Analysis of environmental sounds as indexical signs in film

In this paper, we investigate the problem of classifying a subset of environmental sounds in movie audio tracks that indicate specific indexical semiotic use. These environmental sounds are used to signify and enhance events occurring in film scenes. We propose a classification system for detecting the presence of violence and car chase scenes in film by classifying ten various environmental sounds that form the constituent audio events of these scenes using a number of old and new audio features. Experiments with our classification system on pure test sounds resulted in a correct event classification rate of 88.9%. We also present the results of the classifier on the mixed audio tracks of several scenes taken from The Mummy and Lethal Weapon 2. The classification of sound events is the first step towards determining the presence of the complex sound scenes within film audio and describing the thematic content of the scenes.

Horror film genre typing and scene labeling via audio analysis

We examine localised sound energy patterns, or events, that we associate with high level affect experienced with films. The study of sound energy events in conjunction with their intended affect enable the analysis of film at a higher conceptual level, such as genre. The various affect/emotional responses we investigate in this paper are brought about by well established patterns of sound energy dynamics employed in audio tracks of horror films. This allows the examination of the thematic content of the films in relation to horror elements. We analyse the frequency of sound energy and affect events at a film level as well as at a scene level, and propose measures indicative of the film genre and scene content. Using 4 horror, and 2 non-horror movies as experimental data we establish a correlation between the sound energy event types and horrific thematic content within film, thus enabling an automated mechanism for genre typing and scene content labeling in film.

Video genre categorization using audio wavelet coefficients

In this paper, we investigate the use of a wavelet transform-based analysis of audio tracks accompanying videos for the problem of automatic program genre detection. We compare the classification performance based on wavelet-based audio features to that using conventional features derived from Fourier and time analysis for the task of discriminating TV programs such as news, commercials, music shows, concerts, motor racing games, and animated cartoons. Three different classifiers namely the Decision Trees, SVMs, and k-Nearest Neighbours are studied to analyse the reliability of the performance of our wavelet features based approach. Further, we investigate the issue of an appropriate duration of an audio clip to be analyzed for this automatic genre determination. Our experimental results show that features derived from the wavelet transform of the audio signal can very well separate the six video genres studied. It is also found that there is no significant difference in performance with varying audio clip durations across the classifiers.

Affect computing in film through sound energy dynamics

We develop an algorithm for the detection and classification of affective sound events underscored by specific patterns of sound energy dynamics. We relate the portrayal of these events to proposed high level affect or emotional coloring of the events. In this paper, four possible characteristic sound energy events are identified that convey well established meanings through their dynamics to portray and deliver certain affect, sentiment related to the horror film genre. Our algorithm is developed with the ultimate aim of automatically structuring sections of films that contain distinct shades of emotion related to horror themes for nonlinear media access and navigation. An average of 82% of the energy events, obtained from the analysis of the audio tracks of sections of four sample films corresponded correctly to the proposed affect. While the discrimination between certain sound energy event types was low, the algorithm correctly detected 71% of the occurrences of the sound energy events within audio tracks of the films analyzed, and thus forms a useful basis for determining affective scenes characteristic of horror in movies.

Detecting indexical signs in film audio for scene interpretation

In this paper, we study the sound tracks in films and their indexical semiotic usage by developing a classification system that detects complex sound scenes and their constituent sound events in cinema. We investigate two main issues in this paper: Determination of what constitutes the presence of a high level sound scene and inferences about the thematic content of the scene that can be drawn from this presence, and classification of environmental sounds in the audio track of the scene, to assist in the automatic detection of the high level scene. Experiments with our classification system on pure sounds resulted in a correct event classification rate of 88.9%. When the audio content of a number of film scenes was examined, though a lower accuracy resulted with sound event detection due to the presence of mixed sounds, the film audio samples were generally classified with the correct high-level sound scene label, enabling correct inferences about the story content of the scenes.

Genre, gender and interpretation of movie trailers an exploratory study

Commercial movies cost tens of millions to make. Because they are now released on thousands of screens simultaneously, movie trailers are a major and necessary method of intensively promoting movies before they disappear from cinemas forever. Yet there is a paucity of research about how potential audiences react to these trailers. This study aimed at exploring consumers’ interpretations of movie trailers. Nineteen in-depth interviews were the means of data collection, using nine trailers for yet to be released movies from the romance/drama, action, comedy and thriller categories. Genre provided a focus for exploring consumers’ interpretations of movie trailers. Evaluative judgments of movies came first as a result of the value of genre to the consumer and then as a result of content which conveyed the movie would be involving relative to past movie experiences. Interpretations about the target audience for a movie were also influenced by assumptions that genre preferences differ according to gender. The findings pose implications for the construction of movie trailers.

Multi-level semantic analysis for sports video

There has been a huge increase in the utilization of video as one of the most preferred type of media due to its content richness for many significant applications including sports. To sustain an ongoing rapid growth of sports video, there is an emerging demand for a sophisticated content-based indexing system. Users recall video contents in a high-level abstraction while video is generally stored as an arbitrary sequence of audio-visual tracks. To bridge this gap, this paper will demonstrate the use of domain knowledge and characteristics to design the extraction of high-level concepts directly from audio-visual features. In particular, we propose a multi-level semantic analysis framework to optimize the sharing of domain characteristics.

