Matches in SemOpenAlex for { <https://semopenalex.org/work/W2955146469> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2955146469 abstract "While the Kaldi framework provides state-of-the-art components for speech recognition like feature extraction, deep neural network (DNN)-based acoustic models, and a weighted finite state transducer (WFST)-based decoder, it is difficult to implement a new flexible DNN model. By contrast, a general-purpose deep learning framework, such as TensorFlow, can easily build various types of neural network architectures using a tensor-based computation method, but it is difficult to apply them to WFST-based speech recognition. In this study, a TensorFlow-based acoustic model is integrated with a WFST-based Kaldi decoder to combine the two frameworks. The features and alignments used in Kaldi are converted so they can be trained by the TensorFlow model, and the DNN-based acoustic model is then trained. In the integrated Kaldi decoder, the posterior probabilities are calculated by querying the trained TensorFlow model, and a beam search is performed to generate the lattice. The advantages of the proposed one-pass decoder include the application of various types of neural networks to WFST-based speech recognition and WFST-based online decoding using a TensorFlow-based acoustic model. The TensorFlow based acoustic models trained using the RM, WSJ, and LibriSpeech datasets show the same level of performance as the model trained using the Kaldi framework." @default.
- W2955146469 created "2019-07-12" @default.
- W2955146469 creator A5008951401 @default.
- W2955146469 creator A5083761261 @default.
- W2955146469 date "2019-06-21" @default.
- W2955146469 modified "2023-09-27" @default.
- W2955146469 title "Integration of TensorFlow based Acoustic Model with Kaldi WFST Decoder." @default.
- W2955146469 cites W1494198834 @default.
- W2955146469 cites W1524333225 @default.
- W2955146469 cites W1548328233 @default.
- W2955146469 cites W2026369565 @default.
- W2955146469 cites W2046932483 @default.
- W2955146469 cites W2076063813 @default.
- W2955146469 cites W2095705004 @default.
- W2955146469 cites W2125234026 @default.
- W2955146469 cites W2152790380 @default.
- W2955146469 cites W2402144811 @default.
- W2955146469 cites W2402146185 @default.
- W2955146469 cites W2513383847 @default.
- W2955146469 cites W2523246573 @default.
- W2955146469 cites W2525778437 @default.
- W2955146469 cites W2577366047 @default.
- W2955146469 cites W2735006420 @default.
- W2955146469 cites W2747135936 @default.
- W2955146469 cites W2761434131 @default.
- W2955146469 cites W2779888504 @default.
- W2955146469 cites W2919115771 @default.
- W2955146469 cites W2949117887 @default.
- W2955146469 cites W2964227577 @default.
- W2955146469 hasPublicationYear "2019" @default.
- W2955146469 type Work @default.
- W2955146469 sameAs 2955146469 @default.
- W2955146469 citedByCount "2" @default.
- W2955146469 countsByYear W29551464692020 @default.
- W2955146469 crossrefType "posted-content" @default.
- W2955146469 hasAuthorship W2955146469A5008951401 @default.
- W2955146469 hasAuthorship W2955146469A5083761261 @default.
- W2955146469 hasConcept C11413529 @default.
- W2955146469 hasConcept C138885662 @default.
- W2955146469 hasConcept C153180895 @default.
- W2955146469 hasConcept C154945302 @default.
- W2955146469 hasConcept C155635449 @default.
- W2955146469 hasConcept C2776401178 @default.
- W2955146469 hasConcept C28490314 @default.
- W2955146469 hasConcept C41008148 @default.
- W2955146469 hasConcept C41895202 @default.
- W2955146469 hasConcept C45374587 @default.
- W2955146469 hasConcept C50644808 @default.
- W2955146469 hasConcept C57273362 @default.
- W2955146469 hasConcept C61328038 @default.
- W2955146469 hasConceptScore W2955146469C11413529 @default.
- W2955146469 hasConceptScore W2955146469C138885662 @default.
- W2955146469 hasConceptScore W2955146469C153180895 @default.
- W2955146469 hasConceptScore W2955146469C154945302 @default.
- W2955146469 hasConceptScore W2955146469C155635449 @default.
- W2955146469 hasConceptScore W2955146469C2776401178 @default.
- W2955146469 hasConceptScore W2955146469C28490314 @default.
- W2955146469 hasConceptScore W2955146469C41008148 @default.
- W2955146469 hasConceptScore W2955146469C41895202 @default.
- W2955146469 hasConceptScore W2955146469C45374587 @default.
- W2955146469 hasConceptScore W2955146469C50644808 @default.
- W2955146469 hasConceptScore W2955146469C57273362 @default.
- W2955146469 hasConceptScore W2955146469C61328038 @default.
- W2955146469 hasLocation W29551464691 @default.
- W2955146469 hasOpenAccess W2955146469 @default.
- W2955146469 hasPrimaryLocation W29551464691 @default.
- W2955146469 hasRelatedWork W1558051944 @default.
- W2955146469 hasRelatedWork W1974979586 @default.
- W2955146469 hasRelatedWork W1986184096 @default.
- W2955146469 hasRelatedWork W2007264691 @default.
- W2955146469 hasRelatedWork W2019973879 @default.
- W2955146469 hasRelatedWork W2077541282 @default.
- W2955146469 hasRelatedWork W2095547148 @default.
- W2955146469 hasRelatedWork W2260961936 @default.
- W2955146469 hasRelatedWork W2291934070 @default.
- W2955146469 hasRelatedWork W2406482790 @default.
- W2955146469 hasRelatedWork W2408532390 @default.
- W2955146469 hasRelatedWork W2742195102 @default.
- W2955146469 hasRelatedWork W2751522352 @default.
- W2955146469 hasRelatedWork W2939862648 @default.
- W2955146469 hasRelatedWork W2944384275 @default.
- W2955146469 hasRelatedWork W2945430712 @default.
- W2955146469 hasRelatedWork W2963684067 @default.
- W2955146469 hasRelatedWork W2967068017 @default.
- W2955146469 hasRelatedWork W3172034247 @default.
- W2955146469 hasRelatedWork W81231479 @default.
- W2955146469 isParatext "false" @default.
- W2955146469 isRetracted "false" @default.
- W2955146469 magId "2955146469" @default.
- W2955146469 workType "article" @default.