Task-independent call-routing

被引:5
|
作者
Huang, Q [1 ]
Cox, S [1 ]
机构
[1] Univ E Anglia, Sch Comp Sci, Norwich NR4 7TJ, Norfolk, England
关键词
call routing; interactive voice systems; voice response systems; speech dialogue systems; speech recognition;
D O I
10.1016/j.specom.2005.06.001
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Call-routing is the technology of automatically classifying the type of a telephone call from a customer to a business or an institution in order to transmit the call onward to the correct "destination". Making transcriptions of calls to provide training data for automatic routing in a particular application requires considerable human effort, and it would be highly advantageous for the system to be able to learn how to route calls from training utterances that were not transcribed. This paper introduces several techniques that can be used to build call routers from an untranscribed training set, and also without any prior knowledge of the application vocabulary or grammar. The techniques concentrate on identifying sequences of decoded phones that are salient for routing, and introduces two methods for doing this using language models that are specifically tailored for the routing task. Despite the fact that the phone recognition error-rate on the calls is over 70%, the best system described here achieves a routing error of 13.5% on an 18 route task. (c) 2005 Elsevier B.V. All rights reserved.
引用
收藏
页码:374 / 389
页数:16
相关论文
共 50 条
  • [1] Call-routing schemes for call-center outsourcing
    Gans, Noah
    Zhou, Yong-Pin
    [J]. M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT, 2007, 9 (01) : 33 - 50
  • [2] A call-routing problem with service-level constraints
    Gans, N
    Zhou, YP
    [J]. OPERATIONS RESEARCH, 2003, 51 (02) : 255 - 271
  • [3] DEEP BELIEF NETS FOR NATURAL LANGUAGE CALL-ROUTING
    Sarikaya, Ruhi
    Hinton, Geoffrey E.
    Ramabhadran, Bhuvana
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 5680 - 5683
  • [4] Task-independent effect of time on rCBF
    Rajah, MN
    Hussey, D
    Houle, S
    Kapur, S
    McIntosh, AR
    [J]. NEUROIMAGE, 1998, 7 (04) : 314 - 325
  • [5] Towards task-independent speech recognition
    Lefevre, F
    Gauvain, JL
    Lamel, L
    [J]. 2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING - VOL IV: SIGNAL PROCESSING FOR COMMUNICATIONS; VOL V: SIGNAL PROCESSING EDUCATION SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO & ELECTROACOUSTICS; VOL VI: SIGNAL PROCESSING THEORY & METHODS STUDENT FORUM, 2001, : 521 - 524
  • [6] Managing response time in a call-routing problem with service failure
    de Véricourt, F
    Zhou, YP
    [J]. OPERATIONS RESEARCH, 2005, 53 (06) : 968 - 981
  • [7] Call-routing analysis using SS7 data
    Brugman, D
    [J]. BELL LABS TECHNICAL JOURNAL, 2005, 9 (04) : 133 - 138
  • [8] A Framework to Create Task-Independent Conversational Systems
    Perez, D.
    Kirschning, I.
    [J]. INNOVATIONS IN COMPUTING SCIENCES AND SOFTWARE ENGINEERING, 2010, : 595 - 600
  • [9] Genericity and portability for task-independent speech recognition
    Lefevre, F
    Gauvain, JL
    Lamel, L
    [J]. COMPUTER SPEECH AND LANGUAGE, 2005, 19 (03): : 345 - 363
  • [10] Task-independent semantic activation for numbers and animals
    Thioux, M
    Pesenti, M
    Costes, N
    De Volder, A
    Seron, X
    [J]. COGNITIVE BRAIN RESEARCH, 2005, 24 (02): : 284 - 290