Skip to main content
Top

2016 | Book

Emotion, Affect and Personality in Speech

The Bias of Language and Paralanguage

insite
SEARCH

About this book

This book explores the various categories of speech variation and works to draw a line between linguistic and paralinguistic phenomenon of speech. Paralinguistic contrast is crucial to human speech but has proven to be one of the most difficult tasks in speech systems. In the quest for solutions to speech technology and sciences, this book narrows down the gap between speech technologists and phoneticians and emphasizes the imperative efforts required to accomplish the goal of paralinguistic control in speech technology applications and the acute need for a multidisciplinary categorization system. This interdisciplinary work on paralanguage will not only serve as a source of information but also a theoretical model for linguists, sociologists, psychologists, phoneticians and speech researchers.

Table of Contents

Frontmatter
Chapter 1. Introduction
Abstract
The ability to interpret any kind of human communication correctly is considered an essential competency of any individual. Human behaviour is influenced by various internal as well as external factors such as genetics, culture, social norms, attitude etc. and is impacted by certain traits each individual has. Non-verbal communication possesses immense potential to emphasize the meaning of spoken words through thoughts and feelings especially when the conversation is not face to face. This chapter elucidates the science of paralanguage as a means to extract the unintentional meanings from utterances. Various paralinguistic cues have been investigated for discrete emotion recognition and evolution of language and communication systems.
Swati Johar
Chapter 2. Psychology of Voice
Abstract
The sound of every individual’s voice is unique due to the difference in the size and shape of vocal cords. The vocal folds loosen and tighten resulting in a change in pitch, volume, timbre, or tone of the sound produced. Analyzing speech from a physiological perspective, this chapter explores the pitch component of voice and how influential it can be. Interestingly, information regarding prosody, emotions, gender and age is affected by pitch and pitch can help in unconsciously divulging the feelings, moods and emotions. The chapter also enlightens vocal behaviour as a powerful index of emotional and personality markers which are paramount in the extraction of meaningful information from acoustic signals and contribute to a better understanding of the psychology of voice and performance capabilities.
Swati Johar
Chapter 3. Language, Communication and Human Behaviour
Abstract
Language has been considered as a social behavioural phenomenon and an indicator of the structure of cognitive processes dealing with functions such as communicating, imagining, learning and perceiving. Communication is enriched through coverbal or nonverbal behaviours and this chapter speculates the implications of these behaviours to significantly improve speech recognition and understanding. The association and interdependence of verbal and nonverbal elements has been highlighted and various research approaches and challenges focusing on interpretation of human behaviour by exploitation of these measures have been discussed.
Swati Johar
Chapter 4. Multimodality and Spoken Dialogue Systems
Abstract
Broaching communication from an interdisciplinary perspective, the present chapter attends to the diverse ways in which multimodal principles can be applied to current speech systems to seek natural and seamless human computer interaction capabilities. Offering various avenues to explore and suggesting benefits of multimodal architectures, new perspectives in spoken dialogue systems have been described. The emergence of technological innovation and inevitable incorporation of natural language technologies in future spoken dialogue systems challenge the future of multimodality to evolve as a natural user interface paradigm and facilitate consequential multidisciplinary research.
Swati Johar
Chapter 5. Emotional Speech Recognition
Abstract
Recent years have been marked by a growing need for systems that can grasp human emotions and in particular, recognize emotions. Emotions lie at the centre of any social communication and form the basis for an intelligent and meaningful interaction. The chapter further discusses the acoustic correlates of emotions and describes various techniques and developments imperative to support speech interfaces that recognize emotional expressions in real world settings. Significant advancement in the areas of knowledge representation, infrastructure requirements and algorithm implementation is a prerequisite for modeling effective future speech recognition systems that are more robust and dynamic in nature.
Swati Johar
Chapter 6. Where Speech Recognition Is Going: Conclusion and Future Scope
Abstract
Today, voice and natural language processing are at the forefront of any human machine interaction environment. The chapter emphasizes the tremendous progress that has taken place in machine learning, statistical data-mining and pattern recognition approaches that can help in making speech interfaces more versatile and pervasive. The growing requirements of speech interfaces also warn against the impediments that may come in the way of successful implementation of acoustically robust natural interfaces. Finally, the chapter underlines the technical advances and research efforts to be undertaken for high performance real-time speech recognition that will completely change the way humans interact with their computing devices.
Swati Johar
Backmatter
Metadata
Title
Emotion, Affect and Personality in Speech
Author
Swati Johar
Copyright Year
2016
Electronic ISBN
978-3-319-28047-9
Print ISBN
978-3-319-28045-5
DOI
https://doi.org/10.1007/978-3-319-28047-9