• 대한후두음성언어의학회지
• /
• 제33권3호
• /
• pp.142-155
• /
• 2022

Diagnosis using voice is non-invasive and can be implemented through various voice recording devices; therefore, it can be used as a screening or diagnostic assistant tool for laryngeal voice disease to help clinicians. The development of artificial intelligence algorithms, such as machine learning, led by the latest deep learning technology, began with a binary classification that distinguishes normal and pathological voices; consequently, it has contributed in improving the accuracy of multi-classification to classify various types of pathological voices. However, no conclusions that can be applied in the clinical field have yet been achieved. Most studies on pathological speech classification using speech have used the continuous short vowel /ah/, which is relatively easier than using continuous or running speech. However, continuous speech has the potential to derive more accurate results as additional information can be obtained from the change in the voice signal over time. In this review, explanations of terms related to artificial intelligence research, and the latest trends in machine learning and deep learning algorithms are reviewed; furthermore, the latest research results and limitations are introduced to provide future directions for researchers.

• Korean Journal of Otorhinolaryngology-Head and Neck Surgery
• /
• 제61권11호
• /
• pp.619-623
• /
• 2018

Mucosal bridges of vocal fold have been described as a parallel band to vocal folds with the presence of sulcus vocalis. However, the type of mucosal bridge crossing each vocal fold has not been well documented in the literature. Herein, we present two cases of mucosal bridge found in the vocal fold connecting the mid-portions of true vocal folds. Two patients who had no history of laryngeal trauma, surgery or oro-tracheal intubation visited our clinic due to voice change. Laryngoscopic examination revealed that they had a mid-portion mucosal band without any other mucosal lesions. Two patients underwent laryngomicrosurgery with pulsed dye laser. After the surgery, they showed significant improvement of voice quality.

• 음성과학
• /
• 제14권4호
• /
• pp.213-220
• /
• 2007

This study investigates the voice quality including F0, jitter, shimmer, and NHR for the children with cochlear implant (CI group) and those with normal hearing (NH group). The CI group was further classified two sub-groups depending upon the time of surgery (i.e. under four years vs. over four years). Three corner vowels (e.g. /a/, /i/, /u/) with extended vocalization were used and analyzed with Multi-Dimensional Voice Program (Kay Elemetrics, Model 4300). The statistics were made in two independent sample t-test with SPSS 11.5. The results can be summarized as follows: (1) The children with cochlear implanted before 4 years of age had very similar data with the NH group except for the vowel /a/. (2) The children with cochlear implanted after 4 years of age, however, indicated significant differences in Fo (/a/, /i/, /u/), Jitter (/e/), shimmer (/a/, /i/, /u/) and NHR(/a/) in all three vowels. It is concluded that the early CI surgery and the early intervention would be very important to maintain better voice quality.

• 대한후두음성언어의학회지
• /
• 제22권2호
• /
• pp.115-118
• /
• 2011

Background and Objectives : The voice change occurs after tonsillectomy and adenoidectomy. This study was designed to examine the postoperative nasalance changes using Nasometer. Materials and Method : From April 2009 to February 2010, data of twenty-eight patients who underwent tonsillectomy, tonsillectomy & adenoidectomy were evaluated. 12 males and 16 females were chosen. Nasalance test was performed before, after 1 week, after 1 month from the surgery. Results : Postoperative mean nasalance results statistically significant increased in 1 weeks after surgery, and returned to the preoperative state in 1 month after surgery. Conclusion : Although the nasalance increased immediately after tonsillectomy and adenoidectomy temporally, it was recovered 1 month after surgery. Therefore, the voice change that come postoperatively could be considered as no concern, and surgeons need to aware of various facts, which can affect voice changes before the surgery.

