식도발성 남성 발화의 말 속도

박원경,심희정,고도흥 한국음성학회 2012 말소리와 음성과학 Vol.4 No.3

The purpose of this study is to investigate the speech rate of an esophageal speech group that is capable of vocalization after surgery. The subjects in this experiment were 10 male esophageal speakers and 10 male laryngeal speakers. Each group read a reading passage that was recorded by a DAT recorder (Rolando, EDIROL R-09). These records were analyzed by using CSL (Computerized Speech Lab, model 4150). The results were as follows: (1) the overall speech rate of esophageal speech was 2.50 SPS (syllable per second) while the overall speech rate of laryngeal speech was 4.23 SPS. (2) The articulatory rate of esophageal speech was 3.14 SPS (syllable per second) while the articulatory rate of laryngeal speech was 4.75 SPS. Speech rates as well as articulatory rates of esophageal speech were significantly lower than laryngeal speech. These differences between the two groups may be due to reduced efficiency of airflows across the pharyngeal-esophageal segment for esophageal speakers when compared to airflow through the glottis for laryngeal speakers. These results would provide a guideline in speech rates for esophageal speakers in clinical settings.

Speech-aid prosthesis in velopharyngeal incompetency patient with cleft palate: can speech aids be applicable for adult patient?

강동철,박정호,석현,백진아,김다와,고승오 대한악안면성형재건외과학회 2021 Maxillofacial Plastic Reconstructive Surgery Vol.43 No.-

BackgroundVelopharyngeal incompetence (VPI) therapy for cleft palate (speech therapy alone, speech therapy using speech aids, or combined therapy such as speech therapy using a pharyngeal flap), is more effective in younger patients than in adult patients. Speech therapy is known as very difficult for patients who still have VPI as an adult. Because of the possibility of subsequent speech disorders, the timing of surgery for cleft palate is accelerating. Herein, we present a case of an adult with articulation disorder due to VPI who was treated by speech therapy and a speech-aid prosthesis. Case presentationA woman who underwent cleft palate surgery at 8 years of age still had difficulty with articulation due to VPI as a 24-year-old adult because of a lack of continuous speech therapy. We decided to use a speech-aid application using palatal lift, and a reduction program was conducted four times, along with simultaneous speech therapy, over a period of 1 year and 7 months. During the therapy period, she was able to speak normally within a relatively short period of time, and after implementation of the reduction program, the therapy was completed by completely removing the device. Long-term observations have shown normal speech function without recurrence, even after the device was removed. ConclusionAs seen in this case, speech therapy using speech aids can show a good result for adult patients with cleft palate who missed the usual timing for the treatment of articulation disorders, depending on the situation. Therefore, it is hereby reported as a therapy option worthy of consideration.

주파수, 성별 및 어음 종류에 따른 한국어의 어음역동범위

이경주,허소희,진인기 한국청각언어재활학회 2017 Audiology and Speech Research Vol.13 No.4

Purpose: Dynamic range (DR) of speech refers to the minimum and maximum levels of speech across frequencies and it depends on language. Recent findings showed that Korean speech DR is different from the DRs of other languages such as English and Mandarin. The purpose of this study was to identify the characteristics of Korean speech DR according to frequency (21 bands), gender (male and female), and speech type [words, sentences, and continuous discourses (CDs)]. Methods: DRs for 70 participants were recorded and yielded using cumulative histogram levels. Then, the DRs were compared according to frequency bands, gender, and speech type after level normalization at 65 dB sound pressure level. Results: Although there were no statistical differences between DRs for sentences and CDs, DRs for words were wider than DRs for other speech types. In terms of gender, DRs for female speakers were wider than DRs for male speakers in all speech types except a few frequency bands. Conclusion: Speech DR is important in real ear measurements like speech mapping because audibility can be determined based on the relationship between a person’s hearing thresholds and the DR of speech. Thus, the results of this study contribute to more accurate hearing aid fitting according to frequency bands, gender, and speech type for Korean listeners.

언어장애인용 언어치료 솔루션 개발을 위한 사용성 평가 연구

김기욱(Gi-Wook Kim),강승록(Seung-Rok Kang),한갑수(Kap Soo Han),조윤주(Yun-ju Jo),김라연(Ra-Youn Kim),정영재(Young-Jae Jung),김준혁(Jun-Hyuk Kim),유희천(Heecheon You),고명환(Myoung-Hwan Ko) 대한구순구개열학회 2021 대한구순구개열학회지 Vol.24 No.2

Objective: We performed a usability test for the speech therapy solutions Smart SpeechTM and Smart NasometerTM to apply usability testing results for the development of an optimal speech therapy solution. Materials and Methods: A total of 19 health professionals (12 doctors and 7 speech therapists) practicing speech therapy were recruited. They performed a usability evaluation by simulating speech therapy tasks for the speech-impaired after being familiarized with Smart Speech and Smart Nasometer for 30 minutes. The participants performed the tasks using oral training contents, breathing training contents, and vocal training contents of Smart Speech. Then, they conducted tasks of wearing Smart Nasometer and checking nasalance data measured by Smart Nasometer. Lastly, they completed a satisfaction survey of Smart Speech and Smart Nasometer. Results: The usability evaluation showed that more than 60% of the participants were satisfied with Smart Speech and more than 50% with Smart Nasometer. The participantssuggested improvements of Smart Speech in the game description, content color, guide video, audio, data analysis and management, and difficulty-level control function. Conclusion: The results of this study showed the importance of usability evaluation with users when developing healthcare devices.

