• 대한청각학회지
• /
• 제24권2호
• /
• pp.91-98
• /
• 2020

Background and Objectives: This study aimed to compare functional hearing with the use of a personal sound amplification product (PSAP) or a basic hearing aid (HA) among sensorineural hearing impaired listeners. Subjects and Methods: Nineteen participants with mild-to-moderate sensorineural hearing loss (SNHL) (26-55 dB HL; pure-tone average, 0.5-4 kHz) were prospectively included. No participants had prior experience with HAs or PSAPs. Audiograms, speech intelligibility in both quiet and noisy environments, speech quality, and preference were assessed in three different listening conditions: unaided, with the HA, and with the PSAP. Results: The use of PSAP was associated with significant improvement in pure-tone thresholds at 1, 2, and 4 kHz compared to the unaided condition (all p<0.01). In the quiet environment, speech intelligibility was significantly improved after wearing a PSAP compared to the unaided condition (p<0.001), and this improvement was better than the result obtained with the HA. The PSAP also demonstrated similar improvement in the most comfortable levels compared to those obtained with the HA (p<0.05). However, there was no significant improvement of speech intelligibility in a noisy environment when wearing the PSAP (p=0.160). There was no significant difference in the reported speech quality produced by either device or in participant preference for the PSAP or HA. Conclusions: The current result suggests that PSAPs provide considerable benefits to speech intelligibility in a quiet environment and can be a good alternative to compensate for mild-to-moderate SNHL.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제14권1_2호
• /
• pp.22-39
• /
• 1992

The purpose of this study was to evaluate hypernasality, nasal air emission, glottal stop, articulation disorder in patients with velopharyngeal incompetency(V.P.I.) and to analyze speech improvement after pharyngoplasty. In this study 61 patients with velopharyngeal incompetency were tested, and in patents with pharyngoplasty speech problems before pharyngoplasty were compared with those after pharyngoplasty. The results obtained are as follows : 1. There are few speech problems in pronouncing the vowel sounds. 2. There are many speech problems in pronouncing the pressure sounds and few speech problems in non-pressure sounds. 3. Speech problems in patients with cleft palate are influenced not by anatomical defect but by severity of velopharyngeal incompetence after palatorrhaphy. 4. Operation methods which decrease the velopharygeal incompetence must be considered for reducing the speech problems. 5. Among the 61 cases with V.P.I. 19 cases(31%) showed nasal air emission and 24 cases(39%) showed glottal stop. 6. Pharyngoplasty is of benefit to primary precipitating components such as hypernasality, nasal air emission but of no benefit to secondary compensating component such as glottal stop. 7. There as no significant difference in speech improvement between pre-and post-pharyngoplasty(p<0.05).

• 대한음성학회지:말소리
• /
• 제47호
• /
• pp.121-129
• /
• 2003

This paper describes the use of pitch information for speaker identification. The recognition system is a GMM based one with 4 connected Korean digits speech database. The mean of the pitch period in voiced sections of speech are shown to be ,useful at discriminating between speakers. Utilizing this feature with Gaussian mixture model in the speaker identification system gave a marked improvement, maximum 6% improvement comparing to the baseline Gaussian mixture model.

• 음성과학
• /
• 제12권4호
• /
• pp.247-254
• /
• 2005

This study aimed at clarifing clinical effects of eight-step continuum treatment in a patient who showed apraxia of speech after stroke. The eight-step continuum treatment consisted of 8 steps and its clinical efficacy has been proven with American apraxic patients. However, it has not been clinically proven to be effective in Korean patients with apraxia of speech as of yet. Therefore, this study was conducted in an effort to provide preliminary clinical evidence regarding its effectiveness regardless of the linguistic differences between Korean and English. The therapy took place twice a week for 6 months, a total of 48 times. The results showed that the patient's receptive language was improved from 83% to 89% and 37% in accuracy, and expressive language from 15% to 37%. It seemed that spontaneous recovery did not playa role in his improvement since the study was conducted 2 years after the stroke. In addition, the improvement of expressive language was much greater(22%) than that of receptive language(6%), which implied that the therapy was effective in apraxia of speech because apraxia of speech is relatively confined to expressive ability, more specifically motor programming and sequencing.

• 디지털융복합연구
• /
• 제16권11호
• /
• pp.335-340
• /
• 2018

정확한 인식률을 보이고 있는 상업적인 음성인식 시스템은 화자종속 고립데이터로부터 학습 모델을 사용한다. 그러나 잡음 환경에서 데이터양에 따라 음성인식의 성능이 저하되는 문제점이 있다. 본 논문에서는 가우시안 분포에서 Maximum Log Likelihood를 이용한 벡터 양자화 기반 음성 인식 성능 향상을 제안한다. 제안하는 방법은 음성에 대한 특징을 가지고 벡터 양자화와 Maximum Log Likelihood 음성 특징 추출 방법을 이용하여 유사 음성에 대한 음성 인식의 정확성을 높이는 최적 학습 모델 구성 방법이다. 이를 위해 HMM을 기반으로 음성 특징을 추출하는 방법을 사용한다. 제안하는 방법을 사용하여 기존 시스템에서 생성되어 사용되는 음성 모델에 대한 부정확한 음성 모델에 대한 정확성을 향상시킬 수 있으므로 음성 인식에 강인한 모델을 구성할 수 있다. 제안하는 방법은 음성 인식 시스템에서 향상된 인식의 정확도를 보인다.

