Robust bimodal person identification using face and speech with limited training data and corruption of both modalities

This paper presents a novel method of audio-visual fusion for person identification where both the speech and facial modalities may be corrupted, and there is a lack of prior knowledge about the corruption. Furthermore, we assume there is a limited amount of training data for each modality (e.g., a short training speech segment and a single training facial image for each person). A new representation and a modified cosine similarity are introduced for combining and comparing bimodal features with limited training data as well as vastly differing data rates and feature sizes. Optimal feature selection and multicondition training are used to reduce the mismatch between training and testing, thereby making the system robust to unknown bimodal corruption. Experiments have been carried out on a bimodal data set created from the SPIDRE and AR databases with variable noise corruption of speech and occlusion in the face images. The new method has demonstrated improved recognition accuracy.

An iterative longest matching segment approach to speech enhancement with additive noise and channel distortion

This paper presents a new approach to speech enhancement from single-channel measurements involving both noise and channel distortion (i.e., convolutional noise), and demonstrates its applications for robust speech recognition and for improving noisy speech quality. The approach is based on finding longest matching segments (LMS) from a corpus of clean, wideband speech. The approach adds three novel developments to our previous LMS research. First, we address the problem of channel distortion as well as additive noise. Second, we present an improved method for modeling noise for speech estimation. Third, we present an iterative algorithm which updates the noise and channel estimates of the corpus data model. In experiments using speech recognition as a test with the Aurora 4 database, the use of our enhancement approach as a preprocessor for feature extraction significantly improved the performance of a baseline recognition system. In another comparison against conventional enhancement algorithms, both the PESQ and the segmental SNR ratings of the LMS algorithm were superior to the other methods for noisy speech enhancement.

Speech Enhancement from Additive Noise and Channel Distortion - a Corpus-Based Approach

This paper presents a new approach to single-channel speech enhancement involving both noise and channel distortion (i.e., convolutional noise). The approach is based on finding longest matching segments (LMS) from a corpus of clean, wideband speech. The approach adds three novel developments to our previous LMS research. First, we address the problem of channel distortion as well as additive noise. Second, we present an improved method for modeling noise. Third, we present an iterative algorithm for improved speech estimates. In experiments using speech recognition as a test with the Aurora 4 database, the use of our enhancement approach as a preprocessor for feature extraction significantly improved the performance of a baseline recognition system. In another comparison against conventional enhancement algorithms, both the PESQ and the segmental SNR ratings of the LMS algorithm were superior to the other methods for noisy speech enhancement. Index Terms: corpus-based speech model, longest matching segment, speech enhancement, speech recognition

Merit, Speech Disability and Discrimination

There is a substantial body of evidence – going back over decades – which indicates that the employment sphere is difficult for those who suffer a speech disability. To a large extent, I argue, this is due to the setting of merit in terms of orality and aesthetic. It also relates to the low perception of competence of the speech disabled. I argue that to be effective against discrimination the notion of merit and its assessment requires focus. ‘Merit’ as a concept in discrimination law has had its critics, yet it remains important to investigate it as social construct in order to help understand discrimination and how to counter this. For example, in this article I look at an instance where the resetting of what was viewed as ‘meritorious’ in judicial recruitment successfully improved the diversity in lower judicial posts.

Further, given the relative failure of the employment tribunal system to improve the general position of those who are disabled, I look to alternative methods of countering disability discrimination. The suggestion provided is that an enforced ombudsman type approach capable of dealing with what may be the core issue around employment discrimination (‘merit’) would provide a better mechanism for handling the general situation of disability discrimination than the tribunal system.

Incidence and significance of the JAK2 V617F mutation in patients with chronic myeloproliferative disorders

BACKGROUND: The chronic myeloproliferative disorders (MPD) are clonal haemopoietic stem cell disorders.

AIMS: The incidence of JAK2 V617F mutation was sought in a population of patients with MPD.

METHODS: The JAK2 V617 mutation status was determined in 79 patients with known MPD and 59 patients with features suggestive of MPD.

