Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384936706> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4384936706 endingPage "101538" @default.
- W4384936706 startingPage "101538" @default.
- W4384936706 abstract "This paper discusses how automatic speech recognition systems are and could be designed, in order to best exploit the discriminative information encoded in human speech. This contrasts with many recent machine learning approaches that apply general recognition architectures to signals to identify, with little concern for the nature of the input. The implicit assumption has often been that training can automatically discover the useful properties that exist in signals, with minimal manual intervention. These approaches may be suitable for some tasks such as image recognition, where the diversity of visual input is vast; e.g., an image may be any (natural or synthetic) scene that a camera views. We first examine what makes speech special, i.e., a natural signal from a complex tube, driven by a source that is quasi-periodic and/or noisy, aiming to communicate a wide variety of information, using the different vocal systems of human speakers. Then, we view how pertinent features are extracted from speech via efficient means, related to the objectives of communication. We see how to reliably and efficiently identify the different units of oral language. We learn from the history of attempts to do ASR, e.g., why they succeeded and how improved methods exploited the increasing availability of data and computer power (in particular, deep neural networks). Finally, we suggest ways to render ASR both more accurate and efficient. This work is aimed at both newcomers to ASR and experts, in terms of presenting issues broadly, but without mathematical or algorithmic details, which are readily found in the references." @default.
- W4384936706 created "2023-07-22" @default.
- W4384936706 creator A5011489869 @default.
- W4384936706 date "2023-10-01" @default.
- W4384936706 modified "2023-10-16" @default.
- W4384936706 title "Understanding Automatic Speech Recognition" @default.
- W4384936706 cites W1499159714 @default.
- W4384936706 cites W1964501656 @default.
- W4384936706 cites W1972873790 @default.
- W4384936706 cites W1997141060 @default.
- W4384936706 cites W2002342963 @default.
- W4384936706 cites W2034537249 @default.
- W4384936706 cites W2069976350 @default.
- W4384936706 cites W2090861223 @default.
- W4384936706 cites W2096653978 @default.
- W4384936706 cites W2101927907 @default.
- W4384936706 cites W2103945478 @default.
- W4384936706 cites W2127141656 @default.
- W4384936706 cites W2131694695 @default.
- W4384936706 cites W2148154194 @default.
- W4384936706 cites W2156279557 @default.
- W4384936706 cites W2160815625 @default.
- W4384936706 cites W2163922914 @default.
- W4384936706 cites W2515753980 @default.
- W4384936706 cites W2545177271 @default.
- W4384936706 cites W2588301167 @default.
- W4384936706 cites W2618099328 @default.
- W4384936706 cites W2753772327 @default.
- W4384936706 cites W2801659857 @default.
- W4384936706 cites W282499614 @default.
- W4384936706 cites W2895807593 @default.
- W4384936706 cites W2912019251 @default.
- W4384936706 cites W2919115771 @default.
- W4384936706 cites W2921899150 @default.
- W4384936706 cites W2948312300 @default.
- W4384936706 cites W2964052309 @default.
- W4384936706 cites W2989589988 @default.
- W4384936706 cites W3007243649 @default.
- W4384936706 cites W3044757496 @default.
- W4384936706 cites W3098361150 @default.
- W4384936706 cites W3112702554 @default.
- W4384936706 cites W2780786457 @default.
- W4384936706 doi "https://doi.org/10.1016/j.csl.2023.101538" @default.
- W4384936706 hasPublicationYear "2023" @default.
- W4384936706 type Work @default.
- W4384936706 citedByCount "0" @default.
- W4384936706 crossrefType "journal-article" @default.
- W4384936706 hasAuthorship W4384936706A5011489869 @default.
- W4384936706 hasConcept C119857082 @default.
- W4384936706 hasConcept C136197465 @default.
- W4384936706 hasConcept C154945302 @default.
- W4384936706 hasConcept C165696696 @default.
- W4384936706 hasConcept C195324797 @default.
- W4384936706 hasConcept C199360897 @default.
- W4384936706 hasConcept C204321447 @default.
- W4384936706 hasConcept C2779843651 @default.
- W4384936706 hasConcept C28490314 @default.
- W4384936706 hasConcept C38652104 @default.
- W4384936706 hasConcept C41008148 @default.
- W4384936706 hasConcept C97931131 @default.
- W4384936706 hasConceptScore W4384936706C119857082 @default.
- W4384936706 hasConceptScore W4384936706C136197465 @default.
- W4384936706 hasConceptScore W4384936706C154945302 @default.
- W4384936706 hasConceptScore W4384936706C165696696 @default.
- W4384936706 hasConceptScore W4384936706C195324797 @default.
- W4384936706 hasConceptScore W4384936706C199360897 @default.
- W4384936706 hasConceptScore W4384936706C204321447 @default.
- W4384936706 hasConceptScore W4384936706C2779843651 @default.
- W4384936706 hasConceptScore W4384936706C28490314 @default.
- W4384936706 hasConceptScore W4384936706C38652104 @default.
- W4384936706 hasConceptScore W4384936706C41008148 @default.
- W4384936706 hasConceptScore W4384936706C97931131 @default.
- W4384936706 hasLocation W43849367061 @default.
- W4384936706 hasOpenAccess W4384936706 @default.
- W4384936706 hasPrimaryLocation W43849367061 @default.
- W4384936706 hasRelatedWork W159132833 @default.
- W4384936706 hasRelatedWork W2293457016 @default.
- W4384936706 hasRelatedWork W2502722637 @default.
- W4384936706 hasRelatedWork W2964604098 @default.
- W4384936706 hasRelatedWork W2977842567 @default.
- W4384936706 hasRelatedWork W2983744209 @default.
- W4384936706 hasRelatedWork W2997512100 @default.
- W4384936706 hasRelatedWork W3198474835 @default.
- W4384936706 hasRelatedWork W87581401 @default.
- W4384936706 hasRelatedWork W1872130062 @default.
- W4384936706 hasVolume "83" @default.
- W4384936706 isParatext "false" @default.
- W4384936706 isRetracted "false" @default.
- W4384936706 workType "article" @default.