Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554080800> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2554080800 abstract "Preparing data for speech processing applications is in general a task which requires expert knowledge and takes up a large amount of time. Therefore, being able to automate as much as possible this process can have a significant impact on the expansion of the number of languages for which spoken interaction with the machines is available. In this paper we build upon a previously developed tool, ALISA, which was developed to align speech with imperfect transcripts using only 10 minutes of manually labelled data, in any alphabetic language. Although its error rate is around 0.6% at word-level, we noticed that the sentence-level accuracy is drastically affected by a large number of sentence-initial word deletions. To overcome this problem, we propose two methods: one based on utterance concatenation, and one based on voice activity detection (VAD). The results show that these simple methods can achieve around 10% relative improvement over the baseline results." @default.
- W2554080800 created "2016-11-30" @default.
- W2554080800 creator A5018126799 @default.
- W2554080800 creator A5038722127 @default.
- W2554080800 creator A5076973065 @default.
- W2554080800 date "2016-09-01" @default.
- W2554080800 modified "2023-09-23" @default.
- W2554080800 title "Improving sentence-level alignment of speech with imperfect transcripts using utterance concatenation and VAD" @default.
- W2554080800 cites W10731371 @default.
- W2554080800 cites W1245895196 @default.
- W2554080800 cites W1500331947 @default.
- W2554080800 cites W1516533146 @default.
- W2554080800 cites W1517939602 @default.
- W2554080800 cites W1970101118 @default.
- W2554080800 cites W2015412875 @default.
- W2554080800 cites W2105961775 @default.
- W2554080800 cites W2107457864 @default.
- W2554080800 cites W2181715383 @default.
- W2554080800 cites W2250270880 @default.
- W2554080800 cites W2533495 @default.
- W2554080800 cites W47863446 @default.
- W2554080800 cites W85707815 @default.
- W2554080800 cites W943204654 @default.
- W2554080800 doi "https://doi.org/10.1109/iccp.2016.7737141" @default.
- W2554080800 hasPublicationYear "2016" @default.
- W2554080800 type Work @default.
- W2554080800 sameAs 2554080800 @default.
- W2554080800 citedByCount "1" @default.
- W2554080800 countsByYear W25540808002017 @default.
- W2554080800 crossrefType "proceedings-article" @default.
- W2554080800 hasAuthorship W2554080800A5018126799 @default.
- W2554080800 hasAuthorship W2554080800A5038722127 @default.
- W2554080800 hasAuthorship W2554080800A5076973065 @default.
- W2554080800 hasConcept C111919701 @default.
- W2554080800 hasConcept C138885662 @default.
- W2554080800 hasConcept C154945302 @default.
- W2554080800 hasConcept C162324750 @default.
- W2554080800 hasConcept C187736073 @default.
- W2554080800 hasConcept C204321447 @default.
- W2554080800 hasConcept C2775852435 @default.
- W2554080800 hasConcept C2777530160 @default.
- W2554080800 hasConcept C2780310539 @default.
- W2554080800 hasConcept C2780451532 @default.
- W2554080800 hasConcept C28490314 @default.
- W2554080800 hasConcept C33923547 @default.
- W2554080800 hasConcept C40969351 @default.
- W2554080800 hasConcept C41008148 @default.
- W2554080800 hasConcept C41895202 @default.
- W2554080800 hasConcept C87619178 @default.
- W2554080800 hasConcept C90805587 @default.
- W2554080800 hasConcept C94375191 @default.
- W2554080800 hasConcept C98045186 @default.
- W2554080800 hasConceptScore W2554080800C111919701 @default.
- W2554080800 hasConceptScore W2554080800C138885662 @default.
- W2554080800 hasConceptScore W2554080800C154945302 @default.
- W2554080800 hasConceptScore W2554080800C162324750 @default.
- W2554080800 hasConceptScore W2554080800C187736073 @default.
- W2554080800 hasConceptScore W2554080800C204321447 @default.
- W2554080800 hasConceptScore W2554080800C2775852435 @default.
- W2554080800 hasConceptScore W2554080800C2777530160 @default.
- W2554080800 hasConceptScore W2554080800C2780310539 @default.
- W2554080800 hasConceptScore W2554080800C2780451532 @default.
- W2554080800 hasConceptScore W2554080800C28490314 @default.
- W2554080800 hasConceptScore W2554080800C33923547 @default.
- W2554080800 hasConceptScore W2554080800C40969351 @default.
- W2554080800 hasConceptScore W2554080800C41008148 @default.
- W2554080800 hasConceptScore W2554080800C41895202 @default.
- W2554080800 hasConceptScore W2554080800C87619178 @default.
- W2554080800 hasConceptScore W2554080800C90805587 @default.
- W2554080800 hasConceptScore W2554080800C94375191 @default.
- W2554080800 hasConceptScore W2554080800C98045186 @default.
- W2554080800 hasLocation W25540808001 @default.
- W2554080800 hasOpenAccess W2554080800 @default.
- W2554080800 hasPrimaryLocation W25540808001 @default.
- W2554080800 hasRelatedWork W1490555469 @default.
- W2554080800 hasRelatedWork W1557242051 @default.
- W2554080800 hasRelatedWork W1603553412 @default.
- W2554080800 hasRelatedWork W1995002252 @default.
- W2554080800 hasRelatedWork W2001537489 @default.
- W2554080800 hasRelatedWork W2048684118 @default.
- W2554080800 hasRelatedWork W2074382434 @default.
- W2554080800 hasRelatedWork W2079362249 @default.
- W2554080800 hasRelatedWork W2097399990 @default.
- W2554080800 hasRelatedWork W2100761554 @default.
- W2554080800 hasRelatedWork W2178770890 @default.
- W2554080800 hasRelatedWork W2256811946 @default.
- W2554080800 hasRelatedWork W2397926608 @default.
- W2554080800 hasRelatedWork W2530045276 @default.
- W2554080800 hasRelatedWork W2762430255 @default.
- W2554080800 hasRelatedWork W2780038876 @default.
- W2554080800 hasRelatedWork W2892009249 @default.
- W2554080800 hasRelatedWork W3037354152 @default.
- W2554080800 hasRelatedWork W3174102645 @default.
- W2554080800 hasRelatedWork W2182518606 @default.
- W2554080800 isParatext "false" @default.
- W2554080800 isRetracted "false" @default.
- W2554080800 magId "2554080800" @default.
- W2554080800 workType "article" @default.