a speech understanding architecture

Báo cáo khoa học: "Transparent combination of rule-based and data-driven approaches in a speech understanding architecture" pot

Báo cáo khoa học: "Transparent combination of rule-based and data-driven approaches in a speech understanding architecture" pot

Ngày tải lên : 08/03/2014, 21:20
... pattern for 305 Transparent combination of rule-based and data-driven approaches in a speech understanding architecture Manny Rayner and Beth Ann Hockey RIACS, Mail Stop T2 7A- 2 NASA Ames Research ... Semantic analysis as classification This section describes an abstract architecture which characterises semantic analysis as a task slightly extending the "decision-list" classification algorithm ... which are within grammar cov- erage. There is not a great deal of training data available, and the statistical methods used are sim- ple and unsophisticated. However, we still get a significant...
  • 8
  • 461
  • 0
Planning a Service-Oriented Architecture

Planning a Service-Oriented Architecture

Ngày tải lên : 20/08/2012, 11:43
... Service-Oriented Architecture [] agent including features such as its implementation language, process structure, and even database struc- ture are deliberately abstracted away in the SOA. By using the SOA ... there's a greater opportunity to leverage fragmented applications and processes and reuse them again and again across the enterprise. For example, if one application in the marketing depart- ment ... elimination of redundancy and breaking silos, SOAs should bring increased opera- tional simplicity allowing dialing cost increases to a sus- tainable rate. The elimination of redundancy and a 15%...
  • 9
  • 745
  • 4
Tài liệu Báo cáo khoa học: "A SPEECH-FIRST MODEL FOR REPAIR DETECTION AND CORRECTION" docx

Tài liệu Báo cáo khoa học: "A SPEECH-FIRST MODEL FOR REPAIR DETECTION AND CORRECTION" docx

Ngày tải lên : 20/02/2014, 21:20
... glottalization is usually associated with fragments, not all fragments are glottalized. In our database, 62% of fragments are not glottalized, and 9% of glottalized reparanda offsets are ... initially repaired utterance 'What airport is located' is itself repaired, with the reparadum again delimited by a single prosodic phrase, 'What is the name of the airport located ... these cases as repairs, as well as to distinguish them from nonfrag- ment repairs. Thus, pausal duration may serve as a general acoustic cue for repair detection, particularly for the class...
  • 8
  • 502
  • 0
A Key Management Architecture for Digital Cinema ppt

A Key Management Architecture for Digital Cinema ppt

Ngày tải lên : 07/03/2014, 14:20
... cryptographic mechanisms. SPBs shall carry an RSA private key [8] and a matching digital certificate stating their role, as to allow authentication by a Security Manager or another SPB. After ... Filmförderungsanstalt. Marktdaten - Kinosaalbestand 2005 bis 2009. http://www.ffa.de/start/download.php?file=marktdaten/1_Fuenf_Jahre_Blick/04bis09_jahresabschluss.pdf. [3] European Audiovisual Observatory. ... on a certification asserting their security. Since CAs are trusted by default, a hypothetical attacker could forge a player certificate and certificate chain and send them both to a KDM creating...
  • 8
  • 491
  • 0
Báo cáo khoa học: "A Speech-based Just-in-Time Retrieval System using Semantic Search" doc

Báo cáo khoa học: "A Speech-based Just-in-Time Retrieval System using Semantic Search" doc

Ngày tải lên : 07/03/2014, 22:20
... Search Andrei Popescu-Belis, Majid Yazdani, Alexandre Nanchen, and Philip N. Garner Idiap Research Institute Rue Marconi 19, CP 592 1920 Martigny, Switzerland {apbelis,myazdani,ananchen,pgarner}@idiap.ch Abstract The ... Communication Association), pages 2119–2122, Brighton, UK. Masataka Goto, Koji Kitayama, Katsunobu Itou, and Tet- sunori Kobayashi. 2004. Speech Spotter: On-demand speech recognition in human-human ... Hain, Asmaa El Hannani, Martin Karafiat, Danil Korchagin, Mike Lincoln, Vincent Wan, and Le Zhang. 2009. Real- time ASR from meetings. In Interspeech 2009 (10th Annual Conference of the Intl. Speech...
  • 6
  • 378
  • 0
Báo cáo khoa học: "A speech interface for open-domain question-answering" doc

Báo cáo khoa học: "A speech interface for open-domain question-answering" doc

Ngày tải lên : 08/03/2014, 04:22
... Content-Based Multimedia In- formation Access Conf., apr. J. Kupiec, D. Kimber, and V. Balasubramanian. 1994. Speech- based retrieval using semantic co-occurrence filtering. In Proc. ARPA Human Lang. ... Australia has rain forests? it answered correctly, but the transcription What city in Australia has rainforests (without a space), got no answers. Another example: Q35 Who won the No- bel Peace Prize ... Computational Linguistics Saarland University Saarbr ¨ ucken, Germany zheng@coli.uni-sb.de Abstract Speech interfaces to question-answering systems offer significant potentialfor find- ing information...
  • 4
  • 276
  • 0
A Layered Naming Architecture for the Internet doc

