• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

• The Journal of the Convergence on Culture Technology
• /
• v.1 no.2
• /
• pp.21-36
• /
• 2015

This study is a descriptive study to examine how poem causes effects of literary treatment for the contemporary people and how to improve therapeutic effect with poem by illustrating the process of therapeutic effect by poem. Each poem in the poetry book has a well-organized flow. While those poems are mixed, it can be synapsed into the cognitive system of readers by their taste in the form of introduction, development, turn, and conclusion.' The poetry book is structured with the transition of literary treatment. Such transition structure is embodied in a circle. If poetic contents are positive and creative in such transitive structure, it gives more comfort and excitement to readers increasing therapeutic effect. Therefore, it is very important to progress literatherapy narrative with such creative works.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.1
• /
• pp.1-8
• /
• 2020

If a dangerous situation arises in a place where out of reach from the human, UAVs can be used to determine the size and location of the situation to reduce the further damage. With this in mind, this paper sets the minimum value of the roll, pitch, and yaw using beta flight to detect the UAV's smooth hovering, integration, and derivative (PID) values to ensure that the UAV stays horizontal, minimizing errors for safe hovering, and the camera uses Open CV to install the Raspberry Pi program and then HSV (color, saturation, Brightness) using the color palette, the filter is black and white except for the red color, which is the closest to the fire we want, so that the UAV detects the image in the air in real time. Finally, it was confirmed that hovering was possible at a height of 0.5 to 5m, and red color recognition was possible at a distance of 5cm and at a distance of 5m.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.360-365
• /
• 2008

We propose an efficient robot name registration and recognition method in order to enable a Call-and-Come service for home robots. In the proposed method for the name registration, the search space is first restricted by using monophone-based acoustic models. Second, the registration of robot names is completed by using triphone-based acoustic models in the restricted search space. Next, the parameter for the utterance verification is calculated to reduce the acceptance rate of false calls. In addition, acoustic models are adapted by using a distance speech database to improve the performance of distance speech recognition, Moreover, the location of a user is estimated by using a microphone array. The experimental result on the registration and recognition of robot names shows that the word accuracy of speech recognition is 98.3%.

• Korean Journal of Cognitive Science
• /
• v.15 no.1
• /
• pp.1-11
• /
• 2004

The aim of this study is to reveal the order and the age of mastery of phonemic contrast in vowel sounds of Korean. For this purpose, we made an observation of the correspondences between the sounds produced by children of 12-35 months and the target sounds produced by adults. The provisional order and the age of contrast acquisition shown from the results of this study are as follows. First, the differential production of vowels by the feature relating to the body of the tongue precedes the differential production of vowels by the feature relating to the lip rounding. Second, as for the differential production of vowels by the feature relating to the body of the tongue, the contrast between the low vowels and the others is accomplished first, and the contrast between the high and low vowels and the contrast between the front and the back vowels are established around the age of 24 months. Third, as for the differential production of vowels by the feature relating to the lip rounding, the contrast between the rounded and the unrounded vowel is not accomplished until 36 months. Finally, we observed, prior to the completion of the differential production of phonemes, children use a specific phoneme excessively. This passing phrase could be interpreted as a result of over-application of a distinctive feature in the course of acquisition of it.

• Journal of the Korean Institute of Gas
• /
• v.18 no.3
• /
• pp.31-37
• /
• 2014

The aim of this work is to provide new experimental data on the pyrolysis characteristics and the minimum ignition energy (MIE) by using the same high-density polyethylene (HDPE) powder in domestic HDPE dust explosion accident. To evaluate the explosion sensitivity of HDPE, thermo-gravimetric analysis (TGA), differential scanning calorimeter (DSC) and MIE apparatus (MIKE-3, K$\ddot{u}$hner) was conducted. The measurements showed the volume median diameter of $61.6{\mu}m$ but the particle number density of 98 % in the range $0.4{\sim}4{\mu}m$. The ignition temperature from the results of TGA and DSC in HDPE dust layers was observed in the range of $380{\sim}490^{\circ}C$. MIE was measured under 1 mJ in the HDPE dust concentration of $1200{\sim}1800g/m^3$, it was found that the ratio of particle number density in the range $0.4{\sim}4{\mu}m$ was very high (98%).

