Adaptive speech enhancement with varying noise backgrounds

We present a new approach for speech enhancement in the presence of non-stationary and rapidly changing background noise. A distributed microphone system is used to capture the acoustic characteristics of the environment. The input of each microphone is then classified either as speech or one of the predetermined noise types. Further enhancement of speech in respective microphones is carried out using a modified spectral subtraction algorithm that incorporates multiple noise models to quickly adapt to rapid background noise changes. Tests on real world speech captured under diverse conditions demonstrate the effectiveness of this method.

Microphone identification using one-class classification approach

Rapid growth of technical developments has created huge challenges for microphone forensics - a subcategory of audio forensic science, because of the availability of numerous digital recording devices and massive amount of recording data. Demand for fast and efficient methods to assure integrity and authenticity of information is becoming more and more important in criminal investigation nowadays. Machine learning has emerged as an important technique to support audio analysis processes of microphone forensic practitioners. However, its application to real life situations using supervised learning is still facing great challenges due to expensiveness in collecting data and updating system. In this paper, we introduce a new machine learning approach which is called One-class Classification (OCC) to be applied to microphone forensics; we demonstrate its capability on a corpus of audio samples collected from several microphones. Research results and analysis indicate that OCC has the potential to benefit microphone forensic practitioners in developing new tools and techniques for effective and efficient analysis.

Identifying microphone from noisy recordings by using representative instance one class-classification approach

Rapid growth of technical developments has created huge challenges for microphone forensics - a sub-category of audio forensic science, because of the availability of numerous digital recording devices and massive amount of recording data. Demand for fast and efficient methods to assure integrity and authenticity of information is becoming more and more important in criminal investigation nowadays. Machine learning has emerged as an important technique to support audio analysis processes of microphone forensic practitioners. However, its application to real life situations using supervised learning is still facing great challenges due to expensiveness in collecting data and updating system. In this paper, we introduce a new machine learning approach which is called One-class Classification (OCC) to be applied to microphone forensics; we demonstrate its capability on a corpus of audio samples collected from several microphones. In addition, we propose a representative instance classification framework (RICF) that can effectively improve performance of OCC algorithms for recording signal with noise. Experiment results and analysis indicate that OCC has the potential to benefit microphone forensic practitioners in developing new tools and techniques for effective and efficient analysis.

Vocal communication at the nest between mates in wild zebra finches : a private vocal duet?

Bird vocal duets are joint displays where two individuals, generally a mated pair, produce temporally coordinated vocalizations. Duets may contribute to pair bond maintenance, mate guarding or collaborative defence of resources. The degree of coordination between mates and the variety of vocalizations, however, vary considerably. Although only 3–4.3% of bird species have been reported to duet, this may be because studies have generally focused on conspicuous duets, and more private forms of duet might have been overlooked. We investigated private vocal communication between mates in wild zebra finches, Taeniopygia guttata, a gregarious Australian songbird that forms life-long pair bonds. The partners are inseparable unless nest building, incubating or brooding. Using microphones inside nestboxes, we monitored interactive communication between partners at the nest and its variation during different stages of breeding. After periods of separation, partners performed coordinated mutual vocal displays involving specific soft vocal elements that fulfilled all the criteria used to define duets. In addition, using playback experiments, we obtained preliminary results suggesting that these soft calls could allow mate recognition. Thus, we propose that mutual displays at the nest in zebra finches represent private vocal duets and may function to mediate pair bond maintenance.

Balancing risk? First year performing arts students’ experience of a community arts event

This study examines participants’ responses to first year students’ street performances as a non-placement work-integrated learning (WIL) activity over a two year period. The purpose of the study was to determine: (1) community perception, (2) continuous improvement, and (3) future needs. Data was collected through surveying participants’ post-viewing of the street performances, students’ reflective notes, and a recorded focus group interview. The findings indicated that audience members require additional assistance to value the students’ street performances. The results revealed that students require more guidance around researching the sites of practice, understanding group work dynamics, relaxation methods, intra- and interpersonal skill development, conflict resolution and how to effectively build community relations with the local government Council. From the findings, specific recommendations for continual improvement are made. These include offering an explanation of the street performances’ historical and aesthetic connections to the building sites for audience members, affording battery operated body-microphones and light rostrum for improved sight lines, delivering group dynamics information and arranging opportunities for students to engage more effectively with the Council. While the recommendations in this study are intended to advance the field of research that evaluates non-placement WIL performing arts curriculum in higher education, the findings are relevant to any group-based performance activity in learning and teaching.

An audio signal based model for condition monitoring of sheet metal stamping process

Tool condition monitoring is an important factor in ensuring manufacturing efficiency and product quality. Audio signal based methods are a promising technique for condition monitoring. However, the influence of interfering signals and background noise has hindered the use of this technique in production sites. Blind signal separation (BSS) has the potential to solve this problem by recovering the signal of interest out of the observed mixtures, given that the knowledge about the BSS model is available. In this paper, we discuss the development of the BSS model for sheet metal stamping with a mechanical press system, so that the BSS techniques based on this model can be developed in future. This involves conducting a set of specially designed machine operations and developing a novel signal extraction technique. Also, the link between stamping process conditions and the extracted audio signal associated with stamping was successfully demonstrated by conducting a series of trials with different lubrication conditions and levels of tool wear.