Identical but estimated respectively for the corresponding word. Simulation results show that the proposed method enables the endpoints to be accurately estimated regardless of the amount of noise and consequently achieves 8 o/o improvement in recognition rate.

• MALSORI
• /
• v.55
• /
• pp.131-142
• /
• 2005

A mismatch between the training and the test conditions often causes a drastic decrease in the performance of the speech recognition systems. In this paper, non-linear transformation techniques based on histogram equalization in the acoustic feature space are studied for reducing the mismatched condition. The purpose of histogram equalization(HEQ) is to convert the probability distribution of test speech into the probability distribution of training speech. While conventional histogram equalization methods consider only the probability distribution of a test speech, for noise-corrupted test speech, its probability distribution is also distorted. The transformation function obtained by this distorted probability distribution maybe bring about miss-transformation of feature vectors, and this causes the performance of histogram equalization to decrease. Therefore, this paper proposes a new method of calculating noise-removed probability distribution by using assumption that the CDF of noisy speech feature vectors consists of component of speech feature vectors and component of noise feature vectors, and this compensated probability distribution is used in HEQ process. In the AURORA-2 framework, the proposed method reduced the error rate by over $44\%$ in clean training condition compared to the baseline system. For multi training condition, the proposed methods are also better than the baseline system.

• Phonetics and Speech Sciences
• /
• v.5 no.1
• /
• pp.39-46
• /
• 2013

This study examined the effects of phonetic complexity and articulatory severity on Percentage of Correct Consonant (PCC) and speech intelligibility in adults with dysarthria. Speech samples of thirty-two words from APAC (Assessment of Phonology and Articulation of Children) were collected from 38 dysarthric speakers with one of two different levels of articulatory severities (mild or mild-moderate). A PCC and speech intelligibility score was calculated by the 4 levels of phonetic complexity. Two-way mixed ANOVA analysis revealed: (1) the group with mild severity showed significantly higher PCC and speech intelligibility scores than the mild-moderate articulatory severity group, (2) PCC at the phonetic complexity level 4 was significantly lower than those at the other levels and (3) an interaction effect of articulatory severity and phonetic complexity was observed only on the PCC. Pearson correlation analysis demonstrated the degree of correlation between PCC and speech intelligibility varied depending on the level of articulatory severity and phonetic complexity. The clinical implications of the findings were discussed.

• Speech Sciences
• /
• v.12 no.2
• /
• pp.89-99
• /
• 2005

The purpose of the present study were (1) to assess differences in tongue performances and speech intelligibility between normal and dysarthric speakers; and (2) to analyze the possible interrelationships between tongue strength, range of motion, and speech intelligibility in dysarthric patients. In order to measure maximum strength of anterior and lateral tongue strength, a force transducer has been designed. And a ruler was used for guaging range of motion. 'Word intelligibility test' was administered to each group. The results were analyzed by a quantitative statistical method(t test, Pearson product- moment correlation, and one-way ANOVA). The results were as follows; (1) dysarthric speakers showed significantly poorer performance than the normal in the tongue strength, range of motion, and speech intelligibility tasks; (2) the correlation between speech intelligibility and instrumental tongue performance was high in the dysarthric group; and (3) instrumental assessment was coincide with perceptual judgement of dysarthric tongue performance. The present investigation demonstrated that tongue weakness is causally related to articulation deficits in dysarthric. The clinical use of the force transducer would help a speech pathologist to quantify the degree of tongue weakness.

• Archives of Plastic Surgery
• /
• v.32 no.3
• /
• pp.375-380
• /
• 2005

Furlow palatoplasty has been favored by many plastic surgeons as the primary treatment for the velopharyngeal insufficiency associated with submucous cleft palate. The purpose of this article is to introduce an efficacy of Furlow palatoplasty and speech therapy performed on patients who were diagnosed belatedly as having submucous cleft palates. From 2002 to 2004, four submucous cleft palate patients over 5 years of age with velopharyngeal insufficiency received Furlow palatoplasty. The patients were evaluated through the preoperative perceptual speech assessment, nasometry, and videonasopharyngoscopy. Postoperatively, two patients achieved competent velopharyngeal function in running speech. One of the remaining two could achieve competent velopharyngeal function with visual biofeedback speech therapy and the other could not use her new velopharyngeal function in running speech because of her age. Speech therapy can correct the articulation errors and thus improve the velopharyngeal function to a certain extent by eliminating some compensatory articulations that might have an adverse influence on velopharyngeal function. This study shows that Furlow palatoplasty can successfully correct the velopharyngeal insufficiency in submucous cleft palate patients and speech therapy has a role in reinforcing surgical result. But age is still a restrictive factor even though surgery was well done.

• Phonetics and Speech Sciences
• /
• v.9 no.4
• /
• pp.59-67
• /
• 2017

Regardless of their intention, listeners tend to assess speakers' personalities based on the sounds of the speech they hear. Assessment criteria, however, have not been fully investigated to indicate whether there is any relationship between the acoustic cue of produced speech sounds and perceived personality impression. If properly investigated, the potential relationship between these two will provide crucial insights on the aspects of human communications and further on human-computer interaction. Since human communications have distinctive characteristics of simultaneity and complexity, this investigation would be the identification of minimum essential factors among the sounds of speech and perceived personality impression. The purpose of this study, therefore, is to identify significant associations between the speech sounds and perceived personality impression of speaker by the listeners. Twenty eight subjects participated in the experiment and eight acoustic parameters were extracted by using Praat from the recorded sounds of the speech. The subjects also completed the Neo-five Factor Inventory test so that their personality traits could be measured. The results of the experiment show that four major factors(duration average, pitch difference value, pitch average and intensity average) play crucial roles in defining the significant relationship.