ITU-T H 625-2017 Architecture for network-based speech-to-speech translation services (Study Group 16).pdf

《ITU-T H 625-2017 Architecture for network-based speech-to-speech translation services (Study Group 16).pdf》由会员分享，可在线阅读，更多相关《ITU-T H 625-2017 Architecture for network-based speech-to-speech translation services (Study Group 16).pdf（54页珍藏版）》请在麦多课文档分享上搜索。

1、 I n t e r n a t i o n a l T e l e c o m m u n i c a t i o n U n i o n ITU-T H.625 TELECOMMUNICATION STANDARDIZATION SECTOR OF ITU (03/2017) SERIES H: AUDIOVISUAL AND MULTIMEDIA SYSTEMS Broadband, triple-play and advanced multimedia services Advanced multimedia services and applications Architecture

2、 for network-based speech-to-speech translation services Recommendation ITU-T H.625 ITU-T H-SERIES RECOMMENDATIONS AUDIOVISUAL AND MULTIMEDIA SYSTEMS CHARACTERISTICS OF VISUAL TELEPHONE SYSTEMS H.100H.199 INFRASTRUCTURE OF AUDIOVISUAL SERVICES General H.200H.219 Transmission multiplexing and synchro

3、nization H.220H.229 Systems aspects H.230H.239 Communication procedures H.240H.259 Coding of moving video H.260H.279 Related systems aspects H.280H.299 Systems and terminal equipment for audiovisual services H.300H.349 Directory services architecture for audiovisual and multimedia services H.350H.35

4、9 Quality of service architecture for audiovisual and multimedia services H.360H.369 Telepresence H.420H.429 Supplementary services for multimedia H.450H.499 MOBILITY AND COLLABORATION PROCEDURES Overview of Mobility and Collaboration, definitions, protocols and procedures H.500H.509 Mobility for H-

5、Series multimedia systems and services H.510H.519 Mobile multimedia collaboration applications and services H.520H.529 Security for mobile multimedia systems and services H.530H.539 Security for mobile multimedia collaboration applications and services H.540H.549 Mobility interworking procedures H.5

6、50H.559 Mobile multimedia collaboration inter-working procedures H.560H.569 BROADBAND, TRIPLE-PLAY AND ADVANCED MULTIMEDIA SERVICES Broadband multimedia services over VDSL H.610H.619 Advanced multimedia services and applications H.620H.629 Ubiquitous sensor network applications and Internet of Thing

7、s H.640H.649 IPTV MULTIMEDIA SERVICES AND APPLICATIONS FOR IPTV General aspects H.700H.719 IPTV terminal devices H.720H.729 IPTV middleware H.730H.739 IPTV application event handling H.740H.749 IPTV metadata H.750H.759 IPTV multimedia application frameworks H.760H.769 IPTV service discovery up to co

8、nsumption H.770H.779 Digital Signage H.780H.789 E-HEALTH MULTIMEDIA SERVICES AND APPLICATIONS Personal health systems H.810H.819 Interoperability compliance testing of personal health systems (HRN, PAN, LAN, TAN and WAN) H.820H.859 Multimedia e-health data exchange services H.860H.869 For further de

9、tails, please refer to the list of ITU-T Recommendations. Rec. ITU-T H.625 (03/2017) i Recommendation ITU-T H.625 Architecture for network-based speech-to-speech translation services Summary Recommendation ITU-T H.625 defines the system architecture for network-based speech-to-speech translation (S2

10、ST) on the basis of Recommendation ITU-T F.745 and serves as a technical introduction to the subsequent definitions of detailed system components and protocols. The scope of this Recommendation is to describe the functional architecture and mechanisms of network-based S2ST, interface protocols betwe

11、en S2ST modules, and a workflow of the network-based S2ST system. This revision includes additional information to clarify that Recommendation ITU-T H.625 could be applicable to both face-to-face communication and remote communication. The modality conversion markup language (MCML) is also enhanced

12、for adding more flexibility. History Edition Recommendation Approval Study Group Unique ID* 1.0 ITU-T H.625 2010-10-14 16 11.1002/1000/10992 2.0 ITU-T H.625 2017-03-01 16 11.1002/1000/13190 Keywords Automatic speech recognition (ASR), machine translation (MT), modality conversion markup language (MC

13、ML), speech-to-speech translation (S2ST), text-to-speech synthesis (TTS). * To access the Recommendation, type the URL http:/handle.itu.int/ in the address field of your web browser, followed by the Recommendations unique ID. For example, http:/handle.itu.int/11.1002/1000/11830-en. ii Rec. ITU-T H.6

14、25 (03/2017) FOREWORD The International Telecommunication Union (ITU) is the United Nations specialized agency in the field of telecommunications, information and communication technologies (ICTs). The ITU Telecommunication Standardization Sector (ITU-T) is a permanent organ of ITU. ITU-T is respons

