Man-Machine Voice Communication
Year: 2007
Type: article
Abstract: Speech is our most natural way of communicating. Effective integration of speech into man-machine communication depends on the nature of the user interface and application. This is the justification for grouping together the topics of voice-enabled interactivity and speech engineering together in this chapter. A man-machine interface can be defined as the mediator between users and machines. It is a system that handles the entire communication process and is responsible for the provision of the machine “knowledge”, functionality, and available information. This must be carried out in a way that (1) is compatible with the user’s communication channels; and (2) can translate the user’s actions (user input) into a form (instructions/commands) understandable by a machine [1]. For approximately 25 years, a number of international research and development projects have working to adapt man-machine communication and interaction to the needs of human beings [2]. However, considerable progress in this field has only been achieved in the last 10 years, notably with the development of automatic speech and video-signal processing. While we like to think that speech is a natural form of communication, it is misleading to think that this translates into the facile building of interfaces that will provide a natural interaction with a machine (e.g., computer or robot). Generally, speech is not a natural means of communciation with machines [3]. The naturalness of speech communication should be seen as reflecting our experiences in using the voice modality to communicate with other humans. These people share a great deal of knowledge with the speaker something that cannot be said of current computers, even if there are ongoing efforts to provide machines with broad contextual knowledge. A great deal of the naturalness that we take for granted in voice communication goes away when the listener does not understand the meaning of what we say. The vision of the 1990s was one of ubiquitous, low-cost, easy-to-use communication and computation for everyone. Presently, one of the key technologies that is rapidly evolving to fulfill this vision is that of voice processing. Computers now have the ability to talk, listen and perhaps even understand. The field of voice processing covers a broad range of activities that share the future goal of enabling people to communicate with machines using natural voice communication skills. It rises from the confluence of low-cost computation and improved algorithms that has stimulated a wide range of uses for voice processing technology across the spectrum of information processing. Advances in human-language technology offer the promise of nearly universal access to on-line information and services. Since almost everyone speaks and understands a language, the development of spoken language systems will allow the
Author: Andrzej Drygajlo
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W840084437