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.

Developmental coordination disorder in extremely low birth weight children at nine years

Developmental coordination disorder (DCD) is defined as an impairment in the development of motor coordination that interferes with academic achievement or activities of daily living (DSM-IV). DCD has been reported to affect 5% to 9% of children in the normal population. This study describes the prevalence of DCD in a cohort of extremely low birth weight children (ELBW, <or = l800 g) at 8.9 years of age, from which were excluded children with major impairments. Seventy-three children were included in the study group, along with 18 term-born, socially matched controls. Of the 73 ELBW children, 37 (51%) were classified as having DCD. ELBW children with DCD also had significantly lower Performance IQ (PIQ) scores and were more likely (43%) to have a learning difficulty in arithmetic than ELBW children who did not have DCD. This study found that DCD is a common problem in school-aged ELBW children.

Autobiographical memory specificity, depression, and trauma in bipolar disorder

Objectives. In a bipolar disorder (BD) sample, the present study investigated: (i) the prevalence of trauma; (ii) the specificity of autobiographical memory (AM); (iii) the influence of childhood trauma on AM specificity, current inter-episode depressive mood, and BD severity; (iv) if AM specificity moderates the influence of childhood trauma on current inter-episode depressive mood and BD severity.

Methods. Fifty-two participants were recruited from a geographically well-defined mental health service in Northern Ireland. The AM test, self-report measures of lifetime experience of trauma, childhood trauma, and depression were administered. Severity of BD was estimated utilizing a systematic tool for reviewing all available clinical data of participants.

Results. A high prevalence of trauma was found. A total of 94.2% (49/52) of participants reported experiencing a traumatic event in either childhood or adulthood. AM specificity was significantly lower than previous reports of such in major depression. However, whilst childhood trauma predicted current inter-episode depressive mood, childhood trauma was not predictive of BD severity or AM specificity. Moreover, the association between childhood trauma and depressed mood was not moderated by AM specificity.

Conclusions. The findings of this study suggest a relationship between early psychosocial adversity and current inter-episode depressive mood in BD. In addition, levels of overgeneral AM are similar to that reported for depression, but are unrelated to childhood trauma, current inter-episode depressive mood, or BD severity. Clinical implications include the importance of routine assessment of trauma in BD and the need for adjunctive evidenced-based psychological therapies.

Enquiring about traumatic experiences in bipolar disorder: A case note and self- report comparison

Objectives: This study examined: (i) the prevalence of lifetime trauma, childhood trauma and trauma related to civil unrest in a Bipolar Disorder sample, and (ii) the agreement between rates of disclosure of trauma in case notes and self-report questionnaires.

Methods: The case notes of sixty participants, recruited from a geographically well-defined mental health service in Northern Ireland, were examined for reports of experiences of lifetime, childhood and traumatic events related to civil conflict. The participants also completed self-report measures of trauma.

Results: Considerable differences were found between the prevalence of trauma as measured by self-report questionnaires and case notes reports. The prevalence of lifetime trauma as measured by the Trauma History Questionnaire was 61.7% (compared to case notes prevalence of 33.3%). The prevalence of moderate and severe levels of childhood trauma as measured by the Childhood Trauma Questionnaire was 65% (case notes 21.7%). Rates of trauma related to civil unrest were 35% (case notes 3.3%). Poor levels of agreement were found between all self-report trauma measures and case notes reports. Agreement on two categories of trauma (childhood emotional neglect and childhood physical neglect) reached statistical significance but kappa scores suggest this agreement was poor (kappa = .14. p<.05; kappa = .127, p<.05). © 2011 Elsevier B.V. All rights reserved.

Conclusions: It is probable that the increased rate of trauma disclosed in the self-report questionnaire arises because clinicians during initial assessment and subsequent treatment do not consistently enquire about trauma. The need for staff training is discussed. (C) 2011 Elsevier B.V. All rights reserved.

Asprich Peptides Are Occluded in Calcite and Permanently Disorder Biomineral Crystals

Macromolecules are a minority but important component of the minerals formed by living organisms, or biominerals. The role these macromolecules play at the early stages of biomineral formation, as well as their long-term and long-range effects on the mature biomineral, is poorly understood. A 42-amino acid peptide, asp2, was derived from the Asprich family of proteins. In this study we present X-ray absorption near-edge structure spectroscopy and X-ray photoelectron emission microscopy data from the asp2 peptide, the calcite (CaCO3) crystals, and the peptide + crystal composites. The results clearly show that asp2 is occluded in fully formed biomineral crystals and slightly but permanently disorders the crystal structure at short- and long-range distances.

On thin ice: surface order and disorder during pre-melting

The effect of temperature on the structure of the ice Ih (0001) surface is considered through a series of molecular dynamics simulations on an ice slab. At relatively low temperatures (200K) a small fraction of surface self-interstitials (i.e. admolecules) appear that are formed exclusively from molecules leaving the outermost bilayer. At higher temperatures (ca. 250 K), vacancies start to appear in the inner part of the outermost bilayer exposing the underlying bilayer and providing sites with a high concentration of the dangling hydrogen bonds. Around 250-260 K aggregates of molecules formed on top of the outermost bilayer from self-interstitials become more mobile and have diffusivities approaching that of liquid water. At similar to 270-280 K the inner bilayer of one surface noticeably destructures and it appears that at above 285 K both surfaces are melting. The observed disparity in the onset of melting between the two sides of the slab is rationalised by considering the relationship between surface energy and the spatial distribution of protons at the surface; thermodynamic stability is conferred on the surface by maximising separations between dangling protons at the crystal exterior. Local hotspots associated with a high dangling proton density are suggested to be susceptible to pre-melting and may be more efficient at trapping species at the external surface than regions with low concentrations of protons thus potentially helping ice particles to catalyse reactions. A preliminary conclusion of this work is that only about 10-20 K below the melting temperature of the particular water potential employed is major disruption of the crystalline lattice noted which could be interpreted as being "liquid", the thickness of this film being about a nanometre.

