Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313203218> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4313203218 abstract "Speech-to-speech translation (S2ST) is the process of translation of speech from one language to another. Traditional S2ST systems follow a cascaded approach, where three modules automatics speech recognition (ASR), machine translation (MT), and text-to-speech translation (TTS) are concatenated to obtain the final translated speech utterance. The cascaded nature of the system results in the propagation of errors from one module to another. This, in turn, leads to the degradation in the overall performance of the S2ST task. With the evolution of the deep learning approaches to speech processing, many attempts have been made to perform end-to-end and direct speech-to-speech translation (DS2ST). But most of these approaches rely on language transcripts in one way or the other. In this work, we aim to perform the DS2ST task without using language transcripts. In this direction we have performed three experiments: First, we have investigated the direct learning of mapping function from source to target language with the increase in the number of utterances. Second, we have analyzed how the learning function improves with an increase in the number of Bi-LSTM layers. Third, we have observed how the system behaves with the unknown speakers (not used during training) during inference. From the experiments, it has been observed that with the increase in the number of utterances and layers, the quality of translation improves. And also, with a speaker and text-dependent training of approximately 4.4 hrs of speech, the model can generate the target language utterance even for unknown speakers. Though the generated utterance quality is not that good, but intelligent to some extent to be perceived." @default.
- W4313203218 created "2023-01-06" @default.
- W4313203218 creator A5013209021 @default.
- W4313203218 creator A5020245577 @default.
- W4313203218 creator A5052129812 @default.
- W4313203218 creator A5066249311 @default.
- W4313203218 date "2022-11-01" @default.
- W4313203218 modified "2023-09-27" @default.
- W4313203218 title "Analysis of Layer-Wise Training in Direct Speech to Speech Translation Using BI-LSTM" @default.
- W4313203218 cites W1509691205 @default.
- W4313203218 cites W1510746193 @default.
- W4313203218 cites W1538023239 @default.
- W4313203218 cites W1579847400 @default.
- W4313203218 cites W1969443802 @default.
- W4313203218 cites W1978264303 @default.
- W4313203218 cites W2040882540 @default.
- W4313203218 cites W2048458228 @default.
- W4313203218 cites W2051745966 @default.
- W4313203218 cites W2081592734 @default.
- W4313203218 cites W2131774270 @default.
- W4313203218 cites W2135708429 @default.
- W4313203218 cites W2136545725 @default.
- W4313203218 cites W2145095987 @default.
- W4313203218 cites W2146173057 @default.
- W4313203218 cites W2150355110 @default.
- W4313203218 cites W2915253508 @default.
- W4313203218 cites W2972448360 @default.
- W4313203218 cites W2972495969 @default.
- W4313203218 cites W3007068036 @default.
- W4313203218 cites W3017535695 @default.
- W4313203218 cites W3098557217 @default.
- W4313203218 cites W3142316150 @default.
- W4313203218 cites W3180374548 @default.
- W4313203218 cites W3197659778 @default.
- W4313203218 cites W3208643357 @default.
- W4313203218 doi "https://doi.org/10.1109/o-cocosda202257103.2022.9997945" @default.
- W4313203218 hasPublicationYear "2022" @default.
- W4313203218 type Work @default.
- W4313203218 citedByCount "0" @default.
- W4313203218 crossrefType "proceedings-article" @default.
- W4313203218 hasAuthorship W4313203218A5013209021 @default.
- W4313203218 hasAuthorship W4313203218A5020245577 @default.
- W4313203218 hasAuthorship W4313203218A5052129812 @default.
- W4313203218 hasAuthorship W4313203218A5066249311 @default.
- W4313203218 hasConcept C104317684 @default.
- W4313203218 hasConcept C105580179 @default.
- W4313203218 hasConcept C149364088 @default.
- W4313203218 hasConcept C14999030 @default.
- W4313203218 hasConcept C154945302 @default.
- W4313203218 hasConcept C162324750 @default.
- W4313203218 hasConcept C185592680 @default.
- W4313203218 hasConcept C187736073 @default.
- W4313203218 hasConcept C203005215 @default.
- W4313203218 hasConcept C204321447 @default.
- W4313203218 hasConcept C2775852435 @default.
- W4313203218 hasConcept C2776214188 @default.
- W4313203218 hasConcept C2780366754 @default.
- W4313203218 hasConcept C2780451532 @default.
- W4313203218 hasConcept C28490314 @default.
- W4313203218 hasConcept C41008148 @default.
- W4313203218 hasConcept C55493867 @default.
- W4313203218 hasConcept C61328038 @default.
- W4313203218 hasConceptScore W4313203218C104317684 @default.
- W4313203218 hasConceptScore W4313203218C105580179 @default.
- W4313203218 hasConceptScore W4313203218C149364088 @default.
- W4313203218 hasConceptScore W4313203218C14999030 @default.
- W4313203218 hasConceptScore W4313203218C154945302 @default.
- W4313203218 hasConceptScore W4313203218C162324750 @default.
- W4313203218 hasConceptScore W4313203218C185592680 @default.
- W4313203218 hasConceptScore W4313203218C187736073 @default.
- W4313203218 hasConceptScore W4313203218C203005215 @default.
- W4313203218 hasConceptScore W4313203218C204321447 @default.
- W4313203218 hasConceptScore W4313203218C2775852435 @default.
- W4313203218 hasConceptScore W4313203218C2776214188 @default.
- W4313203218 hasConceptScore W4313203218C2780366754 @default.
- W4313203218 hasConceptScore W4313203218C2780451532 @default.
- W4313203218 hasConceptScore W4313203218C28490314 @default.
- W4313203218 hasConceptScore W4313203218C41008148 @default.
- W4313203218 hasConceptScore W4313203218C55493867 @default.
- W4313203218 hasConceptScore W4313203218C61328038 @default.
- W4313203218 hasLocation W43132032181 @default.
- W4313203218 hasOpenAccess W4313203218 @default.
- W4313203218 hasPrimaryLocation W43132032181 @default.
- W4313203218 hasRelatedWork W1549274509 @default.
- W4313203218 hasRelatedWork W1658560081 @default.
- W4313203218 hasRelatedWork W1883264250 @default.
- W4313203218 hasRelatedWork W2066913438 @default.
- W4313203218 hasRelatedWork W2331981651 @default.
- W4313203218 hasRelatedWork W2587623425 @default.
- W4313203218 hasRelatedWork W3184351855 @default.
- W4313203218 hasRelatedWork W3216100938 @default.
- W4313203218 hasRelatedWork W365755509 @default.
- W4313203218 hasRelatedWork W2178499706 @default.
- W4313203218 isParatext "false" @default.
- W4313203218 isRetracted "false" @default.
- W4313203218 workType "article" @default.