| other,8-1-H01-1017,bq | To support engaging human users in robust , <term> mixed-initiative speech dialogue interactions </term> which reach beyond current capabilities in <term> dialogue systems </term> , the <term> DARPA Communicator program </term> [ 1 ] is funding the development of a <term> distributed message-passing infrastructure </term> for <term> dialogue systems </term> which all <term> Communicator </term> participants are using . | #215 To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using. |
| tech,4-2-H01-1055,bq | However , the improved <term> speech recognition </term> has brought to light a new problem : as <term> dialog systems </term> understand more of what the <term> user </term> tells them , they need to be more sophisticated at responding to the <term> user </term> . | #934 However, the improvedspeech recognition has brought to light a new problem: as dialog systems understand more of what the user tells them, they need to be more sophisticated at responding to the user. |
| other,26-1-N01-1003,bq | <term> Sentence planning </term> is a set of inter-related but distinct tasks , one of which is <term> sentence scoping </term> , i.e. the choice of <term> syntactic structure </term> for elementary <term> speech acts </term> and the decision of how to combine them into one or more <term> sentences </term> . | #1319 Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementaryspeech acts and the decision of how to combine them into one or more sentences. |
| other,10-2-N03-1012,bq | We apply our <term> system </term> to the task of <term> scoring </term> alternative <term> speech recognition hypotheses ( SRH ) </term> in terms of their <term> semantic coherence </term> . | #2466 We apply our system to the task of scoring alternativespeech recognition hypotheses (SRH) in terms of their semantic coherence. |
| other,18-3-N03-1012,bq | We conducted an <term> annotation experiment </term> and showed that <term> human annotators </term> can reliably differentiate between semantically coherent and incoherent <term> speech recognition hypotheses </term> . | #2497 We conducted an annotation experiment and showed that human annotators can reliably differentiate between semantically coherent and incoherentspeech recognition hypotheses. |
| other,9-1-N03-2003,bq | Sources of <term> training data </term> suitable for <term> language modeling </term> of <term> conversational speech </term> are limited . | #3024 Sources of training data suitable for language modeling of conversational speech are limited. |
| tech,15-3-P03-1030,bq | Motivated by these arguments , we introduce a number of new performance enhancing techniques including <term> part of speech tagging </term> , new <term> similarity measures </term> and expanded <term> stop lists </term> . | #4109 Motivated by these arguments, we introduce a number of new performance enhancing techniques including part of speech tagging, new similarity measures and expanded stop lists. |
| tech,19-3-P03-1031,bq | Since multiple <term> candidates </term> for the <term> understanding </term> result can be obtained for a <term> user utterance </term> due to the <term> ambiguity </term> of <term> speech understanding </term> , it is not appropriate to decide on a single <term> understandingresult </term> after each <term> user utterance </term> . | #4174 Since multiple candidates for the understanding result can be obtained for a user utterance due to the ambiguity ofspeech understanding, it is not appropriate to decide on a single understandingresult after each user utterance. |
| other,8-1-C04-1103,bq | <term> Machine transliteration/back-transliteration </term> plays an important role in many <term> multilingual speech and language applications </term> . | #5738 Machine transliteration/back-transliteration plays an important role in many multilingual speech and language applications. |
| other,12-3-I05-5003,bq | We also introduce a novel <term> classification method </term> based on <term> PER </term> which leverages <term> part of speech information </term> of the <term> words </term> contributing to the <term> word matches and non-matches </term> in the <term> sentence </term> . | #8381 We also introduce a novel classification method based on PER which leverages part of speech information of the words contributing to the word matches and non-matches in the sentence. |
| tech,36-12-J05-1003,bq | Although the experiments in this article are on <term> natural language parsing ( NLP ) </term> , the <term> approach </term> should be applicable to many other <term> NLP problems </term> which are naturally framed as <term> ranking tasks </term> , for example , <term> speech recognition </term> , <term> machine translation </term> , or <term> natural language generation </term> . | #8972 Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example,speech recognition, machine translation, or natural language generation. |