A Layered Naming Architecture for the Internet doc

Ngày tải lên : 15/03/2014, 22:20
... cryptograph- ically strong identifier, as in HIP, may be preferable for security reasons. FARA[8] is a meta -architecture that actual network architectures could “instantiate.” In FARA, the basic ... [59], and Open Network Handles [37] take an entirely different approach: they advocate a single new flat namespace that can serve all present and future net- work elements. A flat namespace has no ... I. Castineyra, N. Chiappa, and M. Steenstrup. The Nimrod routing architecture, August 1996. RFC 1992. [8] D. Clark, R. Braden, A. Falk, and V. Pingali. FARA: Reorganizing the addressing architecture. ...
  • 10
  • 413
  • 0
Báo cáo khoa học: "User Expertise Modelling and Adaptivity in a Speech-based E-mail System" doc

Báo cáo khoa học: "User Expertise Modelling and Adaptivity in a Speech-based E-mail System" doc

Ngày tải lên : 23/03/2014, 19:20
... messages about Re: Comments about the draft. The first message is from Matti Hahtomaa, the second from Jaana Jaakkola, the third from Sakari Rantala. If you want to select a message, say for ... lines. U: Read Sakari Rantala's message. S: Third message, from Sakari Rantala, about Re: Comments about the draft. [reads the message] Message read. You are in the first message group. ... hear the message, say "read". You can have additional information about the message by saying "tell me more". U: Second message. S: Second message, from Jaana Jaakkola,...
  • 8
  • 420
  • 0
Báo cáo khoa học: "Spontaneous Speech Understanding for Robust " potx

Báo cáo khoa học: "Spontaneous Speech Understanding for Robust " potx

Ngày tải lên : 31/03/2014, 01:20
... from the semantic analysis based on the real speech recognition re- 396 matically. The utterance “that” can also represent an anaphora, and is analyzed in both ways, as anaphora and as gesture ... lexicon and the concept database are based on our experimental data of situated communication (see section 3) and also on data of a home-tour scenario with a real robot. This data has been an- notated ... XML-databases. As the speech understanding module starts, it first reads these databases and converts them into internal data-structures stored in a fast accessible hash ta- ble. As soon as the...
  • 8
  • 163
  • 0
Báo cáo khoa học: "From RAGS to RICHES: exploiting the potential of a flexible generation architecture" pot

Báo cáo khoa học: "From RAGS to RICHES: exploiting the potential of a flexible generation architecture" pot

Ngày tải lên : 31/03/2014, 04:20
... based on small scale functionally-motivated units. 3 OASYS OASYS (Objects and Arrows SYStem) is a soft- ware library which provides: an implementation of the RAGS Object and Arrows (O /A) data ... needs to have access to at least rhetorical and document information as well as referencing and adding to the syntactic information. To accommodate this, the RAGS data model in- cludes a more concrete ... typed ‘arrows’. This lingua franca allows NLG modules to manipulate data flexibly and consistently. It also facilitates modular design of NLG systems, and reusability of modules and data sets....
  • 8
  • 368
  • 0
Báo cáo khoa học: "MULTILEVEL SEMANTIC ANALYSIS IN AN AUTOMATIC SPEECH UNDERSTANDING AND DIALOG SYSTEM" pptx

Báo cáo khoa học: "MULTILEVEL SEMANTIC ANALYSIS IN AN AUTOMATIC SPEECH UNDERSTANDING AND DIALOG SYSTEM" pptx

Ngày tải lên : 01/04/2014, 00:20
... has in addition the information in which case frame it can appear. 87 For example: coach coach.l.l: .'railway carriage" CLAS~ TRAnsport, LOCation coach.l.2: "privat tutor, ... several different contexts and that too many combinations have to be checked. So the dictionary is organized in a way that all acrants of all frames with the same serrantic restriction and ... the semantic module with additional syntactic knowledge. The analysis is based on the valency and case theory. All verbs, but also some nouns and adjectives are associated with case frames which...
  • 7
  • 275
  • 0
A Study on Architecture Description Languages

A Study on Architecture Description Languages

Ngày tải lên : 12/04/2014, 15:42
... Software Architecture Description Languages for Modeling and Analysis of Federates and Federation Architectures [11] Ahmad Waqas Kamal, Paris Avgeriou - An Evaluation of ADLs on Modeling Patterns ... back as an ADL interchange language but has evolved to an ADL itself. ACME has advantages of general notation, readable by both human and machine, and a strong support of ACME Studio – an well ... facilitated by a formal representation of the architecture, such as with an ADL. A formal architecture representation is more likely to be maintained and followed than an informal one, can more readily...
  • 25
  • 149
  • 0