• Journal of the Korean Society of Safety
• /
• v.33 no.3
• /
• pp.15-20
• /
• 2018

There have been a number of major fatal fire accidents in Korea recently. The number of fires in 2017 were 44,178, which is not only increasing number of fires but also increasing in casualties. Particularly, the fire at Jecheon Sports Center, which suffered many casualties, is expected to have a huge impact. The cause of the fire has not been determined yet, but heat waves on the ceiling have also been pointed out. As such, the copper heating waves, which are used as a preventive measure against damage of pipes due to freezing of pipes, etc., always have a fire hazard. To determine the possibility of a flame-resistant heated fire, a positive electric cable product was used to artificially ignite and analyze the results. In case of a short circuit, the external covering of the positive electric cable is damaged, but not short circuit unless the heating material surrounding the wire is damaged. Due to the characteristics of heating cable for preventing copper waves, the chances of insulation becoming more severe due to moisture and temperature changes are higher than normal wires. If the internal heating system is carbonized by insulating deterioration without damage to the outer coating, it is likely to cause trekking, to form a winding loop in the heating materials, and to cause short circuit in the heated materials. For the positive temperature line, if the middle is shorted, the current continues to flow to the short circuit unless the breaker disconnects. Consequently, a heated fire that does not cut off the power immediately may leave multiple marks or cuts.

• Fire Science and Engineering
• /
• v.20 no.1 s.61
• /
• pp.43-49
• /
• 2006

In this paper, we are studied on the temperature characteristics and fire progress of an incandescent electric lamp at 220V/100W. In the case of stationary state, the ignition possibility of the incandescent electric lamp due to the heat generation was low because the temperature was measured at $161.9^{\circ}C$ the temperature was increased at $538.1^{\circ}C$ in the airtight chamber, but it does not generated the fire because the oxygen was not exist in the airtight chamber. When the lamp is broken, the filament of lamp was melted in the air. The gas of lamp interior spurted to the weakest part by external flame. Thus, the incandescent electric lamp is high possibility of fire when oxygens from airtight space. Also, it is known that the possibility of ignition is very high if combustion materials(sawdust) exists on surrounding. These experimental results will be utilized for the data in the investigation electrical fire cause.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.15 no.6
• /
• pp.56-62
• /
• 2011

An experimental study on design of a catalytic ignitor was performed to use an ignition source for a small bi-propellant liquid rocket engine which use hydrogen peroxide and kerosene as propellants. In the catalytic ignitor, hot gas of hydrogen peroxide which was decomposed by a catalyst induced autoignition of kerosene. Mass flow rate and O/F ratio for the ignitor were calculated by CEA code. A combustion chamber which had a quartz window and thermocouples was manufactured to determine whether the ignition is successful. Ignition performance was investigated according to exit area of fixed rings and mixture ratio. Results showed that reliable ignition performance was achieved at non-choking exit area of fixed ring and O/F ratio of 6~8.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.4
• /
• pp.321-327
• /
• 2015

In this paper, we propose an algorithm for achieving robust Visual Voice Activity Detection (VVAD) for enhanced speech recognition. In conventional VVAD algorithms, the motion of lip region is found by applying an optical flow or Chaos inspired measures for detecting visual speech frames. The optical flow-based VVAD is difficult to be adopted to driving scenarios due to its computational complexity. While invariant to illumination changes, Chaos theory based VVAD method is sensitive to motion translations caused by driver's head movements. The proposed Local Variance Histogram (LVH) is robust to the pixel intensity changes from both illumination change and translation change. Hence, for improved performance in environmental changes, we adopt the novel threshold estimation using total variance change. In the experimental results, the proposed VVAD algorithm achieves robustness in various driving situations.