Speaker adaptation is important to reduce the variability of the speech signal from various speakers. Two approaches are introduced to solve this problem, Vector Quantization (VQ) and Canonical Correlation (CC). Their ability to enhance the discrimination of confused sounds are evaluated through a collected database of Arabic confusable sounds. A recognition accuracy of 73% is obtained without ...

This paper investigates adapting a lexicalized probabilistic context-free grammar (PCFG) to a novel domain, using maximum a posteriori (MAP) estimation. The MAP framework is general enough to include some previous model adaptation approaches, such as corpus mixing in Gildea (2001), for example. Other approaches falling within this framework are more effective. In contrast to the results in Gild...

Out-Of-Vocabulary (OOV) word utterances are unavoidable in speech recognition since the vocabulary size of a recognition dictionary is limited. And therefore, automatic vocabulary adaptation, which selects unregistered (i.e. OOV) words from relevant documents and registers them to a dictionary with their proper probability values, is an important technique. To improve recognition accuracy, a vo...

Multisensory calibration is fundamental for proficient interaction within a changing environment. Initial studies suggested a visual-dominant mechanism. More recently, a cue-reliability-based model, similar to optimal cue integration, has been proposed. However, a more general, reliability-independent model of fixed-ratio adaptation (of which visual dominance is a subcase) has never been tested...

Domain adaptation is a key feature in Machine Translation. It generally encompasses terminology, domain and style adaptation, especially for human postediting workflows in Computer Assisted Translation (CAT). With Neural Machine Translation (NMT), we introduce a new notion of domain adaptation that we call “specialization” and which is showing promising results both in the learning speed and in...

In this paper we describe an analog VLSI circuit, fabricated using a standard 2 m, n-well, BiCMOS process, which utilizes oating-gate structures for non-volatile, on-chip, analog parameter storage. This circuit is designed to operate in the context of a hardware model of the primate oculomotor system and performs visually-guided, saccadic adaptation. The chip contains a one-dimensional array of...

The currently adaptive mechanisms adapt a single acoustic model for a speaker in speaker-independent speech recognition system. However, as more users use the same speech recognizer, single acoustic model adaptation leads to negative adaptation upon switching between users. Such a situation is problematic (undependable adaptation). This paper, considering the situation of a smart home or an off...

Achieving metallic frameworks of single tooth restorations involves obtaining high precision parts. Adaptation accuracy is one of the main factors that influence single tooth restorations long-term reliability. The purpose of the study was to test innovative methods for adaptation accuracy evaluation of different single tooth cast restorations. Acrylic teeth were prepared for single tooth cast ...