Implementing an online audio lecture streaming facility

This paper describes our experiences in implementing an audio lecture streaming facility for Deakin University. For many years Deakin students have benefited from some of the most comprehensive printed study notes of any university in Australia. In 2002, portable digital audio recorders were utilised by academic staff to capture lecture presentations in order to supplement existing unit learning materials and teaching delivery methods. Audio recordings were processed to enable streamed access via the web browser interface using QuickTime. A trial of incorporating PowerPoint presentations was conducted on a limited basis. 68 undergraduate and postgraduate units implemented lecture streaming. This represented over1700 lecture recordings and 20000 audio streams. Evaluation findings indicate that students find this facility highly valuable to their studies and regularly access the audio recordings throughout semester. Benefits include; access to lecture presentations for off-campus enrolled students, the ability to revisit lecture presentations, and the ability to study at a place and time of convenience. Future enhancement to the audio lecture streaming may include implementing a hard-wired audio capture system into lecture theatres and providing for a more rapid turn around of audio processing.

Cinema of (coming) attractions : Bruce Conner's a movie and documentary display

Bruce Conner's film 'Movie' (1958) constructs an argument concerning popular media and history within and through a radical juxtaposition of images to release new and productive meanings. It also comments on the media's representation of history as violence and analyses the consequences of aggression and violence.

Rote movie

"On the voice over de Bruyn places himself behind the wheel of a car, an appropriate metaphor for his expatriate driven reflections on his feelings of exile, distance and loneliness. Necessarily unintelligent memories highlight habitual subjectivity of "walking through a landscape alone", "gypsy", "victim". Images of roadsigns, cars, billboards, the passing landscape; elegantly simple rotoscope (by rote?) drawings, recopied and texturally manipulated filmic images; the inevitability of the repetition of leader. A tired, yearning, moving film." http://www.innersense.com.au/mif/debruyn_films.html

Analysing audio-recorded data : using computer software applications

Conventional methods of qualitative data analysis require transcription of audio-recorded data prior to conduct of the coding and analysis process. In this paper Alison Hutchinson describes and illustrates an innovative method of data analysis that comprises the use of audio-editing software to save selected audio bytes from digital audio recordings of meetings. The use of a database to code and manage the linked audio files and generate detailed and summary reports, including reporting of code frequencies according to participant code and/or meeting, is also highlighted. The advantage of using this approach in the analysis of audio-recorded data is that the process may be undertaken in the medium in which the data were collected. Though time-consuming, this process negates the need for expensive and time intensive transcription of recorded data.

Tracks

The artwork is intended to celebrate the rich cultural heritage of North Terrace and by extension, the many layered cultural facets of South Australia. It is called ‘Tracks’ because the stories are presented as moving tracks of electronic text in vertical columns, in an LED(lighting omitting diode) medium. It is also called ‘Tracks’ because the siting of the LED pillars is determined by a ‘variable grid’ ground pattern which forms a significant feature of the new landscape design. It celebrates the cultural heritage of North Terrace through the composition of four text gathering histories, anecdotes, facts and aspirations under the four headings of air, water, fire and earth. These stories are presented to the public as four colour differentiated continuous streams or tracks of electronic text in four columns placed on the northern side of North Terrace.

In the tracks of Blinky Bill : How Sam the koala led news journalists into an Australian literary tradition

The world was captivated when footage of a badly burnt koala taking water from a Victorian Country Fire Authority volunteer was taken with a mobile phone and broadcast to the world on YouTube in February 2009. When the story of ‘Sam the Koala’ was subsequently adopted by traditional broadcast and print media, recombinant themes were used to construct her story – from heroism, patriotism, villain v victim - even romance was incorporated to entertain and create audience appeal. This paper explores how ‘Sam the Koala’ became a defining news story in the coverage of Victoria’s Black Saturday bushfires and examines the power of narrative when cross pollination occurs between new and traditional media in the production of news. It is argued that Sam’s story is evidence of journalists adopting new approaches to storytelling in a bid to retain their legitimacy as the authoritative voice of news and information in an increasingly technologically driven society.

A novel pseudonoise sequence for time-spread echo based audio watermarking

This paper deals with the problem of digital audio watermarking using echo hiding. Compared to many other methods for audio watermarking, echo hiding techniques exhibit advantages in terms of relatively simple encoding and decoding, and robustness against common attacks. The low security issue existing in most echo hiding techniques is overcome in the timespread echo method by using pseudonoise (PN) sequence as a secret key. In this paper, we propose a novel sequence, in conjunction with a new decoding function, to improve the imperceptibility and the robustness of time-spread echo based audio watermarking. Theoretical analysis and simulation examples illustrate the effectiveness of the proposed sequence and decoding function.

Lunchroom to boardroom : an audio digitization project

The University of Queensland Cybrary in partnership with the Distributed Systems Technology Centre (DSTC), has created a searchable, web based digital oral history resource, based on a collection of stories of women involved in the Queensland Labor movement. A Trades and Labour Council of Queensland oral history collection was used to develop a framework for retrieval of audio materials on the web. A system for linking digitized media files to indexes created from transcripts (Meggie) has been developed. This allows the media file itself to be searched via key words. A trial was conducted and work is now proceeding on completing the collection. The final product will be made available via the Library's web site. The process followed, the choices made, the problems overcome, and the results achieved, will be outlined.