FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386078174> ?p ?o ?g. }

• W4386078174 endingPage "3262" @default.
• W4386078174 startingPage "3249" @default.
• W4386078174 abstract "In the air traffic control (ATC) domain, automatic speech recognition (ASR) suffers from radio speech echo, which cannot be addressed by existing echo cancellation due to auditory-oriented optimization and poor generalization ability caused by volatile radio transmission. In this work, a contrastive learning-based framework is proposed to tackle the radio-echo speech for the ASR task based on convolution networks with multiple paths and recurrent neural networks. 1) By analyzing the communication mechanism of the ATC speech, a novel transmission method is designed to collect clean and noisy speech samples (with the same texts) via a bypass device in a real-world ATC environment. 2) To enhance the model capacity, a temporal and frequency attention block is innovatively designed to guide the model to focus on informative frames and frequencies, aiming at learning shared representations between the clean and noisy speech signals with the same texts. 3) By incorporating contrastive loss, the proposed approach is implemented by a multi-objective optimization, in which the loss weights are dynamically determined to enhance the ASR performance in a learnable manner. With the proposed transmission method, a real-world dataset is collected and annotated to validate the proposed approach. Experimental results demonstrate that the proposed approach outperforms other comparative baselines with different technical frameworks, achieving a 6.76% character error rate on the test dataset. Most importantly, all the proposed improvements are confirmed by designed experiments, in which contrastive learning with learnable multi-objective loss weights contributes to the primary performance improvement." @default.
• W4386078174 created "2023-08-23" @default.
• W4386078174 creator A5003270633 @default.
• W4386078174 creator A5050142864 @default.
• W4386078174 creator A5057805812 @default.
• W4386078174 creator A5066617875 @default.
• W4386078174 creator A5068320786 @default.
• W4386078174 creator A5086780566 @default.
• W4386078174 date "2023-01-01" @default.
• W4386078174 modified "2023-10-16" @default.
• W4386078174 title "Towards Recognition for Radio-echo Speech in Air Traffic Control: Dataset and a Contrastive Learning Approach" @default.
• W4386078174 cites W1600744878 @default.
• W4386078174 cites W1990005915 @default.
• W4386078174 cites W1993882792 @default.
• W4386078174 cites W1996809249 @default.
• W4386078174 cites W2005708641 @default.
• W4386078174 cites W2028528924 @default.
• W4386078174 cites W2036242736 @default.
• W4386078174 cites W2101346879 @default.
• W4386078174 cites W2125838338 @default.
• W4386078174 cites W2127141656 @default.
• W4386078174 cites W2160815625 @default.
• W4386078174 cites W2327501763 @default.
• W4386078174 cites W2510616059 @default.
• W4386078174 cites W2563053575 @default.
• W4386078174 cites W2726599793 @default.
• W4386078174 cites W2744227074 @default.
• W4386078174 cites W2798991696 @default.
• W4386078174 cites W2884585870 @default.
• W4386078174 cites W2892009249 @default.
• W4386078174 cites W2899396049 @default.
• W4386078174 cites W2914275764 @default.
• W4386078174 cites W2962780374 @default.
• W4386078174 cites W2963341071 @default.
• W4386078174 cites W2963677766 @default.
• W4386078174 cites W2972389417 @default.
• W4386078174 cites W2972451902 @default.
• W4386078174 cites W2973215447 @default.
• W4386078174 cites W2976884277 @default.
• W4386078174 cites W2991082564 @default.
• W4386078174 cites W3035524453 @default.
• W4386078174 cites W3081285175 @default.
• W4386078174 cites W3099206234 @default.
• W4386078174 cites W3108655343 @default.
• W4386078174 cites W3114632476 @default.
• W4386078174 cites W3129824274 @default.
• W4386078174 cites W3133953372 @default.
• W4386078174 cites W3174448166 @default.
• W4386078174 cites W3197163313 @default.
• W4386078174 cites W3198608154 @default.
• W4386078174 cites W3198853881 @default.
• W4386078174 cites W3212070308 @default.
• W4386078174 cites W4207024570 @default.
• W4386078174 doi "https://doi.org/10.1109/taslp.2023.3307219" @default.
• W4386078174 hasPublicationYear "2023" @default.
• W4386078174 type Work @default.
• W4386078174 citedByCount "0" @default.
• W4386078174 crossrefType "journal-article" @default.
• W4386078174 hasAuthorship W4386078174A5003270633 @default.
• W4386078174 hasAuthorship W4386078174A5050142864 @default.
• W4386078174 hasAuthorship W4386078174A5057805812 @default.
• W4386078174 hasAuthorship W4386078174A5066617875 @default.
• W4386078174 hasAuthorship W4386078174A5068320786 @default.
• W4386078174 hasAuthorship W4386078174A5086780566 @default.
• W4386078174 hasConcept C134306372 @default.
• W4386078174 hasConcept C154945302 @default.
• W4386078174 hasConcept C177148314 @default.
• W4386078174 hasConcept C2779426996 @default.
• W4386078174 hasConcept C28490314 @default.
• W4386078174 hasConcept C31258907 @default.
• W4386078174 hasConcept C33923547 @default.
• W4386078174 hasConcept C40969351 @default.
• W4386078174 hasConcept C41008148 @default.
• W4386078174 hasConcept C81363708 @default.
• W4386078174 hasConceptScore W4386078174C134306372 @default.
• W4386078174 hasConceptScore W4386078174C154945302 @default.
• W4386078174 hasConceptScore W4386078174C177148314 @default.
• W4386078174 hasConceptScore W4386078174C2779426996 @default.
• W4386078174 hasConceptScore W4386078174C28490314 @default.
• W4386078174 hasConceptScore W4386078174C31258907 @default.
• W4386078174 hasConceptScore W4386078174C33923547 @default.
• W4386078174 hasConceptScore W4386078174C40969351 @default.
• W4386078174 hasConceptScore W4386078174C41008148 @default.
• W4386078174 hasConceptScore W4386078174C81363708 @default.
• W4386078174 hasFunder F4320321001 @default.
• W4386078174 hasFunder F4320335787 @default.
• W4386078174 hasLocation W43860781741 @default.
• W4386078174 hasOpenAccess W4386078174 @default.
• W4386078174 hasPrimaryLocation W43860781741 @default.
• W4386078174 hasRelatedWork W2521062615 @default.
• W4386078174 hasRelatedWork W2735477435 @default.
• W4386078174 hasRelatedWork W2807436399 @default.
• W4386078174 hasRelatedWork W3001728219 @default.
• W4386078174 hasRelatedWork W3016958897 @default.
• W4386078174 hasRelatedWork W3038657813 @default.
• W4386078174 hasRelatedWork W3045739591 @default.
• W4386078174 hasRelatedWork W3181746755 @default.
• W4386078174 hasRelatedWork W4283379348 @default.

• next