Ara Bae, Ki‑mu Yoon, Jaehong Jung, Bokyung Chung, Wooil Kim
{"title":"I-vector similarity based speech segmentation for interested speaker to speaker diarization system","authors":"Ara Bae, Ki‑mu Yoon, Jaehong Jung, Bokyung Chung, Wooil Kim","doi":"10.7776/ASK.2020.39.5.461","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.5.461","url":null,"abstract":"In noisy and multi-speaker environments, the performance of speech recognition is unavoidably lower than in a clean environment. To improve speech recognition, in this paper, the signal of the speaker of interest is extracted from the mixed speech signals with multiple speakers. The VoiceFilter model is used to effectively separate overlapped speech signals. In this work, clustering by Probabilistic Linear Discriminant Analysis (PLDA) similarity score was employed to detect the speech signal of the interested speaker, which is used as the reference speaker to VoiceFilter-based separation. Therefore, by utilizing the speaker feature extracted from the detected speech by the proposed clustering method, this paper propose a speaker diarization system using only the mixed speech without an explicit reference speaker signal. We use phone-dataset consisting of two speakers to evaluate the performance of the speaker diarization system. Source to Distortion Ratio (SDR) of the operator (Rx) speech and customer speech (Tx) are 5.22 dB and –5.22 dB respectively before separation, and the results of the proposed separation system show 11.26 dB and 8.53 dB respectively.","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"461-467"},"PeriodicalIF":0.4,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42501548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Junsu Lee, Yeon-Seong Park, Miji Kim, Changhan Yoon
{"title":"Development of portable single-beam acoustic tweezers for biomedical applications","authors":"Junsu Lee, Yeon-Seong Park, Miji Kim, Changhan Yoon","doi":"10.7776/ASK.2020.39.5.435","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.5.435","url":null,"abstract":"Single-beam acoustic tweezers that are capable of manipulating micron-size particles in a non-contact manner have been used in many biological and biomedical applications. Current single-beam acoustic tweezer systems developed for in vitro experiments consist of a function generator and a power amplifier, thus the system is bulky and expensive. This configuration would not be suitable for in vivo and clinical applications. Thus, in this paper, we present a portable single-beam acoustic tweezer system and its performances of trapping and manipulating micron-size objects. The developed system consists of an Field Programmable Gate Array (FPGA) chip and two pulsers, and parameters such as center frequency and pulse duration were controlled by a Personal Computer (PC) via a USB (Universal Serial Bus) interface in real-time. It was shown that the system was capable of generating the transmitting pulse up to 20 MHz, and producing sufficient intensity to trap microparticles and cells. The performance of the system was evaluated by trapping and manipulating 40 μm and 90 μm in diameter polystyrene particles.","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"435-440"},"PeriodicalIF":0.4,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44370393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. Park, HyunShig Joo, I. Jang, Seung-Hoon Kang, W. Ohm, Sang-Joon Shin, Jeongwon Park
{"title":"A method for removal of reflection artifact in computational fluid dynamic simulation of supersonic jet noise","authors":"T. Park, HyunShig Joo, I. Jang, Seung-Hoon Kang, W. Ohm, Sang-Joon Shin, Jeongwon Park","doi":"10.7776/ASK.2020.39.4.364","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.4.364","url":null,"abstract":"Rocket noise generated from the exhaust plume produces the enormous acoustic loading, which adversely affects the integrity of the electronic components and payload (satellite) at liftoff. The prediction of rocket noise consists of two steps: the supersonic jet exhaust is simulated by a method of the Computational Fluid Dynamics (CFD), and an acoustic transport method, such as the Helmholtz-Kirchhoff integral, is applied to predict the noise field. One of the difficulties in the CFD step is to remove the boundary reflection artifacts from the finite computation boundary. In general, artificial damping, known as a sponge layer, is added nearby the boundary to attenuate these reflected waves but this layer demands a large computational area and an optimization procedure of related parameters. In this paper, a cost-efficient way to separate the reflected waves based on the two microphone method is firstly introduced and applied to the computation result of a laboratory-scale supersonic jet noise without sponge layers.","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"364-370"},"PeriodicalIF":0.4,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46315794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A study on the fault diagnosis of rotating machine by machine learning","authors":"H. Jeon, Ji-Sun Kim, Bong-Ju Kim, Won-Jin Kim","doi":"10.7776/ASK.2020.39.4.263","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.4.263","url":null,"abstract":"In this study, a rotating machine that can reproduce normal condition and 8 fault conditions were produced, and vibration data was acquired. Feature is calculated from the acquired data, and accuracy is analyzed through fault diagnosis using artificial neural networks and genetic algorithms. In order to achieve optimal timing and higher accuracy, features by three domains were applied to the fault diagnosis. The learning number was selected as a setting variable. As a result of the rotating machine fault diagnosis, high precision was found in the frequency domain than in others, and precise fault diagnoses were accomplished through all of 10 operations, at the learning number of 5000 and 8000. Given the efficiency of time, it was estimated to be the most efficient when the number of learning was 5000.","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"263-269"},"PeriodicalIF":0.4,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49443891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cheol-Soo Park, S. Jeong, Gun-Do Kim, I. Moon, G. Yim