| other,70-5-E06-1035,bq | Examination of the effect of <term> features </term> shows that <term> predicting top-level and predicting subtopic boundaries </term> are two distinct tasks : ( 1 ) for predicting <term> subtopic boundaries </term> , the <term> lexical cohesion-based approach </term> alone can achieve competitive results , ( 2 ) for <term> predicting top-level boundaries </term> , the <term> machine learning approach </term> that combines <term> lexical-cohesion and conversational features </term> performs best , and ( 3 ) <term> conversational cues </term> , such as <term> cue phrases </term> and <term> overlapping speech </term> , are better indicators for the top-level prediction task . | #10597 Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks: (1) for predicting subtopic boundaries, the lexical cohesion-based approach alone can achieve competitive results, (2) for predicting top-level boundaries, the machine learning approach that combines lexical-cohesion and conversational features performs best, and (3) conversational cues, such as cue phrases and overlapping speech, are better indicators for the top-level prediction task. |
| tech,16-2-C90-3014,bq | The approach of <term> KPSG provides </term> an explicit development model for constructing a computational <term> phonological system </term> : <term> speech recognition </term> and <term> synthesis system </term> . | #16397 The approach of KPSG provides an explicit development model for constructing a computational phonological system:speech recognition and synthesis system. |
| other,7-1-H90-1060,bq | This paper reports on two contributions to <term> large vocabulary continuous speech recognition </term> . | #16985 This paper reports on two contributions to large vocabulary continuous speech recognition. |
| lr,27-2-H90-1060,bq | First , we present a new paradigm for <term> speaker-independent ( SI ) training </term> of <term> hidden Markov models ( HMM ) </term> , which uses a large amount of <term> speech </term> from a few <term> speakers </term> instead of the traditional practice of using a little <term> speech </term> from many <term> speakers </term> . | #17015 First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount ofspeech from a few speakers instead of the traditional practice of using a little speech from many speakers. |
| lr,41-2-H90-1060,bq | First , we present a new paradigm for <term> speaker-independent ( SI ) training </term> of <term> hidden Markov models ( HMM ) </term> , which uses a large amount of <term> speech </term> from a few <term> speakers </term> instead of the traditional practice of using a little <term> speech </term> from many <term> speakers </term> . | #17029 First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount of speech from a few speakers instead of the traditional practice of using a littlespeech from many speakers. |
| lr,27-3-H90-1060,bq | In addition , combination of the <term> training speakers </term> is done by averaging the <term> statistics > </term> of <term> independently trained models </term> rather than the usual pooling of all the <term> speech data </term> from many <term> speakers </term> prior to <term> training </term> . | #17061 In addition, combination of the training speakers is done by averaging the statistics> of independently trained models rather than the usual pooling of all thespeech data from many speakers prior to training. |
| lr,23-6-H90-1060,bq | Second , we show a significant improvement for <term> speaker adaptation ( SA ) </term> using the new <term> SI corpus </term> and a small amount of <term> speech </term> from the new ( target ) <term> speaker </term> . | #17142 Second, we show a significant improvement for speaker adaptation (SA) using the new SI corpus and a small amount ofspeech from the new (target) speaker. |
| tech,5-1-C92-3165,bq | This paper introduces a robust <term> interactive method for speech understanding </term> . | #18146 This paper introduces a robust interactive method for speech understanding. |
| other,35-3-H92-1003,bq | We summarize the motivation for this effort , the goals , the implementation of a <term> multi-site data collection paradigm </term> , and the accomplishments of <term> MADCOW </term> in monitoring the <term> collection </term> and distribution of 12,000 <term> utterances </term> of <term> spontaneous speech </term> from five sites for use in a <term> multi-site common evaluation of speech , natural language and spoken language | #18598 We summarize the motivation for this effort, the goals, the implementation of a multi-site data collection paradigm, and the accomplishments of MADCOW in monitoring the collection and distribution of 12,000 utterances of spontaneous speech from five sites for use in a multi-site common evaluation of speech, natural language and spoken language |
