FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2189136275> ?p ?o ?g. }

• W2189136275 abstract "Deep neural network (DNN)-based approaches have been shown to be effective in many automatic speech recognition systems. However, few works have focused on DNNs for distant-talking speaker recognition. In this study, a bottleneck feature derived from a DNN and a cepstral domain denoising autoencoder (DAE)-based dereverberation are presented for distant-talking speaker identification, and a combination of these two approaches is proposed. For the DNN-based bottleneck feature, we noted that DNNs can transform the reverberant speech feature to a new feature space with greater discriminative classification ability for distant-talking speaker recognition. Conversely, cepstral domain DAE-based dereverberation tries to suppress the reverberation by mapping the cepstrum of reverberant speech to that of clean speech with the expectation of improving the performance of distant-talking speaker recognition. Since the DNN-based discriminant bottleneck feature and DAE-based dereverberation have a strong complementary nature, the combination of these two methods is expected to be very effective for distant-talking speaker identification. A speaker identification experiment was performed on a distant-talking speech set, with reverberant environments differing from the training environments. In suppressing late reverberation, our method outperformed some state-of-the-art dereverberation approaches such as the multichannel least mean squares (MCLMS). Compared with the MCLMS, we obtained a reduction in relative error rates of 21.4% for the bottleneck feature and 47.0% for the autoencoder feature. Moreover, the combination of likelihoods of the DNN-based bottleneck feature and DAE-based dereverberation further improved the performance." @default.
• W2189136275 created "2016-06-24" @default.
• W2189136275 creator A5007092141 @default.
• W2189136275 creator A5036393534 @default.
• W2189136275 creator A5039590086 @default.
• W2189136275 creator A5050763764 @default.
• W2189136275 date "2015-01-01" @default.
• W2189136275 modified "2023-09-24" @default.
• W2189136275 title "Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker" @default.
• W2189136275 cites W1230632900 @default.
• W2189136275 cites W1498436455 @default.
• W2189136275 cites W1840695391 @default.
• W2189136275 cites W1973669708 @default.
• W2189136275 cites W1982846521 @default.
• W2189136275 cites W1989163463 @default.
• W2189136275 cites W1993882792 @default.
• W2189136275 cites W1998229164 @default.
• W2189136275 cites W2005522781 @default.
• W2189136275 cites W2009106392 @default.
• W2189136275 cites W2041823554 @default.
• W2189136275 cites W2042071805 @default.
• W2189136275 cites W2053150333 @default.
• W2189136275 cites W2060108923 @default.
• W2189136275 cites W2069883713 @default.
• W2189136275 cites W2069976350 @default.
• W2189136275 cites W2100495367 @default.
• W2189136275 cites W2107363208 @default.
• W2189136275 cites W2107992675 @default.
• W2189136275 cites W2110322414 @default.
• W2189136275 cites W2112748425 @default.
• W2189136275 cites W2114782757 @default.
• W2189136275 cites W2124248639 @default.
• W2189136275 cites W2128653836 @default.
• W2189136275 cites W2130361043 @default.
• W2189136275 cites W2130640611 @default.
• W2189136275 cites W2132214945 @default.
• W2189136275 cites W2136922672 @default.
• W2189136275 cites W2142117481 @default.
• W2189136275 cites W2145094598 @default.
• W2189136275 cites W2148898720 @default.
• W2189136275 cites W2149390258 @default.
• W2189136275 cites W2151500768 @default.
• W2189136275 cites W2152210587 @default.
• W2189136275 cites W2158541934 @default.
• W2189136275 cites W2160815625 @default.
• W2189136275 cites W2166772024 @default.
• W2189136275 cites W2171666635 @default.
• W2189136275 cites W2195354 @default.
• W2189136275 cites W2245569228 @default.
• W2189136275 cites W2402919203 @default.
• W2189136275 cites W2405774341 @default.
• W2189136275 cites W49995986 @default.
• W2189136275 cites W67398352 @default.
• W2189136275 hasPublicationYear "2015" @default.
• W2189136275 type Work @default.
• W2189136275 sameAs 2189136275 @default.
• W2189136275 citedByCount "0" @default.
• W2189136275 crossrefType "journal-article" @default.
• W2189136275 hasAuthorship W2189136275A5007092141 @default.
• W2189136275 hasAuthorship W2189136275A5036393534 @default.
• W2189136275 hasAuthorship W2189136275A5039590086 @default.
• W2189136275 hasAuthorship W2189136275A5050763764 @default.
• W2189136275 hasConcept C101738243 @default.
• W2189136275 hasConcept C119599485 @default.
• W2189136275 hasConcept C127413603 @default.
• W2189136275 hasConcept C133892786 @default.
• W2189136275 hasConcept C138885662 @default.
• W2189136275 hasConcept C149635348 @default.
• W2189136275 hasConcept C151989614 @default.
• W2189136275 hasConcept C153180895 @default.
• W2189136275 hasConcept C154945302 @default.
• W2189136275 hasConcept C2776401178 @default.
• W2189136275 hasConcept C2780513914 @default.
• W2189136275 hasConcept C28490314 @default.
• W2189136275 hasConcept C41008148 @default.
• W2189136275 hasConcept C41895202 @default.
• W2189136275 hasConcept C50644808 @default.
• W2189136275 hasConcept C52622490 @default.
• W2189136275 hasConcept C83665646 @default.
• W2189136275 hasConcept C88485024 @default.
• W2189136275 hasConcept C95851461 @default.
• W2189136275 hasConcept C97931131 @default.
• W2189136275 hasConceptScore W2189136275C101738243 @default.
• W2189136275 hasConceptScore W2189136275C119599485 @default.
• W2189136275 hasConceptScore W2189136275C127413603 @default.
• W2189136275 hasConceptScore W2189136275C133892786 @default.
• W2189136275 hasConceptScore W2189136275C138885662 @default.
• W2189136275 hasConceptScore W2189136275C149635348 @default.
• W2189136275 hasConceptScore W2189136275C151989614 @default.
• W2189136275 hasConceptScore W2189136275C153180895 @default.
• W2189136275 hasConceptScore W2189136275C154945302 @default.
• W2189136275 hasConceptScore W2189136275C2776401178 @default.
• W2189136275 hasConceptScore W2189136275C2780513914 @default.
• W2189136275 hasConceptScore W2189136275C28490314 @default.
• W2189136275 hasConceptScore W2189136275C41008148 @default.
• W2189136275 hasConceptScore W2189136275C41895202 @default.
• W2189136275 hasConceptScore W2189136275C50644808 @default.
• W2189136275 hasConceptScore W2189136275C52622490 @default.
• W2189136275 hasConceptScore W2189136275C83665646 @default.
• W2189136275 hasConceptScore W2189136275C88485024 @default.

• next