Sound Source Recognition Research Articles

주변 배경음에 강인한 구간 검출을 통한 음원 인식 및 위치 추적 시스템 설계

본 논문은 비정상 상황 시 발생하는 음원에 대해 주변 환경 음에 강인한 음원 구간을 검출하여, 구간내의 신호를 이용한 음원 인식 과 위치 추적 시스템 설계에 관한 연구이다. 강인한 음원 구간 검출은 수신되는 오디오 신호로부터 단 구간 가중 평균 델타 에너지를 계산하여, 저역 통과 필터에 입력 후, 출력되는 결과 값들의 비교를 통해 배경음에 강인한 구간을 정의 하며, 음원 인식은 검출된 구간 내 데이터로부터 종래의 인식 방법인 HMM(: Hidden Markov Model)을 이용해, 음원 인식 정보를 생성하여 학습 및 인식을 한다. 이는 주변 배경음이 포함된 음원 신호에 대해 기존 신호의 에너지를 이용해 구간을 검출 후, HMM을 통한 인식에 비해 3.94% 상향된 인식률을 보인다. 또한 인식 결과를 바탕으로 구간내의 신호간의 TDOA(: Time Delay of Arrival)를 이용한 위치 파악은 실제 발생 위치와의 각도와 97.44%일치함을 보인다. This paper is on a system design of recognizing sound sources and tracing locations from detecting a section of sound sources which is strong in surrounding environmental sounds about sound sources occurring in an abnormal situation by using signals within the section. In detection of the section with strong sound sources, weighted average delta energy of a short section is calculated from audio signals received. After inputting it into a low-pass filter, through comparison of values of the output result, a section strong in background sound is defined. In recognition of sound sources, from data of the detected section, using an HMM(: Hidden Markov Model) as a traditional recognition method, learning and recognition are realized from creating information to recognize sound sources. About signals of sound sources that surrounding background sounds are included, by using energy of existing signals, after detecting the section, compared with the recognition through the HMM, a recognition rate of 3.94% increase is shown. Also, based on the recognition result, location grasping by using TDOA(: Time Delay of Arrival) between signals in the section accords with 97.44% of angles of a real occurrence location.

The effects of spectral fine structure and amplitude envelope on perceived similarity and identification of approaching vehicles

The recognition and identification of important complex natural sound sources is a critical component of maintaining environmental awareness. The properties of sound sources are not static; environmental factors can cause dramatic shifts in acoustic structure. The present study investigates the effects of large imposed acoustic changes on listener perception of approaching ground and aerial vehicles. In the first experiment, listeners rated the perceived similarity of the vehicle stimuli that were either (1) unaltered, or had (2) spectral fine structure replaced with random noise, or (3) had their natural amplitude envelopes flattened. The results of a multidimensional scaling (MDS) analysis found that the ordering of perceptual space for each of the conditions was generally a function of the acoustic information available. The second experiment investigated listener identification for the same sets of sounds. Identification performance across vehicle sounds had good agreement with similarity mappings and was best when spectral fine structure was smoothed and variations in amplitude envelope were maintained, and worst when the opposite was true. These results are consistent with the notion that amplitude envelope is a critical component in the recognition and identification of complex natural sound sources.

A system for visualizing sound source using augmented reality

PurposeThe purpose of this paper is to design and propose a new interface for hearing‐impaired for the users who can hardly realize the environmental sound.Design/methodology/approachThe authors propose the use of an augmented reality (AR) system with sound source recognition to augment human vision. In this system, sound source and position is detected by using acoustic processing.FindingsThe authors confirmed that the source and direction of sound could be effectively recognized, and that AR was implemented, and thus that the user could use this system to recognize and visualize environmental sounds. When there was only a single sound source in the surrounding environment such as at home or when doing some simple work, and especially when a source was near a user, this system provided information on the sound source and visualized the sound source to satisfy the user's need.Originality/valueThe system can recognize the environmental sound in realtime and inform the user of the type of sound by showing a virtual object in the user's sight. Furthermore, the user can find the direction of the sound source by using a microphone array and locate the sound source through the AR marker attached to the object.

