Robust Audio-Visual Speech Recognition under Noisy Audio-Video Conditions

This paper presents the maximum weighted stream posterior (MWSP) model as a robust and efficient stream integration method for audio-visual speech recognition in environments, where the audio or video streams may be subjected to unknown and time-varying corruption. A significant advantage of MWSP is that it does not require any specific measurements of the signal in either stream to calculate appropriate stream weights during recognition, and as such it is modality-independent. This also means that MWSP complements and can be used alongside many of the other approaches that have been proposed in the literature for this problem. For evaluation we used the large XM2VTS database for speaker-independent audio-visual speech recognition. The extensive tests include both clean and corrupted utterances with corruption added in either/both the video and audio streams using a variety of types (e.g., MPEG-4 video compression) and levels of noise. The experiments show that this approach gives excellent performance in comparison to another well-known dynamic stream weighting approach and also compared to any fixed-weighted integration approach in both clean conditions or when noise is added to either stream. Furthermore, our experiments show that the MWSP approach dynamically selects suitable integration weights on a frame-by-frame basis according to the level of noise in the streams and also according to the naturally fluctuating relative reliability of the modalities even in clean conditions. The MWSP approach is shown to maintain robust recognition performance in all tested conditions, while requiring no prior knowledge about the type or level of noise.

Palaeoglacial and palaeoclimatic conditions in the NW Pacific, as revealed by a morphometric analysis of cirques upon the Kamchatka Peninsula

The distribution of glacial cirques upon the Kamchatka peninsula, Far Eastern Russia, is systematically mapped from satellite images and digital elevation model data. A total of 3,758 cirques are identified, 238 of which are occupied by active glaciers. The morphometry of the remaining 3,520 cirques is analysed. These cirques are found to show a very strong N bias in their azimuth (orientation), likely resulting from aspect-related variations in insolation. The strength of this N bias is considered to indicate that former glaciation upon the peninsula was often ‘marginal’, and mainly of cirque-type, with peaks extending little above regional equilibrium-line altitudes. This is supported by the fact that S and SE-facing cirques are the highest in the dataset, suggesting that glacier-cover was rarely sufficient to allow S and SE-facing glaciers to develop at low altitudes. The strength of these azimuth-related variations in cirque altitude is thought to reflect comparatively cloud-free conditions during former periods of glaciation. It is suggested that these characteristics, of marginal glaciation and comparatively cloud-free conditions, reflect the region’s former aridity, which was likely intensified at the global Last Glacial Maximum, and during earlier periods of ice advance, as a result of the development of negative pressure anomalies over the North Pacific (driven by the growth of the Laurentide Ice Sheet), combined with other factors, including an increase in the extent and duration of sea ice, a reduction in global sea levels, cooler sea surface temperatures, and the localised growth of mountain glaciers. There is published evidence to suggest extensive glaciation of the Kamchatka Peninsula at times during the Late Quaternary, yet the data presented here appears to suggest that such phases were comparatively short-lived, and that smaller cirque-type glaciers were generally more characteristic of the period.

Thermography-based virtual MPPT scheme for improving PV energy efficiency under partial shading conditions

This paper proposes a new thermography-based maximum power point tracking (MPPT) scheme to address photovoltaic (PV) partial shading faults. Solar power generation utilizes a large number of PV cells connected in series and in parallel in an array, and that are physically distributed across a large field. When a PV module is faulted or partial shading occurs, the PV system sees a nonuniform distribution of generated electrical power and thermal profile, and the generation of multiple maximum power points (MPPs). If left untreated, this reduces the overall power generation and severe faults may propagate, resulting in damage to the system. In this paper, a thermal camera is employed for fault detection and a new MPPT scheme is developed to alter the operating point to match an optimized MPP. Extensive data mining is conducted on the images from the thermal camera in order to locate global MPPs. Based on this, a virtual MPPT is set out to find the global MPP. This can reduce MPPT time and be used to calculate the MPP reference voltage. Finally, the proposed methodology is experimentally implemented and validated by tests on a 600-W PV array.