• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.2211-2217
• /
• 2009

In this paper, we propose the speech enhancement algorithm using an one-microphone in a reverberant room environments. Spectral subtraction is the effective method which can reduce the reverberation element and the noise in a spectrum domain. Spectral subtraction needs correct separation of voice section and silent section therefore to improve the performance, voice activity detection(VAD) based on entropy has been applied to the proposed method. We test a performance of the proposed method by comparing with conventional method which used VAD based on energy detection. Reverberation reduction ratio with variable of SNR and a reverberation time is used as a test index. From the simulation result, proposed method shows performance better than conventional method.

• Journal of Sensor Science and Technology
• /
• v.25 no.5
• /
• pp.344-348
• /
• 2016

We developed a 2-channel fiber-optic temperature sensor (FOTS) using a temperature sensing probe, a fiber-optic coupler, transmitting optical fiber, and an optical time domain reflectometer (OTDR). The temperature sensing probe is divided into a sensing probe and a reference probe for accurate thermometry. A sensing probe is composed of a silicon oil, a FC terminator, a brass pipe, and a singlemode optical fiber and the structure of a reference probe is identical with that of the sensing probe excluding a silicon oil. In this study, we measured the modified optical powers of the light signals reflected from the temperature sensing probe placed inside of the water with a thermal variation from 5 to $70^{\circ}C$. Although the optical power of the reference probe was constant regardless of the temperature change, the optical power of the sensing probe decreased linearly as the temperature increased. As experimental results, the FOTS using a subtraction method showed a small difference (i.e., hysteresis) in its response due to heating and cooling. The reversibility and reproducibility of the FOTS were also evaluated.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2006.08a
• /
• pp.144-144
• /
• 2006

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2009.10a
• /
• pp.67-68
• /
• 2009

• Speech Sciences
• /
• v.13 no.1
• /
• pp.129-139
• /
• 2006

In this paper, we propose two effective energy feature normalization methods for robust speech recognition in noisy environments. In the first method, we estimate the noise energy and remove it from the noisy speech energy. In the second method, we propose a modified algorithm for the Log-energy Dynamic Range Normalization (ERN) method. In the ERN method, the log energy of the training data in a clean environment is transformed into the log energy in noisy environments. If the minimum log energy of the test data is outside of a pre-defined range, the log energy of the test data is also transformed. Since the ERN method has several weaknesses, we propose a modified transform scheme designed to reduce the residual mismatch that it produces. In the evaluation conducted on the Aurora2.0 database, we obtained a significant performance improvement.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1543-1546
• /
• 2002

The expandable 4 bit adder/subtracter IC was designed using the adiabatic and dynamic CMOS logic (ADCL) circuit as the ultra-low power consumption basic logic circuit and the IC was fabricated using a standard 1.2 ${\mu}$ CMOS process. As the result the steady operation of 4 bit addition and subtraction has been confirmed even if the frequency of the sinusoidal supply voltage is higher than 10MHz. Additionally, by the simulation, at the frequency of 10MHz, energy consumption per operation is obtained as 93.67pJ (ar addition and as 118.67pJ for subtraction, respectively. Each energy is about 1110 in comparison with the case in which the conventional CMOS logic circuit is used. A simple and low power oscillation circuit is also proposed as the power supply circuit f3r the ADCL circuit. The oscillator operates with a less one volt of DC supply voltage and around one milli-watts power dissipation.

• Journal of Fashion Business
• /
• v.19 no.5
• /
• pp.199-212
• /
• 2015

Environmentally-friendly whole-cut designs can minimize carbon dioxide emissions which are harmful to the earth, and reduce energy, labor force and time in cutting or sewing clothes. The design and way of wearing clothing will be investigated by classifying whole-cut clothing appearing in the history of costume and past traditional outfits such as Drapery, a Pancho, Tunic, or Loincloth. According to the results from the analysis of whole-cut methods applied in design, they were classified as follows: whole-cut, utilizing square-panels as is, pleats, smoking, lip band, origami, cutting way, and subtraction-cutting whole-cut design. The whole-cut design utilizing square panel as it is can minimize the waste of energy and material but can also maximize the possibility of circulation by recycling. In utilizing an all square panel, it broke away from the existing whole-cut in the western pattern, namely, the pattern of clothes clinging to the body, and was found to have new aesthetic value with a new approach. Due to the whole-cut method having a restriction in the use of dart and line cutting in its designing process, there were only designs that did not show the body line, such as designs clinging to the body. Therefore we developed a design similar to those that cling to the body by whole-cut, In addition, the work produced was with high efficiency and variability, which produces simple designs but can be worn in a variety of ways.