{"title":"A study on the estimation of bubble size distribution using an acoustic inversion method","authors":"Cheol-Soo Park, S. Jeong, Gun-Do Kim, I. Moon, G. Yim","doi":"10.7776/ASK.2020.39.3.151","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.3.151","url":null,"abstract":"","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"151-162"},"PeriodicalIF":0.4,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42817993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analysis of the range estimation error of a target in the asynchronous bistatic sonar","authors":"Euicheol Jeong, Tae-Hwan Kim","doi":"10.7776/ASK.2020.39.3.163","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.3.163","url":null,"abstract":"","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"163-169"},"PeriodicalIF":0.4,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46906280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design of a wideband cymbal transducer array","authors":"Donghyun Roh","doi":"10.7776/ASK.2020.39.3.170","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.3.170","url":null,"abstract":"Cymbal transducers are often used as an array rather than single because they have a high quality factor and low energy conversion efficiency. When used as an array, there occurs a big change in the frequency characteristics of the array due to the interaction between constituent transducers. In this study, we designed the structure of a cymbal transducer array to have ultra-wideband characteristics using this property. First, cymbal transducers with specific center frequencies were designed. Then, a 2x2 planar array was constructed with the designed transducers, where the cymbal transducers were arranged to have same or opposite polarization directions. For this structure, we analyzed the effect of the difference in the center frequency of and the spacing between the constituent transducers on the acoustical characteristics of the array. Based on the analysis, we designed the structure of the cymbal transducer array to have the widest possible bandwidth.","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"170-178"},"PeriodicalIF":0.4,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41323875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Myoungin Shin, Youngbin Cho, Youngmin Choo, Keunhwa Lee, Jungpyo Hong, Seongil Kim, W. Hong
{"title":"Analysis on performance of grid-free compressive beamforming based on experiment","authors":"Myoungin Shin, Youngbin Cho, Youngmin Choo, Keunhwa Lee, Jungpyo Hong, Seongil Kim, W. Hong","doi":"10.7776/ASK.2020.39.3.179","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.3.179","url":null,"abstract":"In this paper, we estimated the Direction of Arrival (DOA) using Conventional BeamForming (CBF), adaptive beamforming and compressive beamforming. Minimum Variance Distortionless Response (MVDR) and Multiple Signal Classification (MUSIC) are used as the adaptive beamforming, and grid-free compressive sensing is applied for the compressive sensing beamforming. Theoretical background and limitations of each technique are introduced, and the performance of each technique is compared through simulation and real experiments. The real experiments are conducted in the presence of reflected signal, transmitting a sound using two speakers and receiving acoustic data through a linear array consisting of eight microphones. Simulation and experimental results show that the adaptive beamforming and the grid-free compressive beamforming have a higher resolution than conventional beamforming when there are uncorrelated signals. On the other hand, the performance of the adaptive beamforming is degraded by the reflected signals whereas the grid-free compressive beamforming still improves the conventional beamforming resolution regardless of reflected signal presence.","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"179-190"},"PeriodicalIF":0.4,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41375268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Study on the pre-processors to improve the generalized-cross -correlation based time delay estimation under the narrow band single tone signal environments","authors":"Jun Seok Kim","doi":"10.7776/ASK.2020.39.3.207","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.3.207","url":null,"abstract":"There are several methods for the time delay estimation between signals to two receivers. Among these methods, Generalized Cross Correlation (GCC), which estimates the relative delay from the crosscorrelation between the different signals at the two receivers, is a traditionally well-known method. However, when using a narrow band Continuous Wave (CW) signal, the GCC method degrades the estimation performance from relatively higher signal-to-noise ratio than when using a wideband signal. To improve this phenomenon, this paper examines four different pre-processors for GCC using narrow band single frequency signals. Simulation shows that the performance gain of the preprocessed GCC is up to 9 dB for a 100 msec CW signal as well as up to 4 dB for a 1 s CW signal.","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"207-215"},"PeriodicalIF":0.4,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44602703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A study on user defined spoken wake-up word recognition system using deep neural network-hidden Markov model hybrid model","authors":"Ki-mu Yoon and Wooil Kim","doi":"10.7776/ASK.2020.39.2.131","DOIUrl":"https://doi.org/10.7776/ASK.2020.39.2.131","url":null,"abstract":"","PeriodicalId":42689,"journal":{"name":"Journal of the Acoustical Society of Korea","volume":"39 1","pages":"131-136"},"PeriodicalIF":0.4,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48582542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}