• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.750-762
• /
• 2019

The importance of the call center as a contact point for the enterprise is growing. However, call centers have difficulty with their operating agents due to the agents' lack of knowledge and owing to frequent agent turnover due to downturns in the business, which causes deterioration in the quality of customer service. Therefore, through an N-bank call center case study, we developed a system to reduce the burden of keeping up business knowledge and to improve customer service quality. It is a "real-time agent advisor" system that provides agents with answers to customer questions in real time by combining AI technology for speech recognition, natural language processing, and questions & answers for existing call center information systems, such as a private branch exchange (PBX) and computer telephony integration (CTI). As a result of the case study, we confirmed that the speech recognition system for real-time call analysis and the corpus construction method improves the natural speech processing performance of the query response system. Especially with name entity recognition (NER), the accuracy of the corpus learning improved by 31%. Also, after applying the agent advisor system, the positive feedback rate of agents about the answers from the agent advisor was 93.1%, which proved the system is helpful to the agents.

• Archives of Craniofacial Surgery
• /
• v.21 no.5
• /
• pp.283-287
• /
• 2020

Background: Closed reduction is the standard treatment for nasal bone fractures, which are the most common type of facial bone fractures. We investigated the effect of closed reduction on quality of life. Methods: The 15-dimensional health-related quality of life survey was administered to 120 patients who underwent closed reduction under general anesthesia for nasal bone fractures from February 2018 to December 2019, on both the day after surgery and 3 months after surgery. Three months postoperatively, the presence or absence of five nasal symptoms (nose obstruction, snoring, pain, nasal secretions, and aesthetic dissatisfaction) was also evaluated. Results: The quality of life items that showed significant changes between immediately after surgery and 3 months postoperatively were breathing, sleeping, speech, excretion, and discomfort. Low scores were found at 3 months for breathing, sleeping, and distress. There were 31 patients (25.83%) with nose obstruction, 25 (20.83%) with snoring, 12 (10.00%), with pain, 11 (9.17%) with nasal secretions, and 29 (24.17%) with aesthetic dissatisfaction. Conclusion: Closed reduction affected patients' quality of life, although most aspects improved significantly after 3 months. However, it was not possible to rule out deterioration of quality of life due to complications and dissatisfaction after surgery.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.962-977
• /
• 2019

The human voice is a convenient method of information transfer between different objects such as between men, men and machine, between machines. The development of information and communication technology, the voice has been able to transfer farther than before. The way to communicate, it is to convert the voice to another form, transmit it, and then reconvert it back to sound. In such a communication process, a vocoder is a method of converting and re-converting a voice and sound. The CELP (Code-Excited Linear Prediction) type vocoder, one of the voice codecs, is adapted as a standard codec since it provides high quality sound even though its transmission speed is relatively low. The EVRC (Enhanced Variable Rate CODEC) and QCELP (Qualcomm Code-Excited Linear Prediction), variable bit rate vocoders, are used for mobile phones in 3G environment. For the real-time implementation of a vocoder, the reduction of sound quality is a typical problem. To improve the sound quality, that is important to know the size and shape of noise. In the existing sound quality improvement method, the voice activated is detected or used, or statistical methods are used by the large mount of data. However, there is a disadvantage in that no noise can be detected, when there is a continuous signal or when a change in noise is large.This paper focused on finding a better way to decrease the reduction of sound quality in lower bit transmission environments. Based on simulation results, this study proposed a preprocessor application that estimates the SNR (Signal to Noise Ratio) using the spectral SNR estimation method. The SNR estimation method adopted the IMBE (Improved Multi-Band Excitation) instead of using the SNR, which is a continuous speech signal. Finally, this application improves the quality of the vocoder by enhancing sound quality adaptively.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.31 no.2
• /
• pp.71-77
• /
• 2020

Background and Objectives OperaVOXTM (Oxford Wave Research Ltd.) is a portable voice analysis software package designed for use with iOS devices. As a relatively cheap, portable and easily accessible form of acoustic analysis, OperaVOXTM may be more clinically useful than laboratory-based software in many situations. The aim of this study was to evaluate the agreement between OperaVOXTM and Multi-Dimensional Voice Program (MDVP; Computerized Speech Lab) to assess voice quality before and after laryngeal microsurgery in patient with vocal polyp. Materials and Method Twenty patients who had undergone laryngeal microsurgery for vocal polyp were enrolled in this study. Preoperative and postoperative voices were assessed by acoustic analysis using MDVP and OperaVOXTM. A five-seconds recording of vowel /a/ was used to measure fundamental frequency (F0), jitter, shimmer and noise-to-harmonic ratio (NHR). Results Several acoustic parameters of MDVP and OperaVOXTM related to short-term variability showed significant improvement. While pre-operative value of F0, jitter, shimmer, NHR was 155.75 Hz (male: 125.37 Hz, female: 183.37 Hz), 2.20%, 6.28%, 0.16, post-operative values of these parameter was 164.34 Hz (male: 129.42 Hz, female: 199.26 Hz), 2.15%, 5.18%, 0.14 Hz in MDVP. While pre-operative value of F0, jitter, shimmer, NHR was 168.26 Hz (male: 135.16 Hz, female: 201.37 Hz), 2.27%, 6.95%, 0.26, post-operative values of these parameters was 162.72 Hz (male: 128.267 Hz, female: 197.18 Hz), 1.71%, 5.36%, 0.20 in OperaVOXTM. There was high intersoftware agreement for F0, jitter, shimmer with intraclass correlation coefficient. Conclusion Our results showed that the short-term variability of acoustic parameters in both MDVP and OperaVOXTM were useful for the objective assessment of voice quality in patients who received laryngeal microsurgery. OperaVOXTM is comparable to MDVP and has high intersoftware reliability with MDVP in measuring the F0, jitter, and shimmer