15、ible for studying technical, operating and tariff questions and issuing Recommendations on them with a view to standardizing telecommunications on a worldwide basis. The World Telecommunication Standardization Assembly (WTSA), which meets every four years, establishes the topics for study by the ITU

16、-T study groups which, in turn, produce Recommendations on these topics. The approval of ITU-T Recommendations is covered by the procedure laid down in WTSA Resolution 1. In some areas of information technology which fall within ITU-Ts purview, the necessary standards are prepared on a collaborative

17、 basis with ISO and IEC. NOTE In this Recommendation, the expression “Administration“ is used for conciseness to indicate both a telecommunication administration and a recognized operating agency. Compliance with this Recommendation is voluntary. However, the Recommendation may contain certain manda

18、tory provisions (to ensure, e.g., interoperability or applicability) and compliance with the Recommendation is achieved when all of these mandatory provisions are met. The words “shall“ or some other obligatory language such as “must“ and the negative equivalents are used to express requirements. Th

19、e use of such words does not suggest that compliance with the Recommendation is required of any party. INTELLECTUAL PROPERTY RIGHTSITU draws attention to the possibility that the practice or implementation of this Recommendation may involve the use of a claimed Intellectual Property Right. ITU takes

20、 no position concerning the evidence, validity or applicability of claimed Intellectual Property Rights, whether asserted by ITU members or others outside of the Recommendation development process. As of the date of approval of this Recommendation, ITU had not received notice of intellectual propert

21、y, protected by patents, which may be required to implement this Recommendation. However, implementers are cautioned that this may not represent the latest information and are therefore strongly urged to consult the TSB patent database at http:/www.itu.int/ITU-T/ipr/. ITU 2017 All rights reserved. N

22、o part of this publication may be reproduced, by any means whatsoever, without the prior written permission of ITU. Rec. ITU-T H.625 (03/2017) iii Table of Contents Page 1 Scope . 1 2 References . 1 3 Definitions 2 3.1 Terms defined elsewhere 2 3.2 Term defined in this Recommendation 2 4 Abbreviatio

23、ns and acronyms 3 5 Conventions 3 6 System functional architecture . 4 6.1 System overview 4 6.2 Functional components . 8 6.3 Protocols . 9 (1) MCML root . 10 (2) User . 11 (2-1) Transmitter and Receiver . 12 (3) Server 14 (3-1) Request and Response 15 (3-2) Routing . 16 (3-3) InputUserProfile . 17

24、 (3-4) TargetOutput . 19 (3-5) Input 20 (4) History 30 6.4 General workflow for modality conversion . 31 Annex A MCML 2.0 schema 34 Appendix I Examples of physical level architecture workflow examples of modality conversion using MCP 43 I.1 Shared S2ST client for two-party communication . 43 I.2 Per

25、sonal S2ST client communication . 44 I.3 Cross-modality communication 44 Bibliography. 46 iv Rec. ITU-T H.625 (03/2017) Introduction Speech-to-speech translation (S2ST) technologies, which translate speech in a source language to speech in a target language, are an effective means of facilitating co

26、mmunication beyond language boundaries for those who do not speak a common language. Developing an S2ST system requires the construction of automatic speech recognition (ASR), machine translation (MT) and text-to-speech (TTS) synthesis components. Many ASR, MT and TTS systems for different language

27、pairs have been developed independently all over the world. If these systems could be connected together through a network, then S2ST systems spanning a greater number of language pairs can be achieved. To realize this network-based S2ST technology by connecting various distributed components, this

28、Recommendation describes how to combine those individual S2ST systems and defines architectural requirements for the network-based S2ST system. Rec. ITU-T H.625 (03/2017) 1 Recommendation ITU-T H.625 Architecture for network-based speech-to-speech translation services 1 Scope This Recommendation def

29、ines the following items for designing a platform of the network-based speech-to-speech (S2ST) system: a functional architecture and mechanisms of network-based S2ST; interface protocols between S2ST modules; and a workflow of the network-based S2ST system. 2 References The following ITU-T Recommend

30、ations and other references contain provisions which, through reference in this text, constitute provisions of this Recommendation. At the time of publication, the editions indicated were valid. All Recommendations and other references are subject to revision; users of this Recommendation are theref

31、ore encouraged to investigate the possibility of applying the most recent edition of the Recommendations and other references listed below. A list of the currently valid ITU-T Recommendations is regularly published. The reference to a document within this Recommendation does not give it, as a stand-

32、alone document, the status of a Recommendation. ITU-T F.745 Recommendation ITU-T F.745 (2010), Functional requirements for network-based speech-to-speech translation services. IETF RFC 2279 IETF RFC 2279 (1998), UTF-8, a transformation format of ISO 10646. IETF RFC 2396 IETF RFC 2396 (1998), Uniform

33、 Resource Identifiers (URI): Generic Syntax. IETF RFC 2616 IETF RFC 2616 (1999), Hypertext Transfer Protocol HTTP/1.1. IETF RFC 2818 IETF RFC 2818 (2000), HTTP Over TLS. IETF RFC 3550 IETF RFC 3550 (2003), RTP: A Transport Protocol for Real-Time Applications. W3C XML1.0 W3C XML1.0 (2008), Extensible

