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.

Race, the senses, and the materials of writing practices

The paper is a critical argument foregrounding race, the senses, and the materials of literacy practices. The author argues that counter-colonial literacies in the contemporary times require openly acknowledgement of the influences of white imperialism and racism in dominant schooling practices. The first concern is narrow conceptions of literacy and schooling that follow a white racial script, and which function as a form of historical reproduction, control, and privilege. The second is the need to acknowledge the need to rediscover the sensory nature of literacy practices that is intrinsic to many cultures, and which is transformed in human interactions with new digital forms of textual production. The final argument is the need to attend to the materiality of literacy practices, including the meanings connected to the material ecology. This principle is particularly relevant to Indigenous culture and experience, but likewise, to all digital environments where the materials of literacy practices are continually shifting.

A pilot study investigating the efficacy of an imagery-based motivational intervention for smoking cessation

This pilot study evaluated the potential efficacy of an imagery-based intervention called Functional Imagery Training (FIT) as a therapeutic approach to smoking cessation. FIT showed promising results in reducing cigarette use, managing craving, and promoting abstinence among smokers when compared to a control condition, and may play a role in maintaining smokers' motivation to quit. This study was the first of its kind, and paves the way for future investigations into FIT as a smoking cessation intervention.

An exploration into younger and older pedestrians' risky behaviours at train level crossings

Background: Younger and older pedestrians are both overrepresented in train-pedestrian injury and fatality collision databases. However, scant research has attempted to determine the factors that influence level crossing behaviours for these high risk groups. Method: Five focus groups were undertaken with a total of 27 younger and 17 older pedestrian level crossing users (N = 44). Due to the lack of research in the area, a focus group methodology was implemented to gain a deeper exploratory understanding into the sample’s decision making processes through a pilot study. The three main areas of enquiry were identifying the: (a) primary reasons for unsafe behaviour; (b) factors that deter this behaviour and (c) proposed interventions to improve pedestrian safety at level crossings in the future. Results: Common themes to emerge from both groups regarding the origins of unsafe behaviours were: running late and a fatalistic perspective that some accidents are inevitable. However, younger pedestrians were more likely to report motivators to be: (a) non-perception of danger; (b) impulsive risk taking; and (c) inattention. In contrast, older pedestrians reported their decisions to cross are influenced by mobility issues and sensory salience. Conclusion: The findings indicate that a range of factors influence pedestrian crossing behaviours. This paper will further outline the major findings of the research in regards to intervention development and future research direction.

Manifestations of type 2 diabetes in corneal endothelial cell density, corneal thickness and intraocular pressure

We sought to evaluate central corneal thickness (CCT), corneal endothelial cell density (ECD) and intraocular pressure (IOP) in patients with type 2 diabetes mellitus (DM) and to associate potential differences with diabetes duration and treatment modality in a prospective, randomized study. We measured ECD, CCT and IOP of 125 patients with type 2 DM (mean age 57.1¡11.5 years) and compared them with 90 age-matched controls. Measured parameters were analyzed for association with diabetes duration and glucose control modalities (insulin injection or oral medication) while controlling for age. In the diabetic group, the mean ECD (2511¡252 cells/mm2), mean CCT (539.7¡33.6 mm) and mean IOP (18.3¡2.5 mmHg) varied significantly from those the control group [ECD: 2713¡132 cells/mm2 (P,0.0001), CCT: 525.0¡45.3 mm (P50.003) and IOP: 16.7¡1.8 mmHg (P,0.0001)]. ECD was significantly reduced by about 32 cell/mm2 for diabetics with duration of .10 years when compared with those with duration of ,10 years (P,0.05). CCT was thicker and IOP was higher for diabetics with duration of .10 years than those with duration of ,10 years (P.0.05). None of the measured parameters was significantly associated with diabetes duration and treatment modality (P.0.05). In conclusion, subjects with type 2 DM exhibit significant changes in ECD, IOP and CCT, which, however, are not correlated with disease duration or if the patients receive on insulin injection or oral medications.