• Journal of Biomedical Engineering Research
• /
• v.34 no.1
• /
• pp.8-13
• /
• 2013

Persons with sensorineural hearing impairment have troubles in hearing at noisy environments because of their deteriorated hearing levels and low-spectral resolution of the auditory system and therefore, they use hearing aids to compensate weakened hearing abilities. Various algorithms for hearing loss compensation and environmental noise reduction have been implemented in the hearing aid; however, the performance of these algorithms vary in accordance with external sound situations and therefore, it is important to tune the operation of the hearing aid appropriately in accordance with a wide variety of sound situations. In this study, a sound classification algorithm that can be applied to the hearing aid was suggested. The proposed algorithm can classify the different types of speech situations into four categories: 1) speech-only, 2) noise-only, 3) speech-in-noise, and 4) music-only. The proposed classification algorithm consists of two sub-parts: a feature extractor and a speech situation classifier. The former extracts seven characteristic features - short time energy and zero crossing rate in the time domain; spectral centroid, spectral flux and spectral roll-off in the frequency domain; mel frequency cepstral coefficients and power values of mel bands - from the recent input signals of two microphones, and the latter classifies the current speech situation. The experimental results showed that the proposed algorithm could classify the kinds of speech situations with an accuracy of over 94.4%. Based on these results, we believe that the proposed algorithm can be applied to the hearing aid to improve speech intelligibility in noisy environments.

• Journal of Clinical Otolaryngology Head and Neck Surgery
• /
• v.29 no.2
• /
• pp.212-222
• /
• 2018

Background and Objectives : The purpose of this study was to compare the measured values of acoustic and auditory perceptual assessments between normal and functional dysphonia (FD) groups. Materials and Methods : 102 subjects with FD and 59 normal voice groups were participated in this study. Mid-vowel portion of the sustained vowel /a/ and two sentences of 'Sanchaek' were edited, concatenated, and analyzed by Praat script. And then auditory-perceptual (AP) rating was completed by three listeners. Results : The FD group showed higher acoustic voice quality index version 2.02 and version 3.01 (AVQIv2 and AVQIv3), slope, Hammarberg index (HAM), grade (G) and overall severity (OS), values than normal group. Additionally, smoothed cepstral peak prominence in Praat (PraatCPPS), tilt, low-to high spectral band energies (L/H ratio), long-term average spectrum (LTAS) in FD group were lower than normal voice group. And the correlation among measured values ranged from -0.250 to 0.960. In ROC curve analysis, cutoff values of AVQIv2, AVQIv3, PraatCPPS, slope, tilt, L/H ratio, HAM, and LTAS were 3.270, 2.013, 13.838, -22.286, -9.754, 369.043, 27.912, and 34.523, respectively, and the AUC of each analysis was over .890 in AVQIv2, AVQIv3, and PraatCPPS, over 0.731 in HAM, tilt, and slope, over 0.605 in LTAS and L/H ratio. Conclusions : In conclusion, AVQI and CPPS showed the highest predictive power for distinguishing between normal and FD groups. Acoustic analyses and AP rating as noninvasive examination can reinforce the screening capability of FD and help to establish efficient diagnosis and treatment process plan for FD.

• The Korean Journal of Applied Statistics
• /
• v.32 no.2
• /
• pp.213-227
• /
• 2019

In this paper, we propose an end-to-end deep learning model combining Bayesian neural network with Korean speech recognition. In the past, Korean speech recognition was a complicated task due to the excessive parameters of many intermediate steps and needs for Korean expertise knowledge. Fortunately, Korean speech recognition becomes manageable with the aid of recent breakthroughs in "End-to-end" model. The end-to-end model decodes mel-frequency cepstral coefficients directly as text without any intermediate processes. Especially, Connectionist Temporal Classification loss and Attention based model are a kind of the end-to-end. In addition, we combine Bayesian neural network to implement the end-to-end model and obtain Monte Carlo estimates. Finally, we carry out our experiments on the "WorimalSam" online dictionary dataset. We obtain 4.58% Word Error Rate showing improved results compared to Google and Naver API.