Satoshi Nakamura – författare

Incorporating Knowledge Sources into Statistical Speech Recognition addresses the problem of developing efficient automatic speech recognition (ASR) systems, which maintain a balance between utilizing a wide knowledge of speech variability, while keeping the training / recognition effort feasible and improving speech recognition performance. The book provides an efficient general framework to incorporate additional knowledge sources into state-of-the-art statistical ASR systems. It can be applied to many existing ASR problems with their respective model-based likelihood functions in flexible ways.

In this work, the authors present a fully statistical approach to model non--native speakers'' pronunciation. Second-language speakers pronounce words in multiple different ways compared to the native speakers. Those deviations, may it be phoneme substitutions, deletions or insertions, can be modelled automatically with the new method presented here.

The methods is based on a discrete hidden Markov model as a word pronunciation model, initialized on a standard pronunciation dictionary. The implementation and functionality of the methodology has been proven and verified with a test set of non-native English in the regarding accent.

The book is written for researchers with a professional interest in phonetics and automatic speech and speaker recognition.

This book focuses on how interactive, multimodal technology such as virtual agents can be used in training and treatment (social skills training, cognitive behavioral therapy). People with socio-affective deficits have difficulties controlling their social behavior and also suffer from interpreting others’ social behavior. Behavioral training, such as social skills training, is used in clinical settings. Patients are trained by a coach to experience social interaction and reduce social stress. In addition to behavioral training, cognitive behavioral therapy is also useful for understanding better and training social-affective interaction. All these methods are effective but expensive and difficult to access. This book describes how multimodal interactive technology can be used in healthcare for measuring and training social-affective interactions. Sensing technology analyzes users’ behaviors and eye-gaze, and various machine learning methods can be used for prediction tasks. This bookfocuses on analyzing human behaviors and implementing training methods (e.g., by virtual agents, virtual reality, dialogue modeling, personalized feedback, and evaluations). Target populations include depression, schizophrenia, autism spectrum disorder, and a much larger group of social pathological phenomena.