Matches in SemOpenAlex for { <https://semopenalex.org/work/W2120085319> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2120085319 endingPage "1807" @default.
- W2120085319 startingPage "1799" @default.
- W2120085319 abstract "We present a method for recognition of acoustic events in conversation scenarios where speech usually overlaps with other acoustic events. While speech is usually considered the most informative acoustic event in a conversation scene, it does not always contain all the information. Non-speech events, such as a door knock, steps, or a keyboard typing can reveal aspects of the scene that speakers miss or avoid to mention. Moreover, being able to robustly detect these events could further support speech enhancement and recognition systems by providing useful information cues about the surrounding scenarios and noise. In acoustic event detection, state-of-the-art techniques are typically based on derived features (e.g. MFCC, or Mel-filter-banks) which have successfully parameterized the spectrogram of speech but reduce resolution and detail when we are targeting other kinds of events. In this paper, we propose a method that learns features in an unsupervised manner from high-resolution spectrogram patches (considering a patch as a certain number of consecutive frame features stacked together), and integrates within the deep neural network framework to detect and classify acoustic events. Superiority over both previous works in the field, and similar approaches based on derived features, has been assessed by statical measures and evaluation with CHIL2007 corpus, an annotated database of seminar recordings." @default.
- W2120085319 created "2016-06-24" @default.
- W2120085319 creator A5021240106 @default.
- W2120085319 creator A5039277089 @default.
- W2120085319 creator A5074161622 @default.
- W2120085319 date "2015-01-01" @default.
- W2120085319 modified "2023-09-23" @default.
- W2120085319 title "Acoustic Event Detection in Speech Overlapping Scenarios Based on High-Resolution Spectral Input and Deep Learning" @default.
- W2120085319 cites W1822987211 @default.
- W2120085319 cites W1976363263 @default.
- W2120085319 cites W1977834503 @default.
- W2120085319 cites W1988876483 @default.
- W2120085319 cites W1993882792 @default.
- W2120085319 cites W2005733316 @default.
- W2120085319 cites W2059203007 @default.
- W2120085319 cites W2081433959 @default.
- W2120085319 cites W2086384421 @default.
- W2120085319 cites W2086468861 @default.
- W2120085319 cites W2114187103 @default.
- W2120085319 cites W2115447976 @default.
- W2120085319 cites W2123843894 @default.
- W2120085319 cites W2126109423 @default.
- W2120085319 cites W2128083002 @default.
- W2120085319 cites W2134925458 @default.
- W2120085319 cites W2141739745 @default.
- W2120085319 cites W2146792684 @default.
- W2120085319 cites W2160860215 @default.
- W2120085319 cites W2165712214 @default.
- W2120085319 cites W2168013545 @default.
- W2120085319 cites W2398030828 @default.
- W2120085319 cites W2400753342 @default.
- W2120085319 cites W44815768 @default.
- W2120085319 doi "https://doi.org/10.1587/transinf.2014edp7430" @default.
- W2120085319 hasPublicationYear "2015" @default.
- W2120085319 type Work @default.
- W2120085319 sameAs 2120085319 @default.
- W2120085319 citedByCount "4" @default.
- W2120085319 countsByYear W21200853192017 @default.
- W2120085319 countsByYear W21200853192021 @default.
- W2120085319 crossrefType "journal-article" @default.
- W2120085319 hasAuthorship W2120085319A5021240106 @default.
- W2120085319 hasAuthorship W2120085319A5039277089 @default.
- W2120085319 hasAuthorship W2120085319A5074161622 @default.
- W2120085319 hasBestOaLocation W21200853191 @default.
- W2120085319 hasConcept C106131492 @default.
- W2120085319 hasConcept C121332964 @default.
- W2120085319 hasConcept C138885662 @default.
- W2120085319 hasConcept C151989614 @default.
- W2120085319 hasConcept C153180895 @default.
- W2120085319 hasConcept C154945302 @default.
- W2120085319 hasConcept C2777200299 @default.
- W2120085319 hasConcept C2779662365 @default.
- W2120085319 hasConcept C28490314 @default.
- W2120085319 hasConcept C31972630 @default.
- W2120085319 hasConcept C41008148 @default.
- W2120085319 hasConcept C41895202 @default.
- W2120085319 hasConcept C45273575 @default.
- W2120085319 hasConcept C52622490 @default.
- W2120085319 hasConcept C62520636 @default.
- W2120085319 hasConceptScore W2120085319C106131492 @default.
- W2120085319 hasConceptScore W2120085319C121332964 @default.
- W2120085319 hasConceptScore W2120085319C138885662 @default.
- W2120085319 hasConceptScore W2120085319C151989614 @default.
- W2120085319 hasConceptScore W2120085319C153180895 @default.
- W2120085319 hasConceptScore W2120085319C154945302 @default.
- W2120085319 hasConceptScore W2120085319C2777200299 @default.
- W2120085319 hasConceptScore W2120085319C2779662365 @default.
- W2120085319 hasConceptScore W2120085319C28490314 @default.
- W2120085319 hasConceptScore W2120085319C31972630 @default.
- W2120085319 hasConceptScore W2120085319C41008148 @default.
- W2120085319 hasConceptScore W2120085319C41895202 @default.
- W2120085319 hasConceptScore W2120085319C45273575 @default.
- W2120085319 hasConceptScore W2120085319C52622490 @default.
- W2120085319 hasConceptScore W2120085319C62520636 @default.
- W2120085319 hasIssue "10" @default.
- W2120085319 hasLocation W21200853191 @default.
- W2120085319 hasOpenAccess W2120085319 @default.
- W2120085319 hasPrimaryLocation W21200853191 @default.
- W2120085319 hasRelatedWork W2254811285 @default.
- W2120085319 hasRelatedWork W2313168606 @default.
- W2120085319 hasRelatedWork W2578419950 @default.
- W2120085319 hasRelatedWork W2765640197 @default.
- W2120085319 hasRelatedWork W3183745337 @default.
- W2120085319 hasRelatedWork W3214272778 @default.
- W2120085319 hasRelatedWork W4206322605 @default.
- W2120085319 hasRelatedWork W4210770212 @default.
- W2120085319 hasRelatedWork W4304777473 @default.
- W2120085319 hasRelatedWork W4313473458 @default.
- W2120085319 hasVolume "E98.D" @default.
- W2120085319 isParatext "false" @default.
- W2120085319 isRetracted "false" @default.
- W2120085319 magId "2120085319" @default.
- W2120085319 workType "article" @default.