Speech quality is the most visible and important aspect of quality of service (QoS) for telecommunication networks. Hence, the ability to monitor and design for this quality has become a top priority. Speech quality refers to the clearness of a speaker’s voice as perceived by a listener. Speech quality measurement offers a means of adding the human end user’s perspective to traditional ways of performing network management evaluation of voice telephony services. Traditionally, measurement of users’ perception of speech quality has been performed by expensive and time-consuming subjective listening tests. Over the last three decades, numerous attempts have been made to supplement subjective tests with objective measurements based on algorithms that can be computerised and automated. This chapter describes the technicalities associated with speech quality measurement, and presents a review of current subjective and objective speech quality evaluation methods and standards in telecommunications.
Background: Voice Quality And Its Measurement In Telecommunications
In telecommunications, QoS is thought to be divided into three components (Moller, 2000). The main component is the speech or voice communication quality, and relates to a bi/multi-directional conversation over the telecommunications network. The second component is the service-related influences, which is commonly referred to as the “service performance,” and includes service support, a part of service operability, and service security. The third component of the QoS is the necessary terminal equipment performance. Voice communication quality represents a major component of the overall communication quality perceived by a user and is concerned with the speech transmission from a talker to a listener (Quackenbush, Barnawell, & Clements, 1988). Thus, it is user-directed and therefore provides close insight in the question of which quality feature results in an acceptability of the service from the user’s viewpoint.
Key Terms in this Chapter
Subjective Voice Quality Test/Measure: Voice quality test/measure that is based on ratings by human listeners.
Objective Voice Quality Measure: Metric based on a computational model or an algorithm that computes MOS voice quality values that are as close as possible to the ratings obtained from subjective tests, by observing a small portion of the speech in question.
Intrusive Objective Voice Quality Measure: Objective voice quality measure that bases its measurement on computation of the distortion between the original speech signal and the degraded speech signal. Such measure is often referred to as input-to-output or two-ended measure .
Non-Intrusive Objective Voice Quality measure: Objective voice quality measure that uses only the degraded speech signal and has no access to the original speech signal. Such measure is often referred to as output-based or single-ended measure.
Voice Quality Measurement (VQM): Means of measuring customer experience of voice communication services (systems/devices).
Quality of Service (QoS): The set of those quantitative and qualitative characteristics of a distributed multimedia system, which are necessary in order to achieve the required functionality of an application.
Voice Quality: Result of a person’s judgement on spoken language, which he/she perceives in a specific situation and judges instantaneously according to his/her experience, motivation, and expectation. Regarding voice communication systems, voice quality is the customer’s perception of a service or product.
Mean Opinion Score (MOS): Average value of all the rating scores registered by the human listeners (conducting a subjective voice quality test) for a given test condition.