• 음성과학
• /
• 제9권1호
• /
• pp.17-26
• /
• 2002

Voice onset time (VOT) is defined as the time interval from the oral release of a stop consonant to the onset of glottal pulsing in the following vowel. VOT is a temporal characteristic of stop consonants that reflects the complex timing of glottal articulation relative to supraglottal articulation. There have been many reports on efforts to clarify the acoustical and physiological properties that differentiate the three types of Korean stops, including acoustic, fiberscopic, aerodynamic and electromyographic studies. In the acoustic and fiberscopic studies for stop consonants, the voice onset time and glottal width during the production of stops has been known as the longest and largest in the heavily aspirated type followed by the slightly aspirated type and unaspirated types. The thyroarytenoid and posterior cricoarytenoid muscles were physiologically inter-correlated for differentiating these types of stops. However, a review of the English literature shows that the fine movement of the mucosal edges of the vocal folds during the production of stops has not been well documented. In recent. years, a new method for high-speed recording of laryngeal dynamics by use of a digital recording system allows us to observe with fine time resolution. The movements of the vocal fold edges were documented during the period of stop production using a fiberscopic system of high speed digital images. By observing the glottal width and the visual vibratory movements of the vocal folds before voice onset, the heavily aspirated stop was characterized as being more prominent and dynamic than the slightly aspirated and unaspirated stops.

• 한국의상디자인학회지
• /
• 제16권1호
• /
• pp.153-167
• /
• 2014

The purpose of this study is to compare and analyze about the Telecasters's appearance management, external image & awareness on Self-Efficacy. The method of this study is carried out form 2 January 2013 until 20 January. with the 164 telecasters who announcers, voice actors, gag men, singers. The results of the research is summarized below: First, Among the telecasters, singer is the highest awareness of the beauty services importance about the fashion, makeup, hair, skin care, cosmetic surgery. Especially, about the awareness of the beauty services importance about the fashion, makeup, hair, singers> announcers> voice actors> gagmen appear one after another. Second, about the importance awareness of the beauty services importance & the relation of self-efficacy, for announcers, the more higher awareness the fashion, makeup, hair, the higher self-efficacy of the confidence, effective expression, etc.. For voice actors, the more higher awareness the hair, skin care, the fashion, make up, cosmetic surgery, the higher self-efficacy of the new image making, the confidence, task efficiency improvement, etc... For gagmen, the more higher awareness the fashion, hair, skin care, makeup, cosmetic surgery, the higher self-efficacy of the self-expression, the confidence, the new image making, task efficiency improvement, etc.. For singer, the more higher awareness the makeup, hair, cosmetic surgery, skin care, fashion, the higher self-efficacy of the task efficiency improvement, the self-expression, the confidence, the new image making, etc.. Third, about the importance awareness of the appearance management behavior, external image, about the importance awareness of the appearance management behavior, singer is the most higher awareness, announcers> voice actors> gagmen appear one after another. about the importance awareness of the external image, singer is the most higher awareness, voice actor> announcers> gagmen appear after another. The meanings of this study provide the telecasters's image's fields with the effective basic data.

• 대한후두음성언어의학회지
• /
• 제28권2호
• /
• pp.106-111
• /
• 2017

Background and Objectives : The purpose of this study was to investigate the criterion-related concurrent validity of two standardized auditory-perceptual assessments and the Acoustic Voice Quality Index (AVQI) for measuring dysphonia severity in patients with vocal cord paralysis (VCP). Materials and Methods : Total 210 patients with VCP and 236 normal voice subjects were asked to sustain the vowel [a:] and to read aloud the Korean text "Walk". A 2 second mid-vowel portion of the sustained vowel and two sentences (with 26 syllables) were recorded. And then voice samples were edited, concatenated, and analyzed according to Praat script. Two standardized auditory-perceptual assessment (GRBAS and CAPE-V) were performed by three raters. Results : The VCP group showed higher AVQI, Grade (G) and Overall Severity (OS) values than normal voice group. And the correlation among AVQI, G, and OS ranged from 0.904 to 0.926. In ROC curve analysis, cutoff values of AVQI, G, and OS were <3.79, <0.00, and <30.00, respectively, and the AUC of each analysis was over .89. Conclusion : AVQI and auditory evaluation can improve the early screening ability of VCP voice and help to establish effective diagnosis and treatment plan for VCP-related dysphonia.

