• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.2
• /
• pp.380-386
• /
• 2018

One of the most difficult technical aspects of music is vocals (the voice). Unlike ordinary musical instruments, it is difficult to apply common values because the tone (that is, the color) varies greatly depending on the singer, and therefore, it is necessary to properly mix in various effects. Therefore, this study is intended to suggest concepts, the current state, and effective usage of reverberation (or reverb), which is the most typical of vocal effects, using wave renaissance reverb, which is one of the effects that are the most commonly used by students. The most important part of the mixing process in popular music is how to enhance the voice. Since the spatial impression of sound makes music more beautiful, the role of reverb as a vocal effect is absolute. Computer technology has made it easier to create music, but it has produced a side effect in which individual technique falls short, such as using predetermined presets only. Studies on the use of reverb by musicians through more detailed efforts are expected to contribute to creating good music.

• Phonetics and Speech Sciences
• /
• v.1 no.4
• /
• pp.105-109
• /
• 2009

This thesis describes the method for well voice announcement using the TTS(Text-To-Speech) technology in the shop music broadcasting service. Offering a high quality TTS sound service for each shop requires a great expense. According to a report on the architectural acoustics the room acoustic indexes such as reverberation time and early decay time are closely connected with a subjective awareness about acoustics. By using the result the customers will be able to recognize better the voice announcement by applying sound effect to speech files made by TTS. The result of an aural comprehension examination has shown better about almost all of the parameters by applying reverb effect to TTS sound.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05b
• /
• pp.599-602
• /
• 2010

음악 제작 과정의 마지막 단계는 마스터링이다. 과거의 마스터링은 단순히 컴프레서(Compressor)와 리미터(Limiter)를 이용하여 각 트랙의 오디오 레벨을 일률적으로 매칭시키는 것이었지만, 디지털 장비의 꾸준한 발전으로 많은 마스터링 제작자들은 이퀄라이저(Equalizer)와 컴프레서를 기본으로 리버브(Reverb), 딜레이(Delay), 그리고 디더(Dither)를 이용하여 모든 트랙을 하나의 통일된 분위기로 제작하는 방식으로 진보하고 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.384-390
• /
• 2020

The reverberation effect on the sound when producing movies or VR contents is a very important factor in the realism and liveliness. The reverberation time depending the space is recommended in a standard called RT60(Reverberation Time 60 dB). In this paper, we propose a scene recognition technique for automatic reverberation editing. To this end, we devised a classification model that independently trains color images and predicted depth images in the same model. Indoor scene classification is limited only by training color information because of the similarity of internal structure. Deep learning based depth information extraction technology is used to use spatial depth information. Based on RT60, 10 scene classes were constructed and model training and evaluation were conducted. Finally, the proposed SCR + DNet (Scene Classification for Reverb + Depth Net) classifier achieves higher performance than conventional CNN classifiers with 92.4% accuracy.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.33-38
• /
• 2018

Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.569-573
• /
• 2018

Music is composed of the sound of many instruments. Among them, the sound of the human voice naturally stands out to us and immediately connects with the listener. However, A lot of different steps go into perfectly mixing a vocal, but I'm going to focus on the most important step, equalization. In this paper, starting with the concept and the type of EQ for the requirements associated with the EQ's work and will know about when and how to use subtractive EQ, additive EQ during the recording and mixing process. EQ is one if the most important tools for mixing, especially when dealing with vocals. The control that EQ's offer allows you work, boosting and cutting to fit the vocal perfectly into the mix. The key to get a professional sounding vocal every time is to always keep in mind what you're trying to achieve stylistically and for it, using reference track is very effective. In addition to EQing, there are a variety of complex working steps such as compression, reverb, chorus, delay, adjusted for the effects of the work and harmonies of backing vocals and that are also very important task. The work of EQing is the beginning of the mixing process, among other things, need to be a detailed work throughout the consideration of the above points to its importance is greater relationship.