Matches in SemOpenAlex for { <https://semopenalex.org/work/W43005181> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W43005181 abstract "Traditional approaches to automatic emotion recognition from speech typically make use of utterance level prosodic features. Still, a great deal of useful information about expressivity and emotion can be gained from segmental spectral features, which provide a more detailed description of the speech signal, or from measurements from specific regions of the utterance, such as the stressed vowels. Here we introduce a novel set of spectral features for emotion recognition: statistics of Mel-Frequency Spectral Coefficients computed over three phoneme type classes of interest: stressed vowels, unstressed vowels and consonants in the utterance. We investigate performance of our features in the task of speaker-independent emotion recognition using two publicly available datasets. Our experimental results clearly indicate that indeed both the richer set of spectral features and the differentiation between phoneme type classes are beneficial for the task. Classification accuracies are consistently higher for our features compared to prosodic features or utterance-level spectral features. Combination of our phoneme class features with prosodic features leads to even further improvement. Index Terms: emotion recognition" @default.
- W43005181 created "2016-06-24" @default.
- W43005181 creator A5032571629 @default.
- W43005181 creator A5079631251 @default.
- W43005181 creator A5083518354 @default.
- W43005181 date "2009-09-06" @default.
- W43005181 modified "2023-09-26" @default.
- W43005181 title "Improving emotion recognition using class-level spectral features" @default.
- W43005181 cites W141482854 @default.
- W43005181 cites W1535925594 @default.
- W43005181 cites W1575712594 @default.
- W43005181 cites W1668904664 @default.
- W43005181 cites W175750906 @default.
- W43005181 cites W1844030040 @default.
- W43005181 cites W1875231349 @default.
- W43005181 cites W1923034539 @default.
- W43005181 cites W1994458317 @default.
- W43005181 cites W2077512056 @default.
- W43005181 cites W2111926505 @default.
- W43005181 cites W2118789253 @default.
- W43005181 cites W2118911453 @default.
- W43005181 cites W2123864036 @default.
- W43005181 cites W2125365056 @default.
- W43005181 cites W2127108986 @default.
- W43005181 cites W2148633389 @default.
- W43005181 cites W2153635508 @default.
- W43005181 cites W2156140659 @default.
- W43005181 cites W88081813 @default.
- W43005181 cites W90720583 @default.
- W43005181 doi "https://doi.org/10.21437/interspeech.2009-582" @default.
- W43005181 hasPublicationYear "2009" @default.
- W43005181 type Work @default.
- W43005181 sameAs 43005181 @default.
- W43005181 citedByCount "5" @default.
- W43005181 countsByYear W430051812014 @default.
- W43005181 countsByYear W430051812018 @default.
- W43005181 crossrefType "proceedings-article" @default.
- W43005181 hasAuthorship W43005181A5032571629 @default.
- W43005181 hasAuthorship W43005181A5079631251 @default.
- W43005181 hasAuthorship W43005181A5083518354 @default.
- W43005181 hasConcept C153180895 @default.
- W43005181 hasConcept C154945302 @default.
- W43005181 hasConcept C162324750 @default.
- W43005181 hasConcept C177264268 @default.
- W43005181 hasConcept C187736073 @default.
- W43005181 hasConcept C199360897 @default.
- W43005181 hasConcept C204321447 @default.
- W43005181 hasConcept C206310091 @default.
- W43005181 hasConcept C2775852435 @default.
- W43005181 hasConcept C2777212361 @default.
- W43005181 hasConcept C2777438025 @default.
- W43005181 hasConcept C2780451532 @default.
- W43005181 hasConcept C28490314 @default.
- W43005181 hasConcept C41008148 @default.
- W43005181 hasConceptScore W43005181C153180895 @default.
- W43005181 hasConceptScore W43005181C154945302 @default.
- W43005181 hasConceptScore W43005181C162324750 @default.
- W43005181 hasConceptScore W43005181C177264268 @default.
- W43005181 hasConceptScore W43005181C187736073 @default.
- W43005181 hasConceptScore W43005181C199360897 @default.
- W43005181 hasConceptScore W43005181C204321447 @default.
- W43005181 hasConceptScore W43005181C206310091 @default.
- W43005181 hasConceptScore W43005181C2775852435 @default.
- W43005181 hasConceptScore W43005181C2777212361 @default.
- W43005181 hasConceptScore W43005181C2777438025 @default.
- W43005181 hasConceptScore W43005181C2780451532 @default.
- W43005181 hasConceptScore W43005181C28490314 @default.
- W43005181 hasConceptScore W43005181C41008148 @default.
- W43005181 hasLocation W430051811 @default.
- W43005181 hasOpenAccess W43005181 @default.
- W43005181 hasPrimaryLocation W430051811 @default.
- W43005181 hasRelatedWork W138045608 @default.
- W43005181 hasRelatedWork W1510902139 @default.
- W43005181 hasRelatedWork W165447341 @default.
- W43005181 hasRelatedWork W183468103 @default.
- W43005181 hasRelatedWork W1995503542 @default.
- W43005181 hasRelatedWork W2073110098 @default.
- W43005181 hasRelatedWork W2104773730 @default.
- W43005181 hasRelatedWork W2136441875 @default.
- W43005181 hasRelatedWork W2155748199 @default.
- W43005181 hasRelatedWork W2158514474 @default.
- W43005181 hasRelatedWork W2396552128 @default.
- W43005181 hasRelatedWork W2517973391 @default.
- W43005181 hasRelatedWork W2518377185 @default.
- W43005181 hasRelatedWork W2542587589 @default.
- W43005181 hasRelatedWork W2789962031 @default.
- W43005181 hasRelatedWork W2799870080 @default.
- W43005181 hasRelatedWork W2896646358 @default.
- W43005181 hasRelatedWork W2914066281 @default.
- W43005181 hasRelatedWork W2954089132 @default.
- W43005181 hasRelatedWork W2299583026 @default.
- W43005181 isParatext "false" @default.
- W43005181 isRetracted "false" @default.
- W43005181 magId "43005181" @default.
- W43005181 workType "article" @default.