• 대한임베디드공학회논문지
• /
• 제3권1호
• /
• pp.1-7
• /
• 2008

In this paper, a MSS-NOVO method that combines the HMM composition method with a noise reduction method is proposed for speech recognition in noisy environments. This combined method starts with noise reduction with modified spectral subtraction (MSS) to enhance the input noisy speech, then the noise and voice composition (NOVO) method is applied for making noise adapted models by using the noise in the non-utterance regions of the enhanced noisy speech. In order to evaluate the effectiveness of our proposed method, we compare MSS-NOVO method with other methods, i.e., SS-NOVO, MWF-NOVO. To set up the noisy speech for test, we add White noise to KLE 452 database with different SNRs range from 0dB to 15dB, at 5dB intervals. From the tests, MSS-NOVO method shows average improvement of 66.5% and 13.6% compared with the existing SS-NOVO method and MWF-NOVO method, respectively. Especially our proposed MSS-NOVO method shows a big improvement at low SNRs.

• 음성과학
• /
• 제11권4호
• /
• pp.89-97
• /
• 2004

In this paper, an improved network echo canceller is proposed. The proposed echo canceller is based on the LTJ(lattice transversal joint) adaptive filter which uses informations from the speech decoder. In the proposed implementation method of the network echo canceller, the filer coefficients of the transversal filter part in the LTJ adaptive filter is updated every other sample instead of every sample. So its complexity can be lower than that of the transversal filter. And the echo cancellation rate can be improved by residual echo cancellation using the lattice predictor whose order is less than 10. Computational complexity of the proposed echo canceller is lower than that of the transversal filter but the convergence speed is faster than that of the transversal filter. The performance improvement of the proposed echo canceller was verified by the experiments using the real speech signal and speech coder.

• Archives of Plastic Surgery
• /
• 제33권3호
• /
• pp.308-312
• /
• 2006

Time to time, we face patients who missed the proper time for primary palatal repair. Although we do not have enough available documents, it is important to establish efficacy of palatal repair in patients more than 4 years old. From May 1995 to March 2005, we selected 14 patients who underwent palatal repair in more than 4 years old patients and they are able to tolerate speech articulation tests. Out of 14 patients 5 males an 9 females in sex, aged form 4 to 50 years old. 6 patients with incomplete cleft palate and 8 patients with submucous cleft palate. Double reversing Z-plasty(n=5), pushback palatoplasty(n=4), two flap palatoplasty(n=2), von Langenbeck palatoplasty(n=2), and intravelar veloplasty(n=1) were performed. Preoperative and postoperative speech articulation test, "Simple method of speech evaluation in Korean patients with cleft palate", were conducted. Satisfaction rate was sorted into 5 levels. There is no significant statistical correlation in the speech improvement, satisfaction rate, patients sex, cleft type and operative method. But there is significant statistical correlation between the speech improvement and patienet's age. There were better result in younger patient group than aged patients group.

• 한국통신학회논문지
• /
• 제41권10호
• /
• pp.1183-1185
• /
• 2016

디지털 음성통신에서의 저 비트율 음성부호화기는 음성발성모델의 파라미터를 사용하여 음성을 합성한다. 이 경우, 파라미터에 할당된 비트가 매우 한정적이기 때문에 합성된 음성의 스펙트럼이 크게 왜곡될 수 있으며, 이는 명료도 저하의 요인이 된다. 본 논문에서는 통계적 스펙트럼 이퀄라이저를 이용한 명료도 향상 기법을 제안한다. 본 기법은 각각의 음성부호화기별로 원음과 합성음의 스펙트럼 비율을 이용하여 통계적으로 가중치 벡터를 구하며, 이를 합성 음성에 적용한다. 객관적인 음성명료도 평가 실험을 통해, 제안한 기법이 기존의 방법보다 성능이 우수함을 확인하였다.

• Archives of Plastic Surgery
• /
• 제33권2호
• /
• pp.144-148
• /
• 2006

The velopharyngeal dysfunction usually occurs in patients with previous operation of the cleft palate or with submucosal cleft palate. In case of velopharyngeal dysfunction without cleft palate, no study has been made when it comes to operative method and postoperative results. Here, we would like to present the operative methods and the postoperative results with the cases we've experienced. This study is based on seven cases of velopharyngeal dysfunction without cleft palate from 1999 to 2004. Analysis of age, sex, etiology, operative methods, satisfaction rate and speech evaluation was done. The patients were 3 males and 4 females, with an age ranged from 10 to 28 at the time of surgery. The follow-up period was more than six months. One case had bifid uvula, another had atypical anomaly in palate, and five cases had no anatomical abnormality. The palatal lengthening was done on one patient, the levator muscle repositioning on another patient and to the rest of them, the superiorly based posterior pharyngeal flap was done. It was difficult to determine the etiology of the velopharyngeal dysfunction without cleft palate. The speech improvement and the satisfaction rate of the patients and parents were diverse. Although the authors had a problem with statistical analysis between the operative age and the speech improvement, it was reasonable to perform a surgical operation because postoperative speech improvement was observed in most cases regardless of age. There is little statistical correlation, but significantly higher outcomes were observed in palatal lengthening and levator muscle repositioning than in pharyngeal flap.