Automatic Audio Segmentation Using the Generalized Likelihood Ratio

This paper presents a novel technique for segmenting an audio stream into homogeneous regions according to speaker identities, background noise, music, environmental and channel conditions. Audio segmentation is useful in audio diarization systems, which aim to annotate an input audio stream with information that attributes temporal regions of the audio into their specific sources. The segmentation method introduced in this paper is performed using the Generalized Likelihood Ratio (GLR), computed between two adjacent sliding windows over preprocessed speech. This approach is inspired by the popular segmentation method proposed by the pioneering work of Chen and Gopalakrishnan, using the Bayesian Information Criterion (BIC) with an expanding search window. This paper will aim to identify and address the shortcomings associated with such an approach. The result obtained by the proposed segmentation strategy is evaluated on the 2002 Rich Transcription (RT-02) Evaluation dataset, and a miss rate of 19.47% and a false alarm rate of 16.94% is achieved at the optimal threshold.

Factors associated with suboptimal adherence to antiretroviral therapy in Viet Nam: A cross-sectional study using audio computer-assisted self-interview (ACASI)

Background: Optimal adherence to antiretroviral therapy (ART) is necessary for people living with HIV/AIDS (PLHIV). There have been relatively few systematic analyses of factors that promote or inhibit adherence to antiretroviral therapy among PLHIV in Asia. This study assessed ART adherence and examined factors associated with suboptimal adherence in northern Viet Nam. Methods: Data from 615 PLHIV on ART in two urban and three rural outpatient clinics were collected by medical record extraction and from patient interviews using audio computer-assisted self-interview (ACASI). Results: The prevalence of suboptimal adherence was estimated to be 24.9% via a visual analogue scale (VAS) of past-month dose-missing and 29.1% using a modified Adult AIDS Clinical Trial Group scale for on-time dose-taking in the past 4 days. Factors significantly associated with the more conservative VAS score were: depression (p < 0.001), side-effect experiences (p < 0.001), heavy alcohol use (p = 0.001), chance health locus of control (p = 0.003), low perceived quality of information from care providers (p = 0.04) and low social connectedness (p = 0.03). Illicit drug use alone was not significantly associated with suboptimal adherence, but interacted with heavy alcohol use to reduce adherence (p < 0.001). Conclusions: This is the largest survey of ART adherence yet reported from Asia and the first in a developing country to use the ACASI method in this context. The evidence strongly indicates that ART services in Viet Nam should include screening and treatment for depression, linkage with alcohol and/or drug dependence treatment, and counselling to address the belief that chance or luck determines health outcomes.

A novel representation of bioacoustic events for content-based search in field audio data

Bioacoustic data can provide an important base for environmental monitoring. To explore a large amount of field recordings collected, an automated similarity search algorithm is presented in this paper. A region of an audio defined by frequency and time bounds is provided by a user; the content of the region is used to construct a query. In the retrieving process, our algorithm will automatically scan through recordings to search for similar regions. In detail, we present a feature extraction approach based on the visual content of vocalisations – in this case ridges, and develop a generic regional representation of vocalisations for indexing. Our feature extraction method works best for bird vocalisations showing ridge characteristics. The regional representation method allows the content of an arbitrary region of a continuous recording to be described in a compressed format.

The use of acoustic indices to determine avian species richness in audio-recordings of the environment

Interpreting acoustic recordings of the natural environment is an increasingly important technique for ecologists wishing to monitor terrestrial ecosystems. Technological advances make it possible to accumulate many more recordings than can be listened to or interpreted, thereby necessitating automated assistance to identify elements in the soundscape. In this paper we examine the problem of estimating avian species richness by sampling from very long acoustic recordings. We work with data recorded under natural conditions and with all the attendant problems of undefined and unconstrained acoustic content (such as wind, rain, traffic, etc.) which can mask content of interest (in our case, bird calls). We describe 14 acoustic indices calculated at one minute resolution for the duration of a 24 hour recording. An acoustic index is a statistic that summarizes some aspect of the structure and distribution of acoustic energy and information in a recording. Some of the indices we calculate are standard (e.g. signal-to-noise ratio), some have been reported useful for the detection of bioacoustic activity (e.g. temporal and spectral entropies) and some are directed to avian sources (spectral persistence of whistles). We rank the one minute segments of a 24 hour recording in descending order according to an "acoustic richness" score which is derived from a single index or a weighted combination of two or more. We describe combinations of indices which lead to more efficient estimates of species richness than random sampling from the same recording, where efficiency is defined as total species identified for given listening effort. Using random sampling, we achieve a 53% increase in species recognized over traditional field surveys and an increase of 87% using combinations of indices to direct the sampling. We also demonstrate how combinations of the same indices can be used to detect long duration acoustic events (such as heavy rain and cicada chorus) and to construct long duration (24 h) spectrograms.

