Matches in SemOpenAlex for { <https://semopenalex.org/work/W3006351824> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3006351824 abstract "Most of the languages in the Sino-Tibetan language family use syllables as the basic unit of speech recognition. Recently most methods of syllable segmentation extract the features of speech signals as the basis of segmentation, and some predefined thresholds are introduced to determine the boundaries. Considering that the location of a syllable boundary is not only related to its previous speech signal sequence, but also to its later speech signals, a blind syllable segmentation method based on bi-directional recurrent neural network (BRNN) is proposed, in which the pure speech signals are used as original input. In order to alleviate the gradient vanishing problem, Long Short-Term Memory (LSTM) is used as the basic neuron unit in the BRNN model. In order to calculate the loss of the model efficiently, a linear distance factor and an auxiliary label vector are introduced. The two vectors are only related to the speech signals, and can be calculated at the same time as the training set is generated. With the help of these two vectors, a loss function based on cross-entropy is designed, and the model is trained and evaluated under the speech data with a total length of 2.8 hours coming from a Bai Language speech corpora. The experimental results show that the proposed model based on bi-directional LSTM (BiLSTM) can be effectively applied to syllable segmentation without additional threshold parameters, and the detection accuracy of syllable boundaries is close to 85% with the evaluating dataset." @default.
- W3006351824 created "2020-02-24" @default.
- W3006351824 creator A5036862308 @default.
- W3006351824 creator A5068295686 @default.
- W3006351824 creator A5086868372 @default.
- W3006351824 date "2019-08-01" @default.
- W3006351824 modified "2023-09-26" @default.
- W3006351824 title "An Automatic Blind Syllable Segmentation Model Based on Bi-directional LSTM" @default.
- W3006351824 cites W1617657290 @default.
- W3006351824 cites W1665509042 @default.
- W3006351824 cites W1669577408 @default.
- W3006351824 cites W1898152195 @default.
- W3006351824 cites W2037298640 @default.
- W3006351824 cites W2045157414 @default.
- W3006351824 cites W2064675550 @default.
- W3006351824 cites W2083418169 @default.
- W3006351824 cites W2104486383 @default.
- W3006351824 cites W2127812300 @default.
- W3006351824 cites W2134701267 @default.
- W3006351824 cites W2253740514 @default.
- W3006351824 cites W2355119923 @default.
- W3006351824 cites W2357522389 @default.
- W3006351824 cites W2401271337 @default.
- W3006351824 cites W2406747591 @default.
- W3006351824 cites W2408181179 @default.
- W3006351824 cites W2746591268 @default.
- W3006351824 cites W2749211571 @default.
- W3006351824 cites W2750077311 @default.
- W3006351824 cites W2762967345 @default.
- W3006351824 cites W2800408419 @default.
- W3006351824 cites W2803005441 @default.
- W3006351824 cites W2898019480 @default.
- W3006351824 cites W2586482422 @default.
- W3006351824 doi "https://doi.org/10.1109/ccet48361.2019.8989392" @default.
- W3006351824 hasPublicationYear "2019" @default.
- W3006351824 type Work @default.
- W3006351824 sameAs 3006351824 @default.
- W3006351824 citedByCount "0" @default.
- W3006351824 crossrefType "proceedings-article" @default.
- W3006351824 hasAuthorship W3006351824A5036862308 @default.
- W3006351824 hasAuthorship W3006351824A5068295686 @default.
- W3006351824 hasAuthorship W3006351824A5086868372 @default.
- W3006351824 hasConcept C109089402 @default.
- W3006351824 hasConcept C153180895 @default.
- W3006351824 hasConcept C154945302 @default.
- W3006351824 hasConcept C207030507 @default.
- W3006351824 hasConcept C28490314 @default.
- W3006351824 hasConcept C41008148 @default.
- W3006351824 hasConcept C61328038 @default.
- W3006351824 hasConcept C89600930 @default.
- W3006351824 hasConceptScore W3006351824C109089402 @default.
- W3006351824 hasConceptScore W3006351824C153180895 @default.
- W3006351824 hasConceptScore W3006351824C154945302 @default.
- W3006351824 hasConceptScore W3006351824C207030507 @default.
- W3006351824 hasConceptScore W3006351824C28490314 @default.
- W3006351824 hasConceptScore W3006351824C41008148 @default.
- W3006351824 hasConceptScore W3006351824C61328038 @default.
- W3006351824 hasConceptScore W3006351824C89600930 @default.
- W3006351824 hasLocation W30063518241 @default.
- W3006351824 hasOpenAccess W3006351824 @default.
- W3006351824 hasPrimaryLocation W30063518241 @default.
- W3006351824 hasRelatedWork W1511589806 @default.
- W3006351824 hasRelatedWork W1570082996 @default.
- W3006351824 hasRelatedWork W1970760943 @default.
- W3006351824 hasRelatedWork W1983091641 @default.
- W3006351824 hasRelatedWork W2004833594 @default.
- W3006351824 hasRelatedWork W2014122274 @default.
- W3006351824 hasRelatedWork W2029515177 @default.
- W3006351824 hasRelatedWork W2031219539 @default.
- W3006351824 hasRelatedWork W2046943536 @default.
- W3006351824 hasRelatedWork W2057731032 @default.
- W3006351824 hasRelatedWork W2073762424 @default.
- W3006351824 hasRelatedWork W2099990284 @default.
- W3006351824 hasRelatedWork W2101226710 @default.
- W3006351824 hasRelatedWork W2135647151 @default.
- W3006351824 hasRelatedWork W2147711390 @default.
- W3006351824 hasRelatedWork W2293392884 @default.
- W3006351824 hasRelatedWork W2342101979 @default.
- W3006351824 hasRelatedWork W2379805765 @default.
- W3006351824 hasRelatedWork W2785496868 @default.
- W3006351824 hasRelatedWork W3033536135 @default.
- W3006351824 isParatext "false" @default.
- W3006351824 isRetracted "false" @default.
- W3006351824 magId "3006351824" @default.
- W3006351824 workType "article" @default.