34、 Markup Language (XML) 1.0. W3C XML Schema W3C XML Schema Part 2 (2004), XML Schema Part 2: Datatypes Second Edition. ISO 639-1 ISO 639-1 (2002), Codes for the representation of names of languages Part 1: Alpha-2 code. ISO 639-2 ISO 639-2 (1998), Codes for the representation of names of languages Pa

35、rt 2: Alpha-3 code. ISO 639-3 ISO 639-3 (2007), Codes for the representation of names of languages Part 3: Alpha-3 code for comprehensive coverage of languages. ISO 639-4 ISO 639-5 (2010), Codes for the representation of names of languages Part 4: General principles of coding of the representation o

36、f names of languages and related entities, and application guidelines. ISO 639-5 ISO 639-5 (2008), Codes for the representation of names of languages Part 5: Alpha-3 code for language families and groups. NOTE In this Recommendation, “ISO 639“ refers collectively to the five parts of ISO 639 listed

37、above. 2 Rec. ITU-T H.625 (03/2017) 3 Definitions 3.1 Terms defined elsewhere This Recommendation uses the following terms defined elsewhere: 3.1.1 adaptive differential pulse code modulation (ADPCM) b-ITU-T G.701: Compression algorithms that achieve bit rate reduction through the use of adaptive pr

38、ediction and adaptive quantization. 3.1.2 machine translation (MT) ITU-T F.745: Text in a source language is converted by computers into text in a target language what has the same meaning as the original text in the source language. 3.1.3 modality conversion (MC) ITU-T F.745: The conversion of data

39、 to different formats and languages using automatic speech recognition (ASR), machine translation (MT) and text-to-speech (TTS) systems. 3.1.4 modality conversion markup language (MCML) ITU-T F.745: An XML schema that serves as a data description for data exchanged among modality conversion modules.

40、 3.1.5 modality conversion protocol (MCP) ITU-T F.745: The communication protocol which transfers data between modality conversion (MC) clients and servers using HTTP(S)/RTP as defined in IETF RFC 2616, IETF RFC 2818 and IETF RFC 3550. This protocol transfers the MCML comprising of Multimodal Inform

41、ation (MI) data which is input into MC clients by users and MC results which are obtained by MC servers. 3.1.6 multimodal information (MI) ITU-T F.745: The information input into MC clients by users via multimodal sensors. 3.1.7 multipurpose Internet mail extensions (MIME) b-ITU-T J.200: An applicat

42、ion layer protocol. It features a content architecture to facilitate multimedia data such as text other than US-ASCII code, sound, image, etc. to be handled in Internet mails. 3.1.8 N-best ITU-T F.745: The most likely “N“ hypotheses obtained from modality conversion engines. 3.1.9 pulse code modulat

43、ion (PCM) b-ITU-T G.701: A process in which a signal is sampled, and the difference between each sample of this signal and its estimated value is quantized and converted by encoding to a digital signal. NOTE The estimated values of the signal are calculated by a predictor from the quantized differen

44、ce signal. 3.1.10 speech-to-speech translation (S2ST) ITU-T F.745: Speech in a source language is translated into speech in a target language. 3.1.11 text-to-speech synthesis (TTS) b-ITU-T P.10: A process generates a speech signal from text codes. It is usually composed of the two parts: a language-

45、dependent text processing part (the high level processing part), which generates from the character string (by reading rules, vocabulary and semantic analysis) a set of phonetic, prosodic, etc., parameters which are used by: an acoustical signal generating part, the synthesiser itself, which generat

46、es the audible speech. 3.2 Term defined in this Recommendation This Recommendation defines the following terms: 3.2.1 automatic speech recognition (ASR): A system that can recognize continuous speech, often having phoneme-sized references, using lexical, syntactic, semantic, and pragmatic knowledge,

47、 and Rec. ITU-T H.625 (03/2017) 3 reacts appropriately (therefore having interpreted the message and found the corresponding action to be taken). NOTE This definition is the same as that given for continuous speech understanding system in b-ITU-T P.10. 3.2.2 dialogue management (DM): The process whi

48、ch is capable of managing the states of dialogues as well as creating appropriate responses for input texts and other modalities. 4 Abbreviations and acronyms This Recommendation uses the following abbreviations and acronyms: ADPCM Adaptive Differential Pulse Code Modulation ASR Automatic Speech Rec

49、ognition DM Dialogue Management HTTP Hypertext Transfer Protocol HTTPS Hypertext Transfer Protocol Secure ID Identifier IPA International Phonetic Alphabet MC Modality Conversion MCML Modality Conversion Markup Language MCP Modality Conversion Protocol MI Multimodal Information MIME Multipurpose Internet Mail Extensions MT Machine Translation PCM Pulse Code Modulation RTP Real-time Transport Protocol S2ST Speech-to-Speech Translation TTS Text-To-Spe