This paper investigates supervised and unsupervised adaptation of stochastic grammars, including ngram language models and probabilistic context-free grammars (PCFGs), to a new domain. It is shown that the commonly used approaches of count merging and model interpolation are special cases of a more general maximum a posteriori (MAP) framework, which additionally allows for alternate adaptation ...

Dysarthria is a motor speech disorder characterized by weakness, paralysis, or poor coordination of the muscles responsible for speech. Although automatic speech recognition (ASR) systems have been developed for disordered speech, factors such as low intelligibility and limited vocabulary decrease speech recognition accuracy. In this paper, we introduce a technique that can increase recognition...

Several adaptation approaches have been devised to ensure end-to-end quality-of-service (QoS) for enterprise distributed systems in dynamic operating environments. Not all approaches are applicable, however, for the stringent accuracy, timeliness, and development complexity requirements of distributed real-time and embedded (DRE) systems. This paper empirically evaluates constant-time supervise...

Invariant numerical schemes possess properties that may overcome the numerical properties of most of classical schemes. When they are constructed with moving frames, invariant schemes can present more stability and accuracy. The cornerstone is to select relevant moving frames. We present a new algorithmic process to do this. The construction of invariant schemes consists in parametrizing the sc...

and Applied Analysis 3 on the whole space H, is a bounded operator. Here, I is the identity operator. The following operators D ( I τA τA 2 2 ) , G ( I − τ 2A 2 ) , P ( I τ 2 A ) , R I τB −1, Tτ ( I B−1A ( I τA τ 2 P−2 ) K ( I − R2N−1 ) GKP−2R2N−1 −GKP−2 2I τB R [ n ∑ i 1 αi ( I ( λi − [ λi τ ] τ ) A ) D − λi/τ u0 ])−1

For optical waveguides with high index-contrast and sharp corners, existing full-vectorial mode solvers including those based on boundary integral equations typically have only second or third order of accuracy. In this paper, a new full-vectorial waveguide mode solver is developed based on a new formulation of boundary integral equations and the so-called Neumann-to-Dirichlet operators for sub...

Statistical speech recognition using continuous-density hidden Markov models (CDHMMs) has yielded many practical applications. However, in general, mismatches between the training data and input data significantly degrade recognition accuracy. Various acoustic model adaptation techniques using a few input utterances have been employed to overcome this problem. In this article, we survey these a...

In this paper we describe system architectures for robust MLLR based environmental adaptation of continuous speech recognition systems. Inspired by an existing broadcast news transcription system [1] we refined the identification of acoustic scenarios by using a combined GMM/HMM method. Thus environmental adaptation regarding arbitrary acoustic scenarios beyond speaker changes becomes possible....