Tài liệu hạn chế xem trước, để xem đầy đủ mời bạn chọn Tải xuống
1
/ 385 trang
THÔNG TIN TÀI LIỆU
Thông tin cơ bản
Định dạng
Số trang
385
Dung lượng
15,92 MB
Nội dung
[...]... number of speech recognizer rejections in a dialogue average number of barge-in attempts from the user in a dialogue average number of cancel attempts from the user in a dialogue average number of help requests from the user in a dialogue average number of system error messages in a dialogue average number of system questions in a dialogue average number of system turns in a dialogue average number of. .. number of system words uttered in a dialogue average number of time-out prompts in a dialogue average number of turns in a dialogue average number of user questions in a dialogue average number of user turns in a dialogue average number of user words uttered in a dialogue average number of in-vocabulary user words in a dialogue average number of words uttered in a dialogue false speaker rejection rate... prediction These systems are called spokendialoguesystems (SDSs), in some literature also spoken language dialoguesystems (SLDSs) They have to be differentiated from systems with more restricted capabilities, e.g command systems or systems accepting only dialling tones as an input A categorization of interactive speech systems will be given in Section 2.1.3 Most of the currently available systems enable... taxonomy ofquality aspects developed in Chapter 2 proved to form a solid basis for quality modelling approaches which aim at being generic, and applicable to a variety of other systems The interaction scenario which is addressed here is of course limited However, it is expected that the structured approach to qualityoftelephone-based spoken dialoguesystems can be transferred to other types of systems. .. successfully been used for the definition of design guidelines for spokendialoguesystems The guidelines encompass general principles of cooperative behavior in HMI, and form one aspect of interaction quality A more general picture of interaction quality and of the qualityof services offered via SDSs is presented in Section 2.3 A new taxonomy is developed which allows quality aspects to be classified, and... determine the qualityof the developed systems, and the resulting satisfaction of their users As a wide range of novice users is the target group of current state -of- theart systems and services, the need for subjective assessment and evaluation ofquality is increasing (Hone and Graham, 2001, p 2083): “In the past speech input/output technology was successful only in a limited number of specialised... configuration, per dialogue) frequency-dependent loss of the talker echo path (dB) frequency-dependent loss of the sidetone path (dB) listener sidetone rating (dB) understanding error confusion matrix mean recognition score total number of attribute-value pairs in an utterance number of correctly not set attribute-value pairs total number of concepts in the dialogue total number of dialogues total number of user... types ofsystems Examples are systems which are operated directly in different acoustic environments (car navigation systems, smart home systems) , or multimodal systems Such interactive systems will become increasingly important in the near future, and their success and acceptance will depend to a large extent on the level ofquality they offer to their users Chapter 2 QUALITYOF HUMAN-MACHINE INTERACTION... designers of spoken dialoguesystems In this chapter, an attempt is made to close the gap The starting point is a description of communication scenarios in which a human user interacts with a spokendialogue system over some type of speech transmission network, see Section 2.1 It takes into account the source and the sink of information, as well as the transmission channel Different types of networks... individual elements of a spokendialogue system will be addressed first individually, and commonly used methods and developments will be pointed out However, the qualityof the whole system and of the service visible (audible) to the user will not be just a sum of the individual components It is therefore necessary to quantify the contribution of the individual components to the quality perception of the whole . class="bi x0 y0 w0 h0" alt="" Quality of Telephone-Based Spoken Dialogue Systems This page intentionally left blank QUALITY OF TELEPHONE-BASED SPOKEN DIALOGUE SYSTEMS SEBASTIAN MÖLLER Institut. number of system words uttered in a dialogue average number of time-out prompts in a dialogue average number of turns in a dialogue average number of user questions in a dialogue average number of. number of help requests from the user in a dialogue average number of system error messages in a dialogue average number of system questions in a dialogue average number of system turns in a dialogue average