Efficient decoding with generative score-spaces using the expectation semiring

State-of-the-art speech recognisers are usually based on hidden Markov models (HMMs). They model a hidden symbol sequence with a Markov process, with the observations independent given that sequence. These assumptions yield efficient algorithms, but limit the power of the model. An alternative model that allows a wide range of features, including word- and phone-level features, is a log-linear model. To handle, for example, word-level variable-length features, the original feature vectors must be segmented into words. Thus, decoding must find the optimal combination of segmentation of the utterance into words and word sequence. Features must therefore be extracted for each possible segment of audio. For many types of features, this becomes slow. In this paper, long-span features are derived from the likelihoods of word HMMs. Derivatives of the log-likelihoods, which break the Markov assumption, are appended. Previously, decoding with this model took cubic time in the length of the sequence, and longer for higher-order derivatives. This paper shows how to decode in quadratic time. © 2013 IEEE.

The role of androgens in fetal growth: observational study in two genetic models of disordered androgen signalling.

OBJECTIVE: To examine the role of androgens on birth weight in genetic models of altered androgen signalling. SETTING: Cambridge Disorders of Sex Development (DSD) database and the Swedish national screening programme for congenital adrenal hyperplasia (CAH). PATIENTS: (1) 29 girls with XY karyotype and mutation positive complete androgen insensitivity syndrome (CAIS); (2) 43 girls and 30 boys with genotype confirmed CAH. MAIN OUTCOME MEASURES: Birth weight, birth weight-for-gestational-age (birth weight standard deviation score (SDS)) calculated by comparison with national references. RESULTS: Mean birth weight SDS in CAIS XY infants was higher than the reference for girls (mean, 95% CI: 0.4, 0.1 to 0.7; p=0.02) and was similar to the national reference for boys (0.1, -0.2 to 0.4). Birth weight SDS in CAH girls was similar to the national reference for girls (0.0, -0.2 to 0.2) and did not vary by severity of gene mutation. Birth weight SDS in CAH boys was also similar to the national reference for boys (0.2, -0.2 to 0.6). CONCLUSION: CAIS XY infants have a birth weight distribution similar to normal male infants and birth weight is not increased in infants with CAH. Alterations in androgen signalling have little impact on birth weight. Sex dimorphism in birth size is unrelated to prenatal androgen exposure.

Evaluation of manufacturing techniques for a minifluidics demonstrator system

A multi-disciplinary team based at Heriot-Watt University and other Universities has been set up to tackle the design and manufacturing of lab-on-a-chip for industries as one of the demonstrators of the EPSRC Grand Challenge project "3D-Mintegration". The team focuses on the analysis of foetal genetic material extracted from maternal blood as a smart alternative to invasive prenatal testing such as amniocentesis. The first module of the microsystem envisaged achieves a separation of blood cells from plasma. This system permits the testing of different manufacturing techniques.

A species conserving genetic algorithm for multimodal function optimization

This paper introduces a new technique called species conservation for evolving parallel subpopulations. The technique is based on the concept of dividing the population into several species according to their similarity. Each of these species is built around a dominating individual called the species seed. Species seeds found in the current generation are saved (conserved) by moving them into the next generation. Our technique has proved to be very effective in finding multiple solutions of multimodal optimization problems. We demonstrate this by applying it to a set of test problems, including some problems known to be deceptive to genetic algorithms.

Language model combination and adaptation using weighted finite state transducers

In speech recognition systems language model (LMs) are often constructed by training and combining multiple n-gram models. They can be either used to represent different genres or tasks found in diverse text sources, or capture stochastic properties of different linguistic symbol sequences, for example, syllables and words. Unsupervised LM adaptation may also be used to further improve robustness to varying styles or tasks. When using these techniques, extensive software changes are often required. In this paper an alternative and more general approach based on weighted finite state transducers (WFSTs) is investigated for LM combination and adaptation. As it is entirely based on well-defined WFST operations, minimum change to decoding tools is needed. A wide range of LM combination configurations can be flexibly supported. An efficient on-the-fly WFST decoding algorithm is also proposed. Significant error rate gains of 7.3% relative were obtained on a state-of-the-art broadcast audio recognition task using a history dependently adapted multi-level LM modelling both syllable and word sequences. ©2010 IEEE.