심리음향 특성을 이용한 음성 향상 알고리즘

전유용(Yuyong Jeon),이상민(Sangmin Lee) 대한전기학회 2010 전기학회논문지 Vol.59 No.6

In the speech system, for example hearing aid as well as speech communication, speech quality is degraded by environmental noise. In this study, to enhance the speech quality which is degraded by environmental speech, we proposed an algorithm to reduce the noise and reinforce the speech. The minima controlled recursive averaging (MCRA) algorithm is used to estimate the noise spectrum and spectral weighting factor is used to reduce the noise. And partial masking effect which is one of the human hearing properties is introduced to reinforce the speech. Then we compared the waveform, spectrogram, Perceptual Evaluation of Speech Quality (PESQ) and segmental Signal to Noise Ratio (segSNR) between original speech, noisy speech, noise reduced speech and enhanced speech by proposed method. As a result, enhanced speech by proposed method is reinforced in high frequency which is degraded by noise, and PESQ, segSNR is enhanced. It means that the speech quality is enhanced.

A Speech Homomorphic Encryption Scheme with Less Data Expansion in Cloud Computing

( Canghong Shi ),( Hongxia Wang ),( Yi Hu ),( Qing Qian ),( Hong Zhao ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.5

Speech homomorphic encryption has become one of the key components in secure speech storing in the public cloud computing. The major problem of speech homomorphic encryption is the huge data expansion of speech cipher-text. To address the issue, this paper presents a speech homomorphic encryption scheme with less data expansion, which is a probabilistic statistics and addition homomorphic cryptosystem. In the proposed scheme, the original digital speech with some random numbers selected is firstly grouped to form a series of speech matrix. Then, a proposed matrix encryption method is employed to encrypt that speech matrix. After that, mutual information in sample speech cipher-texts is reduced to limit the data expansion. Performance analysis and experimental results show that the proposed scheme is addition homomorphic, and it not only resists statistical analysis attacks but also eliminates some signal characteristics of original speech. In addition, comparing with Paillier homomorphic cryptosystem, the proposed scheme has less data expansion and lower computational complexity. Furthermore, the time consumption of the proposed scheme is almost the same on the smartphone and the PC. Thus, the proposed scheme is extremely suitable for secure speech storing in public cloud computing.

발표 능력 향상을 위한 자기 평가 활용의 의의

오현진 한국 리터러시 학회 2019 리터러시 연구 Vol.10 No.4

This study presents ‘self-evaluation’ as a way to improve the speech skills of university students, organizes how students feel about it when it is utilized, and attempts to observe how ‘self-evaluation’ contributes to the speech skill improvement of students. Speech education that is needed by university students who have learned speech knowledge several times provides an opportunity for students to experience entire speech situations within actual and detailed situations and accurately recognize their own speech skills while having the identity and distinction of university education. ‘Self-evaluation’, which allows students to not only observe speech in themselves but also allows them to reflectively observe the entire process of presenting while looking into their own strengths and weaknesses, is significant because it places focus on the speech skills of individual students and allows them to improve their negative perceptions on past speech. Through self-evaluation made through actual videos, students were able to recognize various aspects of their own speech skills that they were not aware of before and they gained interest in interactions with the listening audience and reports were given that self-evaluation methods had a positive effect on the improvement of speech skills and that they can be used as learning tools. This shows the utilization possibilities and educational significance of ‘self-evaluation’ in the speech education of university students and it implicated the need for the development of detailed self-evaluation methods or models. 이 연구는 대학생을 대상으로 발표 능력을 향상시키기 위한 방법으로 ‘자기 평가’를 제안하고 그것을 활용했을 때 학생들의 소감을 정리하여 ‘자기 평가’가 학생들에게 미친 영향을 살펴보고자 하였다. 발표에 관한 지식을 여러 차례 학습한 바 있는 대학생에게 필요한 발표 교육은 실제적이고 구체적인 상황 속에서 발표의 전 상황을 경험해 보고 자신의 발표 능력에 대한 정확한 인식할 수 있는 기회를 제공하는 것이어야 하고, 이것은 대학 교육만의 정체성과 차별성을 확보할 것이다. 발표만이 아니라 발표의 전 과정에 대해 스스로 반성적으로 살펴보고 자신의 장, 단점을 파악해 보는 과정인 ‘자기 평가’는 학생 개개인의 발표 능력을 중심에 두고 이전 발표에 대한 부정적 인식을 개선할 수 있게 한다는 점에서 의의가 있다. 실제 동영상을 통한 자기 평가를 통해 학생들은 이전에 알지 못했던 자신의 발표 능력의 다양한 측면을 인지할 수 있었고, 청중과의 상호작용에 관심을 갖게 되었으며, 자기 평가 방법이 발표 능력 향상에 긍정적인 영향을 미치며 학습 도구로 활용가능하다는 것을 알게 되었다고 보고하였다. 이는 대학생을 위한 발표 교육에 ‘자기 평가’의 활용 가능성과 교육적 의의를 보여주는 것이며, 향후 구체적인 자기 평가 방법이나 모형 개발의 필요성을 시사한다.

