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.

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.

Single-Element and Competitive Metal Mobility Measured with Column Infiltration and Batch Tests

The distribution coefficient, K-d, is often used to quantify heavy metal mobility in soils. Batch sorption or column infiltration tests may be used to measure K-d. The latter are closer to natural soil conditions, but are difficult to conduct in clays. This difficulty can be overcome by using a laboratory centrifuge. An acceleration of 2600 gravities was applied to columns of London Clay, an Eocene clay sub-stratum, and Cu, Ni, and Zn mobility was measured in centrifuge infiltration tests, both as single elements and in dual competition. Single-element K-d values were also obtained from batch sorption tests, and the results from the two techniques were compared. It was found that K-d values obtained by batch tests vary considerably depending on the metal concentration, while infiltration tests provided a single K-d value for each metal. This was typically in the lower end of the range of the batch test K-d values. For both tests, the order of mobility was Ni > Zn > Cu. Metals became more mobile in competition than when in single-element systems: Ni K-d decreased 3.3 times and Zn K-d 3.4 times when they competed with Cu, while Cu decreased only 1.2 times when in competition with either Ni or Zn. Our study showed that competitive sorption between metals increases the mobility of those metals less strongly bound more than it increases the mobility of more strongly bound metals.