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.617-626
• /
• 2023

This study aims to investigate the preferred sound level of water sound for various levels of open-plan-office noise regarding soundscape quality and speech privacy. And assessment of the work efficiency of the water sound. For the laboratory experiment, office noise was recorded using a binaural microphone in a real open-plan office. For the assessment of the soundscape quality and speech privacy, Overall Soundscape Quality (OSQ) and Listening Difficulty (LD) were evaluated under three different sound levels (55 dBA, 60 dBA, and 65 dBA) and five different signal-to-noise ratios (SNR -10 dB, -5 dB, 0 dB, +5 dB, and +10 dB). After the evaluation, the preferred SNR was proposed according to OSQ and LD. For the assessment of to work efficiency of water sound, this study evaluated the cognitive performance of both of the condition noise only and combine the water sound with office noise. The results showed that LD increased as the water sound level increased, but OSQ decreased. When the water sound level was more than the office noise level, the OSQ decreased from noise only. Therefore, considering OSQ and LD, the preferred SNR of water sound was -5 dB for all noise levels. At the preferred level of water sound, the cognitive performance results were shown to decrease at 55 dBA compared to noise only, but at 60 dBA and 65 dBA combine the water sound results were increased than the noise only.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.1
• /
• pp.75-80
• /
• 2014

The quality of real-time Voice over Internet Protocol (VoIP) network is affected by network impariments such as delays, jitters, and packet loss. This paper proposes a packet loss concealment algorithm based on voice classification for enhancing VoIP speech quality. In the proposed method, arriving packets are classified by an adaptive thresholding approach based on the analysis of multiple features of short signal segments. The excellent classification results are used in the packet loss concealment. Additionally, linear prediction-based packet loss concealment delivers high voice quality by alleviating the metallic artifacts due to concealing consecutive packet loss or recovering lost packet.

• Journal of Korean Institute of Industrial Engineers
• /
• v.31 no.4
• /
• pp.349-357
• /
• 2005

The Adaptive Multi-Rate (AMR) speech codec is the mandatory for voice service in WCDMA systems. The AMR codec can be used efficiently to provide a balanced trade-off between the capacity and quality of voice by adjusting various service rates. In this paper, three ways of AMR mode allocation schemes on the downlink in WCDMA system are evaluated. To evaluate users satisfaction efficiently, new system performance measure and analytic models are proposed. The proposed analytic models can be applied to obtain optimal mode allocation ways while considering the system capacity and quality of voice. In numerical examples, the ways of finding optimal parameters are illustrated for the given traffic loads and the performances of three mode allocation schemes are compared.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.1
• /
• pp.86-91
• /
• 2012

To provide high voice quality of real-time voice communication based on telematics exposed to various noise environments, the noise reduction algorithm with low computing load is required to effectively remove the noise. In this paper, we propose a noise reduction algorithm based on Mel-Filter and illustrate the proposed algorithm comparing with conventional noise reduction algorithms. As a experimental result that evaluates the performance of the noise reduction algorithms under the car and babble noise environments, the proposed noise reduction algorithm has the lower computing load with the similar PESQ score compared to the conventional noise reduction algorithms. It proves that the proposed noise reduction algorithm can efficiently remove the noise in mobile telematics.

• Journal of the Society of Naval Architects of Korea
• /
• v.47 no.4
• /
• pp.589-597
• /
• 2010

The indoor noise of the naval vessel is very important considering hearing protection, improvement of working environment and easily communication between crews. When the environment of the naval vessel suffering from the noise is considered, it is very important to be quiet in the living area where the crews have a rest sufficiently. In addition, the noise of the working area should be reduced in order to increase working efficiency. Therefore, in this research, the satisfactions about the indoor noise are survey for crews working in a naval vessel. Through this survey, the relationship between the indoor noise and crew's satisfaction about it can be found. As a result, the limit of sound pressure level which almost all crew can be satisfied with the indoor noise about their living and working area is suggested base on the survey in this research.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.107-111
• /
• 2009

Acoustic OFDM is used for audible frequency band acoustic communication which employs loudspeaker as transmitter and microphone as the receiver antenna. Since acoustic OFDM can transmit about 1 kbps using 1600 Hz band. acoustic OFDM signal is inserted into the audio signal like music or speech, However. audio quality deteriorates definitely during the inserting process. This paper introduces a reason for audio quality deterioration and discuss how to reduce this phenomenon.