Matches in SemOpenAlex for { <https://semopenalex.org/work/W2743452000> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2743452000 endingPage "42" @default.
- W2743452000 startingPage "31" @default.
- W2743452000 abstract "Owing to the success of deep learning techniques in automatic speech recognition, deep neural networks (DNNs) have been used as acoustic models for statistical parametric speech synthesis (SPSS). DNNs do not inherently model the temporal structure in speech and text, and hence are not well suited to be directly applied to the problem of SPSS. Recurrent neural networks (RNN) on the other hand have the capability to model time-series. RNNs with long short-term memory (LSTM) cells have been shown to outperform DNN based SPSS. However, LSTM cells and its variants like gated recurrent units (GRU), simplified LSTMs (SLSTM) have complicated structure and are computationally expensive compared to the simple recurrent architecture like Elman RNN. In this paper, we explore deep Elman RNNs for SPSS and compare their effectiveness against deep gated RNNs. Specifically, we perform experiments to show that (1) Deep Elman RNNs are better suited for acoustic modeling in SPSS when compared to DNNs and perform competitively to deep SLSTMs, GRUs and LSTMs, (2) Context representation learning using Elman RNNs improves neural network acoustic models for SPSS, and (3) Elman RNN based duration model is better than the DNN based counterpart. Experiments were performed on Blizzard Challenge 2015 dataset consisting of 3 Indian languages (Telugu, Hindi and Tamil). Through subjective and objective evaluations, we show that our proposed systems outperform the baseline systems across different speakers and languages." @default.
- W2743452000 created "2017-08-17" @default.
- W2743452000 creator A5058673990 @default.
- W2743452000 creator A5086878243 @default.
- W2743452000 date "2017-10-01" @default.
- W2743452000 modified "2023-09-24" @default.
- W2743452000 title "Deep Elman recurrent neural networks for statistical parametric speech synthesis" @default.
- W2743452000 cites W2020024436 @default.
- W2743452000 cites W2049036695 @default.
- W2743452000 cites W2049686551 @default.
- W2743452000 cites W2057653135 @default.
- W2743452000 cites W2078597717 @default.
- W2743452000 cites W2107878631 @default.
- W2743452000 cites W2129142580 @default.
- W2743452000 cites W2160815625 @default.
- W2743452000 cites W2963568027 @default.
- W2743452000 cites W2964199361 @default.
- W2743452000 cites W2964301388 @default.
- W2743452000 cites W3123963976 @default.
- W2743452000 doi "https://doi.org/10.1016/j.specom.2017.08.003" @default.
- W2743452000 hasPublicationYear "2017" @default.
- W2743452000 type Work @default.
- W2743452000 sameAs 2743452000 @default.
- W2743452000 citedByCount "18" @default.
- W2743452000 countsByYear W27434520002017 @default.
- W2743452000 countsByYear W27434520002019 @default.
- W2743452000 countsByYear W27434520002020 @default.
- W2743452000 countsByYear W27434520002021 @default.
- W2743452000 countsByYear W27434520002022 @default.
- W2743452000 countsByYear W27434520002023 @default.
- W2743452000 crossrefType "journal-article" @default.
- W2743452000 hasAuthorship W2743452000A5058673990 @default.
- W2743452000 hasAuthorship W2743452000A5086878243 @default.
- W2743452000 hasConcept C105795698 @default.
- W2743452000 hasConcept C108583219 @default.
- W2743452000 hasConcept C117251300 @default.
- W2743452000 hasConcept C147168706 @default.
- W2743452000 hasConcept C151730666 @default.
- W2743452000 hasConcept C154945302 @default.
- W2743452000 hasConcept C2779343474 @default.
- W2743452000 hasConcept C28490314 @default.
- W2743452000 hasConcept C2984842247 @default.
- W2743452000 hasConcept C33923547 @default.
- W2743452000 hasConcept C41008148 @default.
- W2743452000 hasConcept C50644808 @default.
- W2743452000 hasConcept C86803240 @default.
- W2743452000 hasConceptScore W2743452000C105795698 @default.
- W2743452000 hasConceptScore W2743452000C108583219 @default.
- W2743452000 hasConceptScore W2743452000C117251300 @default.
- W2743452000 hasConceptScore W2743452000C147168706 @default.
- W2743452000 hasConceptScore W2743452000C151730666 @default.
- W2743452000 hasConceptScore W2743452000C154945302 @default.
- W2743452000 hasConceptScore W2743452000C2779343474 @default.
- W2743452000 hasConceptScore W2743452000C28490314 @default.
- W2743452000 hasConceptScore W2743452000C2984842247 @default.
- W2743452000 hasConceptScore W2743452000C33923547 @default.
- W2743452000 hasConceptScore W2743452000C41008148 @default.
- W2743452000 hasConceptScore W2743452000C50644808 @default.
- W2743452000 hasConceptScore W2743452000C86803240 @default.
- W2743452000 hasLocation W27434520001 @default.
- W2743452000 hasOpenAccess W2743452000 @default.
- W2743452000 hasPrimaryLocation W27434520001 @default.
- W2743452000 hasRelatedWork W2480330148 @default.
- W2743452000 hasRelatedWork W2787045460 @default.
- W2743452000 hasRelatedWork W2791691546 @default.
- W2743452000 hasRelatedWork W2793022090 @default.
- W2743452000 hasRelatedWork W2915754718 @default.
- W2743452000 hasRelatedWork W2919358988 @default.
- W2743452000 hasRelatedWork W3011995931 @default.
- W2743452000 hasRelatedWork W4298168912 @default.
- W2743452000 hasRelatedWork W4312424083 @default.
- W2743452000 hasRelatedWork W4327774331 @default.
- W2743452000 hasVolume "93" @default.
- W2743452000 isParatext "false" @default.
- W2743452000 isRetracted "false" @default.
- W2743452000 magId "2743452000" @default.
- W2743452000 workType "article" @default.