• Korean Journal of Otorhinolaryngology-Head and Neck Surgery
• /
• 제60권9호
• /
• pp.454-462
• /
• 2017

Background and Objectives The present study aimed to investigate the effects of penetration/aspiration (P/A) on voice acoustic parameters. Subjects and Method Twenty-seven patients were analyzed with the videofluoroscopic swallowing study (VFSS) and then divided into two groups based on the modified Penetration and Aspiration Scale results. Ten patients (5 males and 5 females) were included in the Non-P/A group, and 17 patients (12 males and 5 females) in the P/A group. Stroke was the major cause of swallowing disorders. Three sustained /a/ vowels recorded in pre- and post-VFSS were analyzed. Mann-Whitney U-test was used to compare acoustic values before and after VFSS, and the receiver operating characteristics (ROC) curve with combination of significant parameters was also conducted. Results Among acoustic parameters, the length of analyzed sample (p=0.010), number of segments computed (p=0.018), total number detected pitch periods (p=0.017), and second formant (p=0.013) in pre- and post-VFSS were significantly different between Non-P/A and P/A groups. In the P/A group after VFSS, the means of these significant parameters decreased. According to ROC combined with four significant parameters, the probability of predicting P/A condition was 84% (p=0.005), the sensitivity was 80%, and the specificity was 80%. Conclusion Voice acoustic analysis can reflect voice changes by penetration/aspiration and the combination of significant parameters can also detect swallowing disorders. Therefore, voice analysis can be a reliable screening tool for patients with swallowing disorders.

• 대한후두음성언어의학회지
• /
• 제33권2호
• /
• pp.59-63
• /
• 2022

The laryngeal framework surgery (LFS) is an operation to correct the position and tension of the vocal cords by changing the laryngeal cartilage and muscles. LFS such as type 1 thyroplasty, arytenoid adduction, and arytenopexy is performed to improve the voice of patients with unilateral vocal cord paralysis. It is known that the voice improvement effect of LFS in patients with unilateral vocal cord paralysis is excellent and lasts for a long time. LFS can also be operated under local anesthesia. Complications are not common, however, severe complications like airway obstruction could occur after the operation. Recently, several other attempts to modify the traditional surgical method have been reported. This review is intended to be helpful in understanding the characteristics and changes in laryngeal framework surgery.

• 대한후두음성언어의학회지
• /
• 제28권2호
• /
• pp.100-105
• /
• 2017

Background and Objectives : Adductor type spasmodic dysphonia (ADSD) is neurogenic disorder and focal laryngeal dystonia, while muscle tension dysphonia (MTD) is caused by functional voice disorder. Both ADSD and MTD may be associated with excessive supraglottic contraction and compensation, resulting in a strained voice quality with spastic voice breaks. The aim of this study was to determine the utility of spectrogram analysis in the differentiation of ADSD from MTD. Materials and Methods : From 2015 through 2017, 17 patients of ADSD and 20 of MTD, underwent acoustic recording and phonatory function studies, were enrolled. Jitter (frequency perturbation), Shimmer (amplitude perturbation) were obtained using MDVP (Multi-dimensional Voice Program) and GRBAS scale was used for perceptual evaluation. The two speech therapist evaluated a wide band (11,250 Hz) spectrogram by blind test using 4 scales (0-3 point) for four spectral findings, abrupt voice breaks, irregular wide spaced vertical striations, well defined formants and high frequency spectral noise. Results : Jitter, Shimmer and GRBAS were not found different between two groups with no significant correlation (p>0.05). Abrupt voice breaks and irregular wide spaced vertical striations of ADSD were significantly higher than those of MTD with strong correlation (p<0.01). High frequency spectral noise of MTD were higher than those of ADSD with strong correlation (p<0.01). Well defined formants were not found different between two groups. Conclusion : The wide band spectrograms provided visual perceptual information can differentiate ADSD from MTD. Spectrogram analysis is a useful diagnostic tool for differentiating ADSD from MTD where perceptual analysis and clinical evaluation alone are insufficient.