• The Journal of the Acoustical Society of Korea
• /
• v.9 no.2
• /
• pp.34-41
• /
• 1990

The energy parameter is widely used in pre-processing of speech signals, because it represent the phoneme characteristics of well But, the energy parameter is affected by the window length during the extracting. Thus, in this paper, the window length effects are studied in detail, and we proposed a new energy extraction algorithm that reduces the length effects. The energy contours with this algorithm are well representing for the characteristics of speech phonemes. And the computations to implement the algorithm are only required one subtraction, one addition, and two comparison aperation per speech sample.

• Korean Journal of Radiology
• /
• v.23 no.1
• /
• pp.139-149
• /
• 2022

Objective: To compare the effects of bone suppression imaging using deep learning (BSp-DL) based on a generative adversarial network (GAN) and bone subtraction imaging using a dual energy technique (BSt-DE) on radiologists' performance for pulmonary nodule detection on chest radiographs (CXRs). Materials and Methods: A total of 111 adults, including 49 patients with 83 pulmonary nodules, who underwent both CXR using the dual energy technique and chest CT, were enrolled. Using CT as a reference, two independent radiologists evaluated CXR images for the presence or absence of pulmonary nodules in three reading sessions (standard CXR, BSt-DE CXR, and BSp-DL CXR). Person-wise and nodule-wise performances were assessed using receiver-operating characteristic (ROC) and alternative free-response ROC (AFROC) curve analyses, respectively. Subgroup analyses based on nodule size, location, and the presence of overlapping bones were performed. Results: BSt-DE with an area under the AFROC curve (AUAFROC) of 0.996 and 0.976 for readers 1 and 2, respectively, and BSp-DL with AUAFROC of 0.981 and 0.958, respectively, showed better nodule-wise performance than standard CXR (AUAFROC of 0.907 and 0.808, respectively; p ≤ 0.005). In the person-wise analysis, BSp-DL with an area under the ROC curve (AUROC) of 0.984 and 0.931 for readers 1 and 2, respectively, showed better performance than standard CXR (AUROC of 0.915 and 0.798, respectively; p ≤ 0.011) and comparable performance to BSt-DE (AUROC of 0.988 and 0.974; p ≥ 0.064). BSt-DE and BSp-DL were superior to standard CXR for detecting nodules overlapping with bones (p < 0.017) or in the upper/middle lung zone (p < 0.017). BSt-DE was superior (p < 0.017) to BSp-DL in detecting peripheral and sub-centimeter nodules. Conclusion: BSp-DL (GAN-based bone suppression) showed comparable performance to BSt-DE and can improve radiologists' performance in detecting pulmonary nodules on CXRs. Nevertheless, for better delineation of small and peripheral nodules, further technical improvements are required.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.56-62
• /
• 2001

In this paper, we adopt a missing data theory to speech recognition. It can be used in order to maintain high performance of speech recognizer when the missing data occurs. In general, hidden Markov model (HMM) is used as a stochastic classifier for speech recognition task. Acoustic events are represented by continuous probability density function in continuous density HMM(CDHMM). The missing data theory has an advantage that can be easily applicable to this CDHMM. A marginalization method is used for processing missing data because it has small complexity and is easy to apply to automatic speech recognition (ASR). Also, a spectral subtraction is used for detecting missing data. If the difference between the energy of speech and that of background noise is below given threshold value, we determine that missing has occurred. We propose a new method that examines the reliability of detected missing data using voicing probability. The voicing probability is used to find voiced frames. It is used to process the missing data in voiced region that has more redundant information than consonants. The experimental results showed that our method improves performance than baseline system that uses spectral subtraction method only. In 452 words isolated word recognition experiment, the proposed method using the voicing probability reduced the average word error rate by 12％ in a typical noise situation.