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.

Coastal brownfields and adaptation to climate change: Discussions on potential hazards from contaminated groundwater displacement due to saltwater incursion

Toxic-waste associated with coastal brownfield sites can pose serious risks to human and environmental health. In light of anticipated sea-level rise (SLR) due to global climate change, coastal brownfields require heightened attention. The primary intent of this study is to pose questions and encourage discussion of this problem among policy makers. Impacts from SLR on coastal zones are examined within a brownfield policy framework and, current coastal brownfield policy discussions with respect to SLR are also examined. (PDF contains 4 pages)

Modeling the Links between Biodiversity, Ecosystem Services and Human Wellbeing in the Context of Climate Change: Results from an Econometric Analysis on the European Forest Ecosystems

25 p.

Ecosystem function and biodiversity on coral reefs

The article highlights a workshop held in Key West, Florida in November 1993 attended by a group of 35 international scientists where topics of ecosystem function and biodiversity on coral reefs were discussed.

Intonation modelling and adaptation for emotional prosody generation

This paper proposes an HMM-based approach to generating emotional intonation patterns. A set of models were built to represent syllable-length intonation units. In a classification framework, the models were able to detect a sequence of intonation units from raw fundamental frequency values. Using the models in a generative framework, we were able to synthesize smooth and natural sounding pitch contours. As a case study for emotional intonation generation, Maximum Likelihood Linear Regression (MLLR) adaptation was used to transform the neutral model parameters with a small amount of happy and sad speech data. Perceptual tests showed that listeners could identify the speech with the sad intonation 80% of the time. On the other hand, listeners formed a bimodal distribution in their ability to detect the system generated happy intontation and on average listeners were able to detect happy intonation only 46% of the time. © Springer-Verlag Berlin Heidelberg 2005.