Matches in SemOpenAlex for { <https://semopenalex.org/work/W2786835190> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2786835190 abstract "End-to-end automatic speech recognition (ASR) can significantly reduce the burden of developing ASR systems for new languages, by eliminating the need for linguistic information such as pronunciation dictionaries. This also creates an opportunity, which we fully exploit in this paper, to build a monolithic multilingual ASR system with a language-independent neural network architecture. We present a model that can recognize speech in 10 different languages, by directly performing grapheme (character/chunked-character) based speech recognition. The model is based on our hybrid attention/connectionist temporal classification (CTC) architecture which has previously been shown to achieve the state-of-the-art performance in several ASR benchmarks. Here we augment its set of output symbols to include the union of character sets appearing in all the target languages. These include Roman and Cyrillic Alphabets, Arabic numbers, simplified Chinese, and Japanese Kanji/Hiragana/Katakana characters (5,500 characters in all). This allows training of a single multilingual model, whose parameters are shared across all the languages. The model can jointly identify the language and recognize the speech, automatically formatting the recognized text in the appropriate character set. The experiments, which used speech databases composed of Wall Street Journal (English), Corpus of Spontaneous Japanese, HKUST Mandarin CTS, and Voxforge (German, Spanish, French, Italian, Dutch, Portuguese, Russian), demonstrate comparable/superior performance relative to language-dependent end-to-end ASR systems." @default.
- W2786835190 created "2018-02-23" @default.
- W2786835190 creator A5001291873 @default.
- W2786835190 creator A5082524152 @default.
- W2786835190 creator A5087554069 @default.
- W2786835190 date "2017-12-01" @default.
- W2786835190 modified "2023-10-16" @default.
- W2786835190 title "Language independent end-to-end architecture for joint language identification and speech recognition" @default.
- W2786835190 cites W1526236009 @default.
- W2786835190 cites W1846073453 @default.
- W2786835190 cites W1970890968 @default.
- W2786835190 cites W1978660892 @default.
- W2786835190 cites W1982774639 @default.
- W2786835190 cites W2025198378 @default.
- W2786835190 cites W2085628288 @default.
- W2786835190 cites W2091746061 @default.
- W2786835190 cites W2096140469 @default.
- W2786835190 cites W2127141656 @default.
- W2786835190 cites W2514741789 @default.
- W2786835190 cites W2608712415 @default.
- W2786835190 cites W2627092829 @default.
- W2786835190 cites W2739883972 @default.
- W2786835190 cites W2963211739 @default.
- W2786835190 cites W73572011 @default.
- W2786835190 doi "https://doi.org/10.1109/asru.2017.8268945" @default.
- W2786835190 hasPublicationYear "2017" @default.
- W2786835190 type Work @default.
- W2786835190 sameAs 2786835190 @default.
- W2786835190 citedByCount "82" @default.
- W2786835190 countsByYear W27868351902018 @default.
- W2786835190 countsByYear W27868351902019 @default.
- W2786835190 countsByYear W27868351902020 @default.
- W2786835190 countsByYear W27868351902021 @default.
- W2786835190 countsByYear W27868351902022 @default.
- W2786835190 countsByYear W27868351902023 @default.
- W2786835190 crossrefType "proceedings-article" @default.
- W2786835190 hasAuthorship W2786835190A5001291873 @default.
- W2786835190 hasAuthorship W2786835190A5082524152 @default.
- W2786835190 hasAuthorship W2786835190A5087554069 @default.
- W2786835190 hasConcept C116834253 @default.
- W2786835190 hasConcept C123657996 @default.
- W2786835190 hasConcept C127413603 @default.
- W2786835190 hasConcept C129792486 @default.
- W2786835190 hasConcept C154945302 @default.
- W2786835190 hasConcept C166957645 @default.
- W2786835190 hasConcept C170154142 @default.
- W2786835190 hasConcept C18555067 @default.
- W2786835190 hasConcept C195324797 @default.
- W2786835190 hasConcept C204321447 @default.
- W2786835190 hasConcept C28490314 @default.
- W2786835190 hasConcept C41008148 @default.
- W2786835190 hasConcept C59822182 @default.
- W2786835190 hasConcept C74296488 @default.
- W2786835190 hasConcept C86803240 @default.
- W2786835190 hasConcept C95457728 @default.
- W2786835190 hasConceptScore W2786835190C116834253 @default.
- W2786835190 hasConceptScore W2786835190C123657996 @default.
- W2786835190 hasConceptScore W2786835190C127413603 @default.
- W2786835190 hasConceptScore W2786835190C129792486 @default.
- W2786835190 hasConceptScore W2786835190C154945302 @default.
- W2786835190 hasConceptScore W2786835190C166957645 @default.
- W2786835190 hasConceptScore W2786835190C170154142 @default.
- W2786835190 hasConceptScore W2786835190C18555067 @default.
- W2786835190 hasConceptScore W2786835190C195324797 @default.
- W2786835190 hasConceptScore W2786835190C204321447 @default.
- W2786835190 hasConceptScore W2786835190C28490314 @default.
- W2786835190 hasConceptScore W2786835190C41008148 @default.
- W2786835190 hasConceptScore W2786835190C59822182 @default.
- W2786835190 hasConceptScore W2786835190C74296488 @default.
- W2786835190 hasConceptScore W2786835190C86803240 @default.
- W2786835190 hasConceptScore W2786835190C95457728 @default.
- W2786835190 hasLocation W27868351901 @default.
- W2786835190 hasOpenAccess W2786835190 @default.
- W2786835190 hasPrimaryLocation W27868351901 @default.
- W2786835190 hasRelatedWork W1803932089 @default.
- W2786835190 hasRelatedWork W2475268295 @default.
- W2786835190 hasRelatedWork W2578342220 @default.
- W2786835190 hasRelatedWork W2583219169 @default.
- W2786835190 hasRelatedWork W3045567129 @default.
- W2786835190 hasRelatedWork W3088333221 @default.
- W2786835190 hasRelatedWork W3107474891 @default.
- W2786835190 hasRelatedWork W3134336087 @default.
- W2786835190 hasRelatedWork W4300928910 @default.
- W2786835190 hasRelatedWork W851785710 @default.
- W2786835190 isParatext "false" @default.
- W2786835190 isRetracted "false" @default.
- W2786835190 magId "2786835190" @default.
- W2786835190 workType "article" @default.