The Study of Joint Acoustic Holography Algorithms based on Continuous Scanning

To effectively solve the problem of rapid measurement and recognition about large underwater sound source, continuous scanning is applied to measure the large underwater sound source. The theory of sound source recognition based on mobile framework technology (FAH)nd Helmholtz equation least squares method (HELS)s investigated. Combination of acoustic holography method based on MFAH and HELS is created and verified through simulation and basin test. The study shows that combination algorithm can accurately identify all kinds of underwater source and obtain a high positioning accuracy of the noise source, and can be used for a wide frequency range; when there are multiple coherent sound sources in the complex sound field, noise source identification and location only requires that an array holographic measurement surface is 1.3 times for the reconstruction surface. Using a small measuring surface to quickly identify large underwater sound source is achieved. The shortcomings of workload and time-consuming in the traditional measurement are resolved. And it provides convenience for engineering applications.

The first three seconds

The human auditory system can rapidly process musical information such as, for example: the recognition and identification of sound sources, the deciphering of meter, tempo, mode, and texture, the processing of lyrics and dynamics, the identification of musical style and genre, the perception of performance nuance, and the apprehension of emotional character. Two empirical studies are reported that attempt to chronicle when such information is processed. In the first exploratory study, a diverse set of musical excerpts was selected and trimmed to various durations, ranging from 50 ms to 3000 ms. These samples, beginning with the shortest and ending with the longest, were presented to participants, who were then asked to free associate and talk about any observations that came to mind. Based on these results, a second main study was carried out using a betting paradigm to determine the amount of exposure needed for listeners to feel confident about acquired musical information. The results suggest a rapid unfolding of cognitive processes within a 3-second listening span.

Detection of the break in interaural correlation is affected by interaural delay, aging, and center frequency

This study investigated whether interaural integration is affected by introducing an interaural delay. In Experiment 1, both younger adults with normal hearing and older adults in the early stages of presbycusis were able to detect a transient break in interaural correlation (BIC) in the temporal middle of interaurally correlated wideband noises. However, their duration thresholds for detecting the BIC became larger with increasing interaural time difference (ITD) from 0 to 6 ms, and the threshold increase for older participants was larger than that for younger participants. In Experiment 2, to investigate whether the effect of changing ITD on the BIC detection is frequency-dependent, 1/3-octave narrowband noises with various center frequencies were used as stimuli. Results show that the duration threshold for detecting the BIC was higher for high-frequency noises than for low-frequency noises. Also, with increasing ITD from 0 to 4 ms, the threshold increase was larger for high-frequency noises than for low-frequency noises. The results suggest that there are age- and frequency-related temporal declines in maintaining fine-structure signals for interaural integration. These declines may affect the recognition of sound sources in reverberant environments.

Bird hearing and communication in natural environments.

A soundscape, taken from human work, generally refers to the complex of sounds that are integral to and formed by a particular natural environment. Some of this sound is from abiotic sources (e.g., wind, streams, various anthropogenic sources, etc.) while some of this sound may come from conspecifics or other animals. In nature, all sound reaching an animal’s ears, whether from biotic or abiotic sources, is shaped by this natural environment. Noise, sound distortion, and frequency‐dependent attenuation can increase detection thresholds and interfere with discrimination, recognition, and localization of sound sources. Signals degraded by travel through the environment and/or affected by masking can in turn adversely affect critical behaviors such as mate attraction, territorial defense, parent‐offspring communication, predator avoidance, and prey detection. Using laboratory psychophysical data from several species of birds, some interactions among these factors and the implications for communication in a noisy environment are described. Species differences in auditory sensitivity and the characteristics of the environment are major factors in predicting whether a given soundscape limits communication between birds or interferes with detection of other biologically important sounds. [Work supported by NIH grant to R.J.D.]

The texture of natural sounds

The texture, a spectro-temporal pattern, of many sound sources is a robust and characteristic perceptual property that listeners use for sound source recognition. The robustness of the texture ensures that we can recognize sound sources like a helicopter, flowing water, or a surf breaking on pebbles in a wide variety of acoustic environments. This robustness suggests that textures can be used for automatic source identification or environment classification. We introduce a method to determine the presence of sound textures associated with, for example, flat noise, pulsed noises (helicopter), sweep based textures (running water), and tonal noises (babble). The cumulative probability density of time-frequency fluctuations are matched with prototypical cumulative probability density functions (cpdf) with a running variant of the Kolmogorov-Smirnov test. Textures with a similar distribution as the target distribution, contribute approximately equally to all values of the cpdf. The flatness of this distribution is used as a distance measure. When the pdf's of the target textures do not overlap strongly, the method can determine the texture of time-frequency-regions as small as 100 ms by 6 semi-tones. This method can therefore also be used to determine the texture of the background.

