FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2592384597> ?p ?o ?g. }

• W2592384597 endingPage "418" @default.
• W2592384597 startingPage "401" @default.
• W2592384597 abstract "This paper gives an in-depth presentation of the multi-microphone speech recognition system we submitted to the 3rd CHiME speech separation and recognition challenge (CHiME-3) and its extension. The proposed system takes advantage of recurrent neural networks (RNNs) throughout the model from the front-end speech enhancement to the language modeling. Three different types of beamforming are used to combine multi-microphone signals to obtain a single higher-quality signal. The beamformed signal is further processed by a single-channel long short-term memory (LSTM) enhancement network, which is used to extract stacked mel-frequency cepstral coefficients (MFCC) features. In addition, the beamformed signal is processed by two proposed noise-robust feature extraction methods. All features are used for decoding in speech recognition systems with deep neural network (DNN) based acoustic models and large-scale RNN language models to achieve high recognition accuracy in noisy environments. Our training methodology includes multi-channel noisy data training and speaker adaptive training, whereas at test time model combination is used to improve generalization. Results on the CHiME-3 benchmark show that the full set of techniques substantially reduced the word error rate (WER). Combining hypotheses from different beamforming and robust-feature systems ultimately achieved 5.05% WER for the real-test data, an 84.7% reduction relative to the baseline of 32.99% WER and a 44.5% reduction from our official CHiME-3 challenge result of 9.1% WER. Furthermore, this final result is better than the best result (5.8% WER) reported in the CHiME-3 challenge." @default.
• W2592384597 created "2017-03-16" @default.
• W2592384597 creator A5001291873 @default.
• W2592384597 creator A5017825677 @default.
• W2592384597 creator A5065994318 @default.
• W2592384597 creator A5076453358 @default.
• W2592384597 creator A5082524152 @default.
• W2592384597 creator A5087554069 @default.
• W2592384597 creator A5091201226 @default.
• W2592384597 date "2017-11-01" @default.
• W2592384597 modified "2023-10-18" @default.
• W2592384597 title "Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN/RNN backend" @default.
• W2592384597 cites W1935589317 @default.
• W2592384597 cites W1993721840 @default.
• W2592384597 cites W2002342963 @default.
• W2592384597 cites W2035576074 @default.
• W2592384597 cites W2037057286 @default.
• W2592384597 cites W2069681747 @default.
• W2592384597 cites W2070707809 @default.
• W2592384597 cites W2075012882 @default.
• W2592384597 cites W2107878631 @default.
• W2592384597 cites W2108072369 @default.
• W2592384597 cites W2108767768 @default.
• W2592384597 cites W2148613904 @default.
• W2592384597 cites W2156960608 @default.
• W2592384597 cites W2158143227 @default.
• W2592384597 cites W2168729028 @default.
• W2592384597 doi "https://doi.org/10.1016/j.csl.2017.01.013" @default.
• W2592384597 hasPublicationYear "2017" @default.
• W2592384597 type Work @default.
• W2592384597 sameAs 2592384597 @default.
• W2592384597 citedByCount "23" @default.
• W2592384597 countsByYear W25923845972018 @default.
• W2592384597 countsByYear W25923845972019 @default.
• W2592384597 countsByYear W25923845972020 @default.
• W2592384597 countsByYear W25923845972021 @default.
• W2592384597 countsByYear W25923845972022 @default.
• W2592384597 crossrefType "journal-article" @default.
• W2592384597 hasAuthorship W2592384597A5001291873 @default.
• W2592384597 hasAuthorship W2592384597A5017825677 @default.
• W2592384597 hasAuthorship W2592384597A5065994318 @default.
• W2592384597 hasAuthorship W2592384597A5076453358 @default.
• W2592384597 hasAuthorship W2592384597A5082524152 @default.
• W2592384597 hasAuthorship W2592384597A5087554069 @default.
• W2592384597 hasAuthorship W2592384597A5091201226 @default.
• W2592384597 hasConcept C104317684 @default.
• W2592384597 hasConcept C11413529 @default.
• W2592384597 hasConcept C137293760 @default.
• W2592384597 hasConcept C147168706 @default.
• W2592384597 hasConcept C151989614 @default.
• W2592384597 hasConcept C153180895 @default.
• W2592384597 hasConcept C154945302 @default.
• W2592384597 hasConcept C163294075 @default.
• W2592384597 hasConcept C185592680 @default.
• W2592384597 hasConcept C2776182073 @default.
• W2592384597 hasConcept C2778263558 @default.
• W2592384597 hasConcept C28490314 @default.
• W2592384597 hasConcept C40969351 @default.
• W2592384597 hasConcept C41008148 @default.
• W2592384597 hasConcept C50644808 @default.
• W2592384597 hasConcept C52622490 @default.
• W2592384597 hasConcept C54197355 @default.
• W2592384597 hasConcept C55493867 @default.
• W2592384597 hasConcept C57273362 @default.
• W2592384597 hasConcept C63479239 @default.
• W2592384597 hasConcept C68115822 @default.
• W2592384597 hasConcept C76155785 @default.
• W2592384597 hasConceptScore W2592384597C104317684 @default.
• W2592384597 hasConceptScore W2592384597C11413529 @default.
• W2592384597 hasConceptScore W2592384597C137293760 @default.
• W2592384597 hasConceptScore W2592384597C147168706 @default.
• W2592384597 hasConceptScore W2592384597C151989614 @default.
• W2592384597 hasConceptScore W2592384597C153180895 @default.
• W2592384597 hasConceptScore W2592384597C154945302 @default.
• W2592384597 hasConceptScore W2592384597C163294075 @default.
• W2592384597 hasConceptScore W2592384597C185592680 @default.
• W2592384597 hasConceptScore W2592384597C2776182073 @default.
• W2592384597 hasConceptScore W2592384597C2778263558 @default.
• W2592384597 hasConceptScore W2592384597C28490314 @default.
• W2592384597 hasConceptScore W2592384597C40969351 @default.
• W2592384597 hasConceptScore W2592384597C41008148 @default.
• W2592384597 hasConceptScore W2592384597C50644808 @default.
• W2592384597 hasConceptScore W2592384597C52622490 @default.
• W2592384597 hasConceptScore W2592384597C54197355 @default.
• W2592384597 hasConceptScore W2592384597C55493867 @default.
• W2592384597 hasConceptScore W2592384597C57273362 @default.
• W2592384597 hasConceptScore W2592384597C63479239 @default.
• W2592384597 hasConceptScore W2592384597C68115822 @default.
• W2592384597 hasConceptScore W2592384597C76155785 @default.
• W2592384597 hasFunder F4320322626 @default.
• W2592384597 hasLocation W25923845971 @default.
• W2592384597 hasOpenAccess W2592384597 @default.
• W2592384597 hasPrimaryLocation W25923845971 @default.
• W2592384597 hasRelatedWork W1491017269 @default.
• W2592384597 hasRelatedWork W2027890689 @default.
• W2592384597 hasRelatedWork W2185164075 @default.
• W2592384597 hasRelatedWork W2289731793 @default.
• W2592384597 hasRelatedWork W2536442632 @default.

• next