RESULTS: The mutation was found in patients with polycythaemia vera, essential thrombocythaemia, idiopathic myelofibrosis and in patients with other chronic myeloproliferative disorders. Eight JAK2 V617F positive cases were identified amongst those patients with features suggestive of MPD.

CONCLUSIONS: The incidence of the JAK2 V617F mutation in MPD patients is similar to that reported by other groups. The assay confirmed and refined the diagnosis of several patients with features indicative of MPD. We suggest screening for this mutation in all patients with known and suspected MPD as identification is valuable in classification and is a potential target for signal transduction therapy.

Wide Matching - An Approach to Improving Noise Robustness for Speech Enhancement

It is shown that under certain conditions it is possible to obtain a good speech estimate from noise without requiring noise estimation. We study an implementation of the theory, namely wide matching, for speech enhancement. The new approach performs sentence-wide joint speech segment estimation subject to maximum recognizability to gain noise robustness. Experiments have been conducted to evaluate the new approach with variable noises and SNRs from -5 dB to noise free. It is shown that the new approach, without any estimation of the noise, significantly outperformed conventional methods in the low SNR conditions while retaining comparable performance in the high SNR conditions. It is further suggested that the wide matching and deep learning approaches can be combined towards a highly robust and accurate speech estimator.

LNK mutations and myeloproliferative disorders

The lymphocyte adaptor protein (LNK) is one of a family of adaptor proteins involved cell signalling and control of B cell populations. It has a critical role in regulation of signalling in hematopoiesis. Lnk negatively regulates cytokine initiated cell signalling and it functions as a negative regulator of the mutant protein in myeloproliferative neoplasms JAK2V617F. A number of mutations in LNK have been described in a variety of myeloproliferative neoplasms some of which have been demonstrated to cause increased cellular proliferation. The majority of mutations occur in exon 2. In a small number of cases idiopathic erythrocytosis with subnormal erythropoietin levels LNK mutations have been found which may account for the clinical phenotype. Thus investigation for LNK mutations should be considered in the investigation of idiopathic erythrocytosis and perhaps other myeloproliferative neoplasms.

Evaluation of Restorative Dentistry Specialty Registrars’ Clinical Experience of Developmental Disorders: A Survey

Background

Specialty Registrars in Restorative Dentistry (StRs) should be competent in the independent restorative management of patients with developmental disorders including hypodontia and cleft lip/palate upon completion of their specialist training.1 Knowledge and management may be assessed via the Intercollegiate Specialty Fellowship Examination (ISFE) in Restorative Dentistry.2

Objective

The aim of this study was to collate and compare data on the training and experience of StRs in the management of patients with developmental disorders across different training units within the British Isles.

Methods

Questionnaires were distributed to all StRs attending the Annual General Meeting of the Specialty Registrars in Restorative Dentistry Group, Belfast, in October 2015. Participants were asked to rate their confidence and experience of assessing and planning treatment for patients with developmental disorders, construction of appropriate prostheses, and provision of dental implants. Respondents were also asked to record clinical supervision and didactic teaching at their unit, and to rate their confidence of passing a future ISFE station assessing knowledge of developmental disorders.

Results

Responses were obtained from 32 StRs (n=32) training within all five countries of the British Isles. The majority of respondents were based in England (72%) with three in Wales, and two in each of Scotland, Northern Ireland, and the Republic of Ireland. Approximately one third of respondents (34%) were in the final years of training (years 4-6). Almost half of the StRs reported that they were not confident of independently assessing (44%) new patients with a developmental disorder, with larger numbers (72%) indicating a lack of confidence in treatment planning. Six respondents rated their experience of treating obturator patients as ‘poor’ or ‘very poor’. The majority (56%) rated their experience of implant provision in these cases as ‘good’ or ‘excellent’ with three-quarters (75%) rating clinical supervision at their unit as ‘good’ or ‘excellent’. Less than half (41%) rated the didactic teaching at their unit as ‘good’ or ‘excellent’, and only 8 StRs indicated that they were confident of passing an ISFE station focused on developmental disorders.

Conclusion

Experience and training regarding patients with developmental disorders is inconsistent for StRs across the British Isles with a number of trainees reporting a lack of clinical exposure.