FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220793814> ?p ?o ?g. }

• W4220793814 abstract "Transcribing speech from audio files to text is an important task not only for exploring the audio content in text form but also for utilizing the transcribed data as a source to train speech models, such as automated speech recognition (ASR) models. A post-correction approach has been frequently employed to reduce the time cost of transcription where users edit errors in the recognition results of ASR models. However, this approach assumes clear speech and is not designed for unclear speech (such as speech with high levels of noise or reverberation), which severely degrades the accuracy of ASR and requires many manual corrections. To construct an alternative approach to transcribe unclear speech, we introduce the idea of respeaking, which has primarily been used to create captions for television programs in real time. In respeaking, a proficient human respeaker repeats the heard speech as shadowing, and their utterances are recognized by an ASR model. While this approach can be effective for transcribing unclear speech, one problem is that respeaking is a highly cognitively demanding task and extensive training is often required to become a respeaker. We address this point with BeParrot, the first interface designed for respeaking that allows novice users to benefit from respeaking without extensive training through two key features: parameter adjustment and pronunciation feedback. Our user study involving 60 crowd workers demonstrated that they could transcribe different types of unclear speech 32.2 % faster with BeParrot than with a conventional approach without losing the accuracy of transcriptions. In addition, comments from the workers supported the design of the adjustment and feedback features, exhibiting a willingness to continue using BeParrot for transcription tasks. Our work demonstrates how we can leverage recent advances in machine learning techniques to overcome the area that is still challenging for computers themselves with the help of a human-in-the-loop approach." @default.
• W4220793814 created "2022-04-03" @default.
• W4220793814 creator A5030650456 @default.
• W4220793814 creator A5044514558 @default.
• W4220793814 creator A5051687457 @default.
• W4220793814 date "2022-03-22" @default.
• W4220793814 modified "2023-10-16" @default.
• W4220793814 title "BeParrot: Efficient Interface for Transcribing Unclear Speech via Respeaking" @default.
• W4220793814 cites W1119960297 @default.
• W4220793814 cites W1527177318 @default.
• W4220793814 cites W1544682780 @default.
• W4220793814 cites W1576919282 @default.
• W4220793814 cites W1876657623 @default.
• W4220793814 cites W1970026646 @default.
• W4220793814 cites W1977757124 @default.
• W4220793814 cites W1987810558 @default.
• W4220793814 cites W1997178453 @default.
• W4220793814 cites W2010910318 @default.
• W4220793814 cites W2050968192 @default.
• W4220793814 cites W2078922236 @default.
• W4220793814 cites W2129120544 @default.
• W4220793814 cites W2143562645 @default.
• W4220793814 cites W2157289187 @default.
• W4220793814 cites W2170101331 @default.
• W4220793814 cites W2183100634 @default.
• W4220793814 cites W2505877856 @default.
• W4220793814 cites W2621461883 @default.
• W4220793814 cites W2627092829 @default.
• W4220793814 cites W272928725 @default.
• W4220793814 cites W2741188008 @default.
• W4220793814 cites W2796141464 @default.
• W4220793814 cites W2801659857 @default.
• W4220793814 cites W28755848 @default.
• W4220793814 cites W2912581782 @default.
• W4220793814 cites W2942475617 @default.
• W4220793814 cites W2962780374 @default.
• W4220793814 cites W2963785710 @default.
• W4220793814 cites W2973216307 @default.
• W4220793814 cites W2981910996 @default.
• W4220793814 cites W3009398997 @default.
• W4220793814 cites W3020336359 @default.
• W4220793814 cites W3030958012 @default.
• W4220793814 cites W3086154751 @default.
• W4220793814 cites W3097777922 @default.
• W4220793814 cites W3098557217 @default.
• W4220793814 cites W3109931032 @default.
• W4220793814 cites W3196843354 @default.
• W4220793814 doi "https://doi.org/10.1145/3490099.3511164" @default.
• W4220793814 hasPublicationYear "2022" @default.
• W4220793814 type Work @default.
• W4220793814 citedByCount "2" @default.
• W4220793814 countsByYear W42207938142022 @default.
• W4220793814 countsByYear W42207938142023 @default.
• W4220793814 crossrefType "proceedings-article" @default.
• W4220793814 hasAuthorship W4220793814A5030650456 @default.
• W4220793814 hasAuthorship W4220793814A5044514558 @default.
• W4220793814 hasAuthorship W4220793814A5051687457 @default.
• W4220793814 hasBestOaLocation W42207938141 @default.
• W4220793814 hasConcept C111472728 @default.
• W4220793814 hasConcept C113843644 @default.
• W4220793814 hasConcept C129307140 @default.
• W4220793814 hasConcept C138885662 @default.
• W4220793814 hasConcept C14999030 @default.
• W4220793814 hasConcept C154945302 @default.
• W4220793814 hasConcept C155635449 @default.
• W4220793814 hasConcept C157915830 @default.
• W4220793814 hasConcept C157968479 @default.
• W4220793814 hasConcept C162324750 @default.
• W4220793814 hasConcept C173608175 @default.
• W4220793814 hasConcept C179926584 @default.
• W4220793814 hasConcept C187736073 @default.
• W4220793814 hasConcept C199360897 @default.
• W4220793814 hasConcept C204201278 @default.
• W4220793814 hasConcept C204321447 @default.
• W4220793814 hasConcept C2524010 @default.
• W4220793814 hasConcept C2780451532 @default.
• W4220793814 hasConcept C2780801425 @default.
• W4220793814 hasConcept C2780844864 @default.
• W4220793814 hasConcept C28490314 @default.
• W4220793814 hasConcept C28719098 @default.
• W4220793814 hasConcept C33923547 @default.
• W4220793814 hasConcept C41008148 @default.
• W4220793814 hasConcept C41895202 @default.
• W4220793814 hasConcept C504749915 @default.
• W4220793814 hasConcept C54953205 @default.
• W4220793814 hasConcept C60048801 @default.
• W4220793814 hasConcept C61328038 @default.
• W4220793814 hasConcept C91863865 @default.
• W4220793814 hasConceptScore W4220793814C111472728 @default.
• W4220793814 hasConceptScore W4220793814C113843644 @default.
• W4220793814 hasConceptScore W4220793814C129307140 @default.
• W4220793814 hasConceptScore W4220793814C138885662 @default.
• W4220793814 hasConceptScore W4220793814C14999030 @default.
• W4220793814 hasConceptScore W4220793814C154945302 @default.
• W4220793814 hasConceptScore W4220793814C155635449 @default.
• W4220793814 hasConceptScore W4220793814C157915830 @default.
• W4220793814 hasConceptScore W4220793814C157968479 @default.
• W4220793814 hasConceptScore W4220793814C162324750 @default.
• W4220793814 hasConceptScore W4220793814C173608175 @default.
• W4220793814 hasConceptScore W4220793814C179926584 @default.

• next