Video Soundtrack Research Articles

An Investigation of Chinese College Students' Access to European and American Popular Music in the Social Media Environment

The purpose of this paper is to explore how Chinese college students acquire European and American popular music in the social media environment. With the popularization of the Internet and the development of social media, college students gradually tend to contact and acquire music resources through these emerging platforms. Through questionnaire surveys and case studies, the study found that social media not only became the main channel for college students to obtain information about European and American popular music, but also profoundly influenced their music preferences and choices. Specifically, college students access the latest information, popular singles and album recommendations of European and American pop music through domestic social media platforms such as Weibo, WeChat and Jitterbug, as well as international platforms such as Instagram and YouTube. In addition, they also pay attention to the official accounts of singers, official accounts of music programs, and music recommendation bloggers to get more comprehensive music information. At the same time, the forms of sharing, amenity, and video soundtracks on social media have greatly contributed to the spread of European and American popular music.

Automatic environmental sound concepts discovery for video retrieval

This paper characterizes a new method for video–soundtrack retrieval based on environmental sounds. Actually, a set of 26 semantic audio concepts is employed. This set is chosen for its helpfulness to the users in terms of video browsing. Additionally, a set of 2000 videos has been annotated with these concepts. To enhance a new signal processing, we start with the separation of the audio sources. In addition, using a fundamental representation of the audio signal as a sequence of Mel Frequency Cepstral Coefficient, we can carry out experiments with three signal representations: the Support Vector machines, the Gaussian Mixture Model and the Hidden Markov Model. Throughout the experiment synthesis, we maintain the Gaussian Mixture Model classifier based on the Kullback–Leibler distance measure. As a matter of fact, we preserve this audio concept classification to integrate a video retrieval system. Hence, the obtained results mirror the effectiveness of our approaches in distinguishing environmental sound and researching video.

Video viewing: do auditory salient events capture visual attention?

We assess whether salient auditory events contained in soundtracks modify eye movements when exploring videos. In a previous study, we found that, on average, nonspatial sound contained in video soundtracks impacts on eye movements. This result indicates that sound could play a leading part in visual attention models to predict eye movements. In this research, we go further and test whether the effect of sound on eye movements is stronger just after salient auditory events. To automatically spot salient auditory events, we used two auditory saliency models: the discrete energy separation algorithm and the energy model. Both models provide a saliency time curve, based on the fusion of several elementary audio features. The most salient auditory events were extracted by thresholding these curves. We examined some eye movement parameters just after these events rather than on all the video frames. We showed that the effect of sound on eye movements (variability between eye positions, saccade amplitude, and fixation duration) was not stronger after salient auditory events than on average over entire videos. Thus, we suggest that sound could impact on visual exploration not only after salient events but in a more global way.

On the Applicability of Speaker Diarization to Audio Indexing of Non-Speech and Mixed Non-Speech/Speech Video Soundtracks

A video’s soundtrack is usually highly correlated to its content. Hence, audio-based techniques have recently emerged as a means for video concept detection complementary to visual analysis. Most state-of-the-art approaches rely on manual definition of predefined sound concepts such as “ngine sounds,” “utdoor/indoor sounds.” These approaches come with three major drawbacks: manual definitions do not scale as they are highly domain-dependent, manual definitions are highly subjective with respect to annotators and a large part of the audio content is omitted since the predefined concepts are usually found only in a fraction of the soundtrack. This paper explores how unsupervised audio segmentation systems like speaker diarization can be adapted to automatically identify low-level sound concepts similar to annotator defined concepts and how these concepts can be used for audio indexing. Speaker diarization systems are designed to answer the question “ho spoke when?”by finding segments in an audio stream that exhibit similar properties in feature space, i.e., sound similar. Using a diarization system, all the content of an audio file is analyzed and similar sounds are clustered. This article provides an in-depth analysis on the statistic properties of similar acoustic segments identified by the diarization system in a predefined document set and the theoretical fitness of this approach to discern one document class from another. It also discusses how diarization can be tuned in order to better reflect the acoustic properties of general sounds as opposed to speech and introduces a proof-of-concept system for multimedia event classification working with diarization-based indexing.

Preliminary study of jointed snaffle vs. crossunder bitless bridles: Quantified comparison of behaviour in four horses

The study tested the null hypothesis that if a horse is ridden in a snaffle bridle and then a crossunder bitless bridle, there will be no change in its behaviour. It was predicted that there would be change and that behaviour would improve when bitless. Four horses, none of which had ever been ridden in a crossunder bitless bridle, were ridden through two 4 min, exercise tests, first bitted then bitless. An independent judge marked the 27 phases of each test on a 10 point scale and comments and scores were recorded on a video soundtrack. The results refuted the null hypothesis and upheld the predictions. Mean score, when bitted, was 37%; and through the first 4 min of being bitless, 64%. A binomial probability distribution suggested that the results were significantly different from random effects. All 4 horses accepted the crossunder bitless bridle without hesitation. Further studies are warranted and it is hoped that others will build on this new field of investigation. The authors are of the opinion that the bit can be a welfare and safety problem for both horse and horseman. Equestrian organisations that currently mandate use of the bit for competitions are urged to review their rules.

Reliable mismatch negativity event-related potentials for tones presented with a concurrent video soundtrack

Reliable mismatch negativity event-related potentials for tones presented with a concurrent video soundtrack

Copyright and the music business

For the music industry the age of manufacture is now over. Companies (and company profits) are no longer organised around making things but depend on the creation of rights. In the industry's own jargon, each piece of music represents ‘a basket of rights’; the company task is to exploit as many of these rights as possible, not just those realised when it is sold in recorded form to the public, but also those realised when it is broadcast on radio or television, used on a film, commercial or video soundtrack, and so on. Musical rights (copyrights, performing rights) are the basic pop commodity and to understand the music business in the 1980s we have to understand how these rights work. In this article, then, I begin and end with record companies' uses of copyright law and ideology to defend themselves against current technological and political threats to income, but I also want to ask questions about how the law itself defines music and determines the possibilities of musical ‘exploitation’. And this means putting contemporary arguments (for and against the blank tape levy, for example) in historical perspective.

An Advanced Computer-Assisted Sound Mixing System for Film and Video Post-Production

The Necam system provides a powerful tool in the dubbing theater for the rapid artistic building of film and video soundtracks. Attention to human engineering has resulted in the creation of a control system of great flexibility. The sound engineer can choose as little or as much computer assistance as he needs at any time, thus maximizing versatility in dubbing. With all its capabilities, this system enables the sound engineer to concentrate on the most critical creative aspects of his task, whether he is laying down effects, optimizing a critical dialogue balance, or creating the final music/dialogue/effects mix.