Interceptive skills in children aged 9-11 years, diagnosed with Autism Spectrum Disorder

Growing evidence suggests that significant motor problems are associated with a diagnosis of Autism Spectrum Disorders (ASD), particularly in catching tasks. Catching is a complex, dynamic skill that involves the ability to synchronise one's own movement to that of a moving target. To successfully complete the task, the participant must pick up and use perceptual information about the moving target to arrive at the catching place at the right time. This study looks at catching ability in children diagnosed with ASD (mean age 10.16 ± 0.9 years) and age-matched non-verbal (9.72 ± 0.79 years) and receptive language (9.51 ± 0.46) control groups. Participants were asked to "catch" a ball as it rolled down a fixed ramp. Two ramp heights provided two levels of task difficulty, whilst the sensory information (audio and visual) specifying ball arrival time was varied. Results showed children with ASD performed significantly worse than both the receptive language (p =.02) and non-verbal (p =.02) control groups in terms of total number of balls caught. A detailed analysis of the movement kinematics showed that difficulties with picking up and using the sensory information to guide the action may be the source of the problem. © 2013 Elsevier Ltd.

A Corpus-Based Approach to Speech Enhancement from Nonstationary Noise

Temporal dynamics and speaker characteristics are two important features of speech that distinguish speech from noise. In this paper, we propose a method to maximally extract these two features of speech for speech enhancement. We demonstrate that this can reduce the requirement for prior information about the noise, which can be difficult to estimate for fast-varying noise. Given noisy speech, the new approach estimates clean speech by recognizing long segments of the clean speech as whole units. In the recognition, clean speech sentences, taken from a speech corpus, are used as examples. Matching segments are identified between the noisy sentence and the corpus sentences. The estimate is formed by using the longest matching segments found in the corpus sentences. Longer speech segments as whole units contain more distinct dynamics and richer speaker characteristics, and can be identified more accurately from noise than shorter speech segments. Therefore, estimation based on the longest recognized segments increases the noise immunity and hence the estimation accuracy. The new approach consists of a statistical model to represent up to sentence-long temporal dynamics in the corpus speech, and an algorithm to identify the longest matching segments between the noisy sentence and the corpus sentences. The algorithm is made more robust to noise uncertainty by introducing missing-feature based noise compensation into the corpus sentences. Experiments have been conducted on the TIMIT database for speech enhancement from various types of nonstationary noise including song, music, and crosstalk speech. The new approach has shown improved performance over conventional enhancement algorithms in both objective and subjective evaluations.

Combining missing-feature theory, speech enhancement, and speaker-dependent/-independent modeling for speech separation

This paper considers the separation and recognition of overlapped speech sentences assuming single-channel observation. A system based on a combination of several different techniques is proposed. The system uses a missing-feature approach for improving crosstalk/noise robustness, a Wiener filter for speech enhancement, hidden Markov models for speech reconstruction, and speaker-dependent/-independent modeling for speaker and speech recognition. We develop the system on the Speech Separation Challenge database, involving a task of separating and recognizing two mixing sentences without assuming advanced knowledge about the identity of the speakers nor about the signal-to-noise ratio. The paper is an extended version of a previous conference paper submitted for the challenge.

Informational masking in young and elderly listeners for speech masked by simultaneous speech and noise

Three experiments measured the effects of age on informational masking of speech by competing speech. The experiments were designed to minimize the energetic contributions of the competing speech so that informational masking could be measured with no large corrections for energetic masking. Experiment 1 used a "speech-in-speech-in-noise" design, in which the competing speech was presented in noise at a signal-to-noise ratio (SNR) of -4 dB. This ensured that the noise primarily contributed the energetic masking but the competing speech contributed the informational masking. Equal amounts of informational masking (3 dB) were observed for young and elderly listeners, although less was found for hearing-impaired listeners. Experiment 2 tested a range of SNRs in this design and showed that informational masking increased with SNR up to about an SNR of -4 dB, but decreased thereafter. Experiment 3 further reduced the energetic contribution of the competing speech by filtering it into different frequency bands from the target speech. The elderly listeners again showed approximately the same amount of informational masking (4-5 dB), although some elderly listeners had particular difficulty understanding these stimuli in any condition. On the whole, these results suggest that young and elderly listeners were equally susceptible to informational masking. © 2009 Acoustical Society of America.

An analysis of the masking of speech by competing speech using self-report data (L)

Many of the items in the “Speech, Spatial, and Qualities of Hearing” scale questionnaire [S. Gatehouse and W. Noble, Int. J. Audiol.43, 85–99 (2004)] are concerned with speech understanding in a variety of backgrounds, both speech and nonspeech. To study if this self-report data reflected informational masking, previously collected data on 414 people were analyzed. The lowest scores (greatest difficulties) were found for the two items in which there were two speech targets, with successively higher scores for competing speech (six items), energetic masking (one item), and no masking (three items). The results suggest significant masking by competing speech in everyday listening situations.