Managing and analysing big audio data for environmental monitoring

Environmental monitoring is becoming critical as human activity and climate change place greater pressures on biodiversity, leading to an increasing need for data to make informed decisions. Acoustic sensors can help collect data across large areas for extended periods making them attractive in environmental monitoring. However, managing and analysing large volumes of environmental acoustic data is a great challenge and is consequently hindering the effective utilization of the big dataset collected. This paper presents an overview of our current techniques for collecting, storing and analysing large volumes of acoustic data efficiently, accurately, and cost-effectively.

Competition Hertz : the culture and practice of car audio competitions

The present paper explores extreme car audio systems and the culture and practices that surround car audio competitions. I begin by examining whether, and how, car audio can be thought of as a 'music scene' and in what ways the culture and practice of car audio may fit within post-subcultural discourses. Following this, I offer a description of car audio competitions, revealing some of the practices that define this aspect of car audio scenes. In particular, I concentrate on sound pressure level (SPL) competitions and some of the interesting aspects of the SPL scene. Finally, I briefly examine how the powerful effects (and affects) of bass frequencies are an important part of the attraction of loud car audio systems and how car audio systems contribute to the territorializing of urban spaces.

Enhancing learning in large undergraduate classes using custom made audio-visual cases

This is an exploratory study into the effective use of embedding custom made audiovisual case studies (AVCS) in enhancing the student’s learning experience. This paper describes a project that used AVCS for a large divergent cohort of undergraduate students, enrolled in an International Business course. The study makes a number of key contributions to advancing learning and teaching within the discipline. AVCS provide first hand reporting of the case material, where the students have the ability to improve their understanding from both verbal and nonverbal cues. The paper demonstrates how AVCS can be embedded in a student-centred teaching approach to capture the students’ interest and to enhance a deep approach to learning by providing real-world authentic experience.

Audio signalling as a backup communication channel for multi-robot systems

This paper presents a low-bandwidth multi-robot communication system designed to serve as a backup communication channel in the event a robot suffers a network device fault. While much research has been performed in the area of distributing network communication across multiple robots within a system, individual robots are still susceptible to hardware failure. In the past, such robots would simply be removed from service, and their tasks re-allocated to other members. However, there are times when a faulty robot might be crucial to a mission, or be able to contribute in a less communication intensive area. By allowing robots to encode and decode messages into unique sequences of DTMF symbols, called words, our system is able to facilitate continued low-bandwidth communication between robots without access to network communication. Our results have shown that the system is capable of permitting robots to negotiate task initiation and termination, and is flexible enough to permit a pair of robots to perform a simple turn taking task.

Driving simulator evaluation of the failure of an audio in-vehicle warning for railway level crossings

It is impracticable to upgrade the 18,900 Australian passive crossings as such crossings are often located in remote areas, where power is lacking and with low road and rail traffic. The rail industry is interested in developing innovative in-vehicle technology interventions to warn motorists of approaching trains directly in their vehicles. The objective of this study was therefore to evaluate the benefits of the introduction of such technology. We evaluated the changes in driver performance once the technology is enabled and functioning correctly, as well as the effects of an unsafe failure of the technology? We conducted a driving simulator study where participants (N=15) were familiarised with an in-vehicle audio warning for an extended period. After being familiarised with the system, the technology started failing, and we tested the reaction of drivers with a train approaching. This study has shown that with the traditional passive crossings with RX2 signage, the majority of drivers complied (70%) and looked for trains on both sides of the rail track. With the introduction of the in-vehicle audio message, drivers did not approach crossings faster, did not reduce their safety margins and did not reduce their gaze towards the rail tracks. However participants’ compliance at the stop sign decreased by 16.5% with the technology installed in the vehicle. The effect of the failure of the in-vehicle audio warning technology showed that most participants did not experience difficulties in detecting the approaching train even though they did not receive any warning message. This showed that participants were still actively looking for trains with the system in their vehicle. However, two participants did not stop and one decided to beat the train when they did not receive the audio message, suggesting potential human factors issues to be considered with such technology.

