Compact Subnetwork-based Continuous Speech R

On images of continuous functions from a compact manifold to Euclidean space

ON MAXIMAL IDEALS OF R∞L

Let $L$ be a completely regular frame and $mathcal{R}L$ be the ring of real-valued continuous functions on $L$. We consider the set $$mathcal{R}_{infty}L = {varphi in mathcal{R} L : uparrow varphi( dfrac{-1}{n}, dfrac{1}{n}) mbox{ is a compact frame for any $n in mathbb{N}$}}.$$ Suppose that $C_{infty} (X)$ is the family of all functions $f in C(X)$ for which the set ${x in X: |f(x)|geq dfrac{1...

Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation

A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...

Speech-to-Speech Translation Software on PDAs for Travel Conversation

We present an automatic speech-to-speech translation system for Personal Digital Assistants (PDAs) that helps oral communication between Japanese and English speakers in various situations while traveling. Our own compact large-vocabulary continuous speech recognition engine and compact translation engine based on a lexicalized grammar provided the basis for the Japanese/English bi-directional ...

Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation

A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...