Emotional speech: towards a new generation of databases

Research on speech and emotion is moving from a period of exploratory research into one where there is a prospect of substantial applications, notably in human-computer interaction. Progress in the area relies heavily on the development of appropriate databases. This paper addresses the issues that need to be considered in developing databases of emotional speech, and shows how the challenge of developing apropriate databases is being addressed in three major recent projects - the Belfast project, the Reading-Leeds project and the CREST-ESP project. From these and other studies the paper draws together the tools and methods that have been developed, addresses the problems that arise and indicates the future directions for the development of emotional speech databases.

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.

Hidden Gems: systematically searching electronic databases for research publications for social work and social care.

Context: Electronic bibliographic databases are a key source for professional publications about social work and community care more generally. This article describes and evaluates a method of identifying relevant articles as part of a systematic review of research evidence. Decision making about institutional and home care services for older people is used as an example. Method: Four databases (Social Science Citation Index, Medline, CINAHL, and Caredata) that abstract publications relevant to health and social services were searched systematically to identify relevant research studies. The items retrieved were appraised independently using a standard form developed for the purpose. The searches were compared in terms of sensitivity, precision, overlap between databases, and inter-rater reliability. Results: The search retrieved 525 articles, of which 276 were relevant. The four databases retrieved 55%, 41%, 19%, and 1% of the relevant articles respectively, achieving these sensitivities with precision levels of 54%, 48%, 84% and 94%. The databases retrieved 116, 73, 24 and 15 unique relevant articles respectively, showing the need to use a range of databases. Discussion: A general approach to creating a search to retrieve relevant research has been developed. The development of an international, indexed database dedicated to literature relevant to social services is a priority to enable progress in evidence-based policy and practice in social work. Editors and researchers should consider using structured abstracts in order to improve the retrieval and dissemination of research.

Speech Recognition with unknown partial feature corruption - a review of the union model

This paper provides a summary of our studies on robust speech recognition based on a new statistical approach – the probabilistic union model. We consider speech recognition given that part of the acoustic features may be corrupted by noise. The union model is a method for basing the recognition on the clean part of the features, thereby reducing the effect of the noise on recognition. To this end, the union model is similar to the missing feature method. However, the two methods achieve this end through different routes. The missing feature method usually requires the identity of the noisy data for noise removal, while the union model combines the local features based on the union of random events, to reduce the dependence of the model on information about the noise. We previously investigated the applications of the union model to speech recognition involving unknown partial corruption in frequency band, in time duration, and in feature streams. Additionally, a combination of the union model with conventional noise-reduction techniques was studied, as a means of dealing with a mixture of known or trainable noise and unknown unexpected noise. In this paper, a unified review, in the context of dealing with unknown partial feature corruption, is provided into each of these applications, giving the appropriate theory and implementation algorithms, along with an experimental evaluation.