Matches in SemOpenAlex for { <https://semopenalex.org/work/W2718052359> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2718052359 abstract "We propose a speech enhancement algorithm based on single- and multi-microphone processing techniques. The core of the algorithm estimates a time-frequency mask which represents the target speech and use masking-based beamforming to enhance corrupted speech. Specifically, in single-microphone processing, the received signals of a microphone array are treated as individual signals and we estimate a mask for the signal of each microphone using a deep neural network (DNN). With these masks, in multi-microphone processing, we calculate a spatial covariance matrix of noise and steering vector for beamforming. In addition, we propose a masking-based post-filter to further suppress the noise in the output of beamforming. Then, the enhanced speech is sent back to DNN for mask re-estimation. When these steps are iterated for a few times, we obtain the final enhanced speech. The proposed algorithm is evaluated as a frontend for automatic speech recognition (ASR) and achieves a 5.05% average word error rate (WER) on the real environment test set of CHiME-3, outperforming the current best algorithm by 13.34%." @default.
- W2718052359 created "2017-06-30" @default.
- W2718052359 creator A5022772351 @default.
- W2718052359 creator A5045708462 @default.
- W2718052359 creator A5051837453 @default.
- W2718052359 date "2017-03-01" @default.
- W2718052359 modified "2023-09-24" @default.
- W2718052359 title "A speech enhancement algorithm by iterating single- and multi-microphone processing and its application to robust ASR" @default.
- W2718052359 cites W2046317813 @default.
- W2718052359 cites W2069681747 @default.
- W2718052359 cites W2144244295 @default.
- W2718052359 cites W2148613904 @default.
- W2718052359 cites W2158143227 @default.
- W2718052359 cites W2168379380 @default.
- W2718052359 cites W2288645994 @default.
- W2718052359 cites W2289394825 @default.
- W2718052359 cites W2398042854 @default.
- W2718052359 cites W2400339399 @default.
- W2718052359 cites W4245919820 @default.
- W2718052359 doi "https://doi.org/10.1109/icassp.2017.7952161" @default.
- W2718052359 hasPublicationYear "2017" @default.
- W2718052359 type Work @default.
- W2718052359 sameAs 2718052359 @default.
- W2718052359 citedByCount "50" @default.
- W2718052359 countsByYear W27180523592017 @default.
- W2718052359 countsByYear W27180523592018 @default.
- W2718052359 countsByYear W27180523592019 @default.
- W2718052359 countsByYear W27180523592020 @default.
- W2718052359 countsByYear W27180523592021 @default.
- W2718052359 countsByYear W27180523592022 @default.
- W2718052359 countsByYear W27180523592023 @default.
- W2718052359 crossrefType "proceedings-article" @default.
- W2718052359 hasAuthorship W2718052359A5022772351 @default.
- W2718052359 hasAuthorship W2718052359A5045708462 @default.
- W2718052359 hasAuthorship W2718052359A5051837453 @default.
- W2718052359 hasConcept C104267543 @default.
- W2718052359 hasConcept C11413529 @default.
- W2718052359 hasConcept C154945302 @default.
- W2718052359 hasConcept C163294075 @default.
- W2718052359 hasConcept C2776182073 @default.
- W2718052359 hasConcept C2778263558 @default.
- W2718052359 hasConcept C28490314 @default.
- W2718052359 hasConcept C41008148 @default.
- W2718052359 hasConcept C61328038 @default.
- W2718052359 hasConcept C68115822 @default.
- W2718052359 hasConcept C76155785 @default.
- W2718052359 hasConcept C84462506 @default.
- W2718052359 hasConcept C9390403 @default.
- W2718052359 hasConceptScore W2718052359C104267543 @default.
- W2718052359 hasConceptScore W2718052359C11413529 @default.
- W2718052359 hasConceptScore W2718052359C154945302 @default.
- W2718052359 hasConceptScore W2718052359C163294075 @default.
- W2718052359 hasConceptScore W2718052359C2776182073 @default.
- W2718052359 hasConceptScore W2718052359C2778263558 @default.
- W2718052359 hasConceptScore W2718052359C28490314 @default.
- W2718052359 hasConceptScore W2718052359C41008148 @default.
- W2718052359 hasConceptScore W2718052359C61328038 @default.
- W2718052359 hasConceptScore W2718052359C68115822 @default.
- W2718052359 hasConceptScore W2718052359C76155785 @default.
- W2718052359 hasConceptScore W2718052359C84462506 @default.
- W2718052359 hasConceptScore W2718052359C9390403 @default.
- W2718052359 hasLocation W27180523591 @default.
- W2718052359 hasOpenAccess W2718052359 @default.
- W2718052359 hasPrimaryLocation W27180523591 @default.
- W2718052359 hasRelatedWork W2000010996 @default.
- W2718052359 hasRelatedWork W2057718221 @default.
- W2718052359 hasRelatedWork W2105257460 @default.
- W2718052359 hasRelatedWork W2118159520 @default.
- W2718052359 hasRelatedWork W2156393451 @default.
- W2718052359 hasRelatedWork W216105396 @default.
- W2718052359 hasRelatedWork W2365178682 @default.
- W2718052359 hasRelatedWork W2890085347 @default.
- W2718052359 hasRelatedWork W2990774611 @default.
- W2718052359 hasRelatedWork W4322749604 @default.
- W2718052359 isParatext "false" @default.
- W2718052359 isRetracted "false" @default.
- W2718052359 magId "2718052359" @default.
- W2718052359 workType "article" @default.