잡음음성 음향모델을 이용한 VTS 기반의 음성특징 보상

정용주(Yong-Joo Chung),정민우(Min-Woo Chung) 한국정보기술학회 2013 한국정보기술학회논문지 Vol.11 No.3

In the conventional VTS-based noisy speech recognition methods, they used methods where an acoustic model is trained using clean speech and then the parameters of the acoustic models are adapted to the new noisy speech or the original speech is estimated using VTS. However, these approaches have a drawback that acoustic models trained using noisy speech can not be used. We think that improved noisy speech recognition performance is possible by employing the noisy speech acoustic models trained by methods like the MTR and MMSR instead of the acoustic models trained with clean speech. In this paper, motivated by this idea, we derived the mathematical relation in log-spectrum domain between test noisy speech and train noisy speech considering channel noise and after approximating the relation using VTS, the mismatch between test and train noisy speech is reduced through the MMSE of the train noisy speech. We applied the proposed method to the noisy speech acoustic models trained by the MMSR and MTR method and could reduce the word error rate by 10.3% and 10.8%, respectively, compared with the MTR and MMSR method in noisy speech recognition experiments on Aurora 2 database.

Speech and emotion recognition using a multi-output model

Min Dong Jin,Jongho Won,Deok-Hwan Kim 한국차세대컴퓨팅학회 2022 한국차세대컴퓨팅학회 학술대회 Vol.2022 No.10

Voice language, the primary way of human communication, delivers not only verbal information but also emotional information through various characteristics such as voice intonation, height, and surrounding environment. Currently, many studies focus on grasping emotion and speech recognition on voice for human-computer interaction and are developing deep neural network models by extracting various frequency characteristics of speech. Representatives of these speech-based deep learning algorithms include speech recognition, namely speech-to-text or automatic speech recognition, and speech emotion recognition. The development of these two algorithms has been developed for a long time, but multi-output algorithms that process them in parallel at the same time are rare. This paper introduces a multi-output model that recognizes speech and emotion in one voice, thinking that simultaneously understanding language and emotion, which are the most critical information in a human voice, will significantly help human-computer interaction. This model confirmed that there was no significant difference between the training of the language and emotion recognition models separately, with a word error rate of 6.59% in the speech recognition section and an accuracy of 79.67% on average in the emotion recognition section.

Treatment of velopharyngeal insufficiency in a patient with a submucous cleft palate using a speech aid: the more treatment options, the better the treatment results

Park, Yun-Ha,Jo, Hyun-Jun,Hong, In-Seok,Leem, Dae-Ho,Baek, Jin-A,Ko, Seung-O Korean Association of Maxillofacial Plastic and Re 2019 Maxillofacial Plastic Reconstructive Surgery Vol.41 No.-

Background: The submucous cleft palate (SMCP) is a type of cleft palate that may result in velopharyngeal insufficiency (VPI). Palate muscles completely separate oral and nasal cavities by closing off the velopharynx during functional processes such as speech or swallow. Also, hypernasality may arise from anatomical or neurological abnormalities in these functions. Treatments of this issue involve a combination of surgical intervention, speech aid, and speech therapy. This case report demonstrates successfully treated VPI resulted from SMCP without any surgical intervention but solely with speech aid appliance and speech therapy. Case presentation: A 13-year-old female patient with a speech disorder from velopharyngeal insufficiency that was caused by a submucous cleft palate visited to our OMFS clinic. In the intraoral examination, the patient had a short soft palate and bifid uvula. And the muscles in the palate did not contract properly during oral speech. She had no surgical history such as primary palatoplasty or pharyngoplasty except for tonsillectomy. And there were no other medical histories. Objective speech assessment using nasometer was performed. We diagnosed that the patient had a SMCP. The patient has shown a decrease in speech intelligibility, which resulted from hypernasality. We decided to treat the patient with speech aid (palatal lift) along with speech therapy. During the 7-month treatment, hypernasality measured by a nasometer decreased and speech intelligibility became normal. Conclusions: Surgery remains the first treatment option for patients with velopharyngeal insufficiencies from submucous cleft palates. However, there were few reports about objective speech evaluation pre- or post-operation. Moreover, there has been no report of non-surgical treatment in the recent studies. From this perspective, this report of objective improvement of speech intelligibility of VPI patient with SMCP by non-surgical treatment has a significant meaning. Speech aid can be considered as one of treatment options for management of SMCP.