Complete-linkage clustering for voice activity detection in audio and visual speech

We propose a novel technique for conducting robust voice activity detection (VAD) in high-noise recordings. We use Gaussian mixture modeling (GMM) to train two generic models; speech and non-speech. We then score smaller segments of a given (unseen) recording against each of these GMMs to obtain two respective likelihood scores for each segment. These scores are used to compute a dissimilarity measure between pairs of segments and to carry out complete-linkage clustering of the segments into speech and non-speech clusters. We compare the accuracy of our method against state-of-the-art and standardised VAD techniques to demonstrate an absolute improvement of 15% in half-total error rate (HTER) over the best performing baseline system and across the QUT-NOISE-TIMIT database. We then apply our approach to the Audio-Visual Database of American English (AVDBAE) to demonstrate the performance of our algorithm in using visual, audio-visual or a proposed fusion of these features.

Acoustic adaptation in cross database audio visual SHMM training for phonetic spoken term detection

Visual information in the form of lip movements of the speaker has been shown to improve the performance of speech recognition and search applications. In our previous work, we proposed cross database training of synchronous hidden Markov models (SHMMs) to make use of external large and publicly available audio databases in addition to the relatively small given audio visual database. In this work, the cross database training approach is improved by performing an additional audio adaptation step, which enables audio visual SHMMs to benefit from audio observations of the external audio models before adding visual modality to them. The proposed approach outperforms the baseline cross database training approach in clean and noisy environments in terms of phone recognition accuracy as well as spoken term detection (STD) accuracy.

Cross database training of audio-visual hidden Markov models for phone recognition

Speech recognition can be improved by using visual information in the form of lip movements of the speaker in addition to audio information. To date, state-of-the-art techniques for audio-visual speech recognition continue to use audio and visual data of the same database for training their models. In this paper, we present a new approach to make use of one modality of an external dataset in addition to a given audio-visual dataset. By so doing, it is possible to create more powerful models from other extensive audio-only databases and adapt them on our comparatively smaller multi-stream databases. Results show that the presented approach outperforms the widely adopted synchronous hidden Markov models (HMM) trained jointly on audio and visual data of a given audio-visual database for phone recognition by 29% relative. It also outperforms the external audio models trained on extensive external audio datasets and also internal audio models by 5.5% and 46% relative respectively. We also show that the proposed approach is beneficial in noisy environments where the audio source is affected by the environmental noise.

Similarity-based birdcall retrieval from environmental audio

Automated digital recordings are useful for large-scale temporal and spatial environmental monitoring. An important research effort has been the automated classification of calling bird species. In this paper we examine a related task, retrieval of birdcalls from a database of audio recordings, similar to a user supplied query call. Such a retrieval task can sometimes be more useful than an automated classifier. We compare three approaches to similarity-based birdcall retrieval using spectral ridge features and two kinds of gradient features, structure tensor and the histogram of oriented gradients. The retrieval accuracy of our spectral ridge method is 94% compared to 82% for the structure tensor method and 90% for the histogram of gradients method. Additionally, this approach potentially offers a more compact representation and is more computationally efficient.

The navigation and visualisation of environmental audio using zooming spectrograms

Acoustic recordings play an increasingly important role in monitoring terrestrial and aquatic environments. However, rapid advances in technology make it possible to accumulate thousands of hours of recordings, more than ecologists can ever listen to. Our approach to this big-data challenge is to visualize the content of long-duration audio recordings on multiple scales, from minutes, hours, days to years. The visualization should facilitate navigation and yield ecologically meaningful information prior to listening to the audio. To construct images, we calculate acoustic indices, statistics that describe the distribution of acoustic energy and reflect content of ecological interest. We combine various indices to produce false-color spectrogram images that reveal acoustic content and facilitate navigation. The technical challenge we investigate in this work is how to navigate recordings that are days or even months in duration. We introduce a method of zooming through multiple temporal scales, analogous to Google Maps. However, the “landscape” to be navigated is not geographical and not therefore intrinsically visual, but rather a graphical representation of the underlying audio. We describe solutions to navigating spectrograms that range over three orders of magnitude of temporal scale. We make three sets of observations: 1. We determine that at least ten intermediate scale steps are required to zoom over three orders of magnitude of temporal scale; 2. We determine that three different visual representations are required to cover the range of temporal scales; 3. We present a solution to the problem of maintaining visual continuity when stepping between different visual representations. Finally, we demonstrate the utility of the approach with four case studies.