Nowadays, almost all speaker-independent (SI) speech recognition systems use CDHMM with multivariate mixture Gaussian as observation density to cover speaker variabilities. It has been shown that given sufficient training data, the more mixtures are used in the HMM observation density, the better the system’s perform. However, acoustic HMM with more Gaussian densities is more complex and slows ...

In this paper, we introduce a system for on-line digit speech recognition services. Besides the speech recognition service in our system, we also provide adaptation function to improve the noise-robustness between different environment. In the case of English digit recognition, our recognition system can achieve over 80% accuracy for a specific speaker by using a few adaptation data. We use Sph...

The recognition accuracy in recent large vocabulary automatic speech recognition (ASR) systems is highly related to the existing mismatch between the training and testing sets. For example, dialect differences across the training and testing speakers result to a significant degradation in recognition performance. Some popular adaptation approaches improve the recognition performance of speech r...

The recognition accuracy in recent large vocabulary Automatic Speech Recognition (ASR) systems is highly related to the existing mismatch between the training and test sets. For example, dialect di erences across the training and testing speakers result to a signi cant degradation in recognition performance. Some popular adaptation approaches improve the recognition performance of speech recogn...

The article describes the speech recognition system development in Bengali language for aging population with various adaptation techniques. Variability in acoustic characteristics among different speakers degrades speech recognition accuracy. In general, perceptual as well as acoustical variations exists among speakers, but variations are more pronounced between young and aged population. Devi...

For various reasons such as ideology of patronage, fear of censorial measures and specific cultural and literary plans, authors may present their original texts as translation, and sometimes translators manipulate the original text to the extent that it can not be considered as translation anymore. This research was aimed at investigating Bastin's adaptation as a kind of pseudo-translation. He ...

To realize fast speaker adaptation in the case of limited adaptation data, we propose a fast speaker adaptation approach, called maximum likelihood smoothes and predictions. It smoothes and predicts target mean vectors based on their source mean vector by maximizing the likelihood of the smoothed model generating the adaptation data. So it can make best use of the first few adaptation data to q...

In this paper an unsupervised intra-speaker variability compensation method, ISVC, and unsupervised model adaptation are tested to address the problem of limited enrolling data in text-dependent speaker verification. In contrast to model adaptation methods, ISVC is memoryless with respect to previous verification attempts. As shown here, unsupervised model adaptation can lead to substantial imp...

Individuals with generalized anxiety disorder (GAD) display poor emotional conflict adaptation, a cognitive control process requiring the adjustment of performance based on previous-trial conflict. It is unclear whether GAD-related conflict adaptation difficulties are present during tasks without emotionally-salient stimuli. We examined conflict adaptation using the N2 component of the event-re...

With the popularity of mobile services, an effective context-aware mobile service adaptation is becoming more and more important for operators. In this paper, we propose a Co-evolution eXtended Classifier System (CXCS) to perform context-aware mobile service adaptation. Our key idea is to learn user context, match adaptation rule, and provide the best suitable mobile services for users. Differe...