Influence of sound source recognition on annoyance judgment

Research on annoyance usually focuses on the annoyance estimation of the perceived acoustic signal. It disregards the fact that the basic aim of the auditory system is the detection of the properties of the sound source and not the sound signal itself. In this study the annoyance caused by a tram and a bus and two pairs of artificially modified original recordings has been investigated under two experimental conditions. In the first, subjects judged the noise annoyance of the original signals (the tram and bus) together with two modified sound sources (a tram-like bus and a bus-like tram). In the second, the original signals were judged together with another pair of modified sound sources (a tram-like noise and a bus-like noise). The tram-like bus and bus-like tram signals were created in the way that hybrid instruments are built, while the tram-like noise and bus-like noise were simply white noise shaped in accordance with the power spectrum envelope of the original signals. Although both types of modified signals had the same power spectra and time patterns as the original signals, the tram-like bus and bus-like tram signals were more similar in their effect on annoyance judgments to the original recordings than the tram-like noise and bus-like noise signals. It is shown that the same acoustic characteristics of signals, including the calculated loudness, does not necessarily entail the same annoyance judgments. The annoyance judgments of two original signals - the tram and bus - obtained in the two psychoacoustic experiments were not the same. A possible explanation of this phenomenon is discussed.

Environmental sound research as it stands today

Environmental sound research is still in its beginning stages, although in recent years a body of research has started to accumulate, both on the perception of environmental sounds themselves and on their practical applications in other areas of auditory research and cognitive science. However, several important issues remain unresolved, such as methodologies for environmental sound research, how to coordinate research efforts in disparate areas of environmental sound study, and how best to integrate environmental sound research into the larger body of hearing research. These issues will be discussed along with some of the current and future practical applications of environmental sounds, such as in assistive listening devices and automatic sound source recognition.

Timbre modeling for the purpose of sound source recognition and separation in music

Timbre models of musical instruments were studied in order to recognize sound sources in music and to organize sounds to their sources. The log‐power spectrum of the sounds was modeled using a combination of linear bases, one defined as a function of frequency, and another as a function of harmonic index. Algorithms for initializing, learning, and sequentilly adapting this model are described. In simulations, the model had a benefit over conventional Mel‐cepstral representations, especially in the case of certain instruments, including the electric guitar, the organ, the mallet percussions, and the clarinets. The improvement was observed in supervised instrument classification, but not so clearly in the unsupervised clustering of sounds.

Perspectives on the Contribution of Timbre to Musical Structure

September 01 1999 Perspectives on the Contribution of Timbre to Musical Structure Stephen McAdams Stephen McAdams Institut de Recherche et Coordination Acoustique/Musique (IRCAM) 1 Place Igor-Stravinsky, Paris F-75004, France, http://www.ircam.frLaboratoire de Psychologie Expérimentale, Centre Nationale de Recherche Scientifique (CNRS) Université René Descartes, EPHE, 28 rue Serpente, Paris F-75006, France, smc@ircam.fr Search for other works by this author on: This Site Google Scholar Author and Article Information Stephen McAdams Institut de Recherche et Coordination Acoustique/Musique (IRCAM) 1 Place Igor-Stravinsky, Paris F-75004, France, http://www.ircam.frLaboratoire de Psychologie Expérimentale, Centre Nationale de Recherche Scientifique (CNRS) Université René Descartes, EPHE, 28 rue Serpente, Paris F-75006, France, smc@ircam.fr Online ISSN: 1531-5169 Print ISSN: 0148-9267 © 1999 Massachusetts Institute of Technology1999 Computer Music Journal (1999) 23 (3): 85–102. https://doi.org/10.1162/014892699559797 Cite Icon Cite Permissions Share Icon Share Facebook Twitter LinkedIn MailTo Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Search Site Citation Stephen McAdams; Perspectives on the Contribution of Timbre to Musical Structure. Computer Music Journal 1999; 23 (3): 85–102. doi: https://doi.org/10.1162/014892699559797 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentAll JournalsComputer Music Journal Search Advanced Search This content is only available as a PDF. © 1999 Massachusetts Institute of Technology1999 Article PDF first page preview Close Modal You do not currently have access to this content.