Matches in ScholarlyData for { ?s ?p ?o. }
- item-1 hasContent dan-tufis.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent radu-ion.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent alexandru-ceausu.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent dan-stefanescu.
- item-4 previous item-3.
- 900 creator djamel-mostefa.
- 900 creator olivier-hamon.
- 900 type InProceedings.
- 900 label "An Experimental Methodology for an End-to-End Evaluation in Speech-to-Speech Translation".
- 900 sameAs 900.
- 900 abstract "This paper describes the evaluation methodology used to evaluate the TC-STAR speech-to-speech translation (SST) system and the results from the third year of the project. It follows the results presented in Hamon (2007), dealing with the first end-to-end evaluation of the project. In this paper, we try to experiment with the methodology and the protocol during a second end-to-end evaluation, by comparing outputs from the TC-STAR system with interpreters from the European parliament. For this purpose, we test different criteria of evaluation and type of questions within a comprehension test. The results show that interpreters do not translate all the information (as opposed to the automatic system), but the quality of SST is still far from that of human translation. The experimental comprehension test used provides new information to study the quality of automatic systems, but without settling the issue of which protocol is the best. This depends on what the evaluator wants to know about the SST: either to have a subjective end-user evaluation or a more objective one.".
- 900 hasAuthorList authorList.
- 900 hasTopic Linguistics.
- 900 isPartOf proceedings.
- 900 keyword "Evaluation methodologies".
- 900 keyword "Machine Translation, SpeechToSpeech Translation".
- 900 title "An Experimental Methodology for an End-to-End Evaluation in Speech-to-Speech Translation".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent olivier-hamon.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent djamel-mostefa.
- item-2 previous item-1.
- 901 creator arnaud-vallee.
- 901 creator djamel-mostefa.
- 901 type InProceedings.
- 901 label "New Telephone Speech Databases for French: a Children Database and an optimized Adult Corpus".
- 901 sameAs 901.
- 901 abstract "This paper presents the results of the NEOLOGOS project: a children database and an optimized adult database for the French language. A new approach was adopted for the collection of the adult database in order to enable the development of new algorithms in the field of speech processing (study of speaker characteristics, speakers similarity, speaker selection algorithms, etc.) The objective here was to define and to carry out a new methodology for collecting significant quantities of speaker dependent data, for a significant number of speakers, as was done for several databases oriented towards speaker verification, but with the additional constraint of maximising the coverage of the space of all speakers. The children database is made of 1,000 sessions recorded by children between 7 and 16 years old. Both speech databases are SpeehDat-compliant meaning that they can be easily used for research and development in the field of speech technology.".
- 901 hasAuthorList authorList.
- 901 hasTopic Linguistics.
- 901 isPartOf proceedings.
- 901 keyword "Speech recognition and understanding".
- 901 keyword "Speech resource/database".
- 901 title "New Telephone Speech Databases for French: a Children Database and an optimized Adult Corpus".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent djamel-mostefa.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent arnaud-vallee.
- item-2 previous item-1.
- 902 creator abby-neely.
- 902 creator christopher-cieri.
- 902 creator david-graff.
- 902 creator kevin-walker.
- 902 creator linda-brandschain.
- 902 type InProceedings.
- 902 label "Speaker Recognition: Building the Mixer 4 and 5 Corpora".
- 902 sameAs 902.
- 902 abstract "The original Mixer corpus was designed to satisfy developing commercial and forensic needs. The resulting Mixer corpora, Phases 1 through 5, have evolved to support and increasing variety of research tasks, including multilingual and cross-channel recognition. The Mixer Phases 4 and 5 corpora feature a wider variety of channels and greater variation in the situations under which the speech is recorded. This paper focuses on the plans, progress and results of Mixer 4 and 5.".
- 902 hasAuthorList authorList.
- 902 hasTopic Linguistics.
- 902 isPartOf proceedings.
- 902 keyword "Corpus (creation, annotation, etc.)".
- 902 keyword "Speech recognition and understanding".
- 902 keyword "Speech resource/database".
- 902 title "Speaker Recognition: Building the Mixer 4 and 5 Corpora".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasLastItem item-5.
- item-1 type ListItem.
- item-1 hasContent linda-brandschain.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent christopher-cieri.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent david-graff.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent abby-neely.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent kevin-walker.