Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283584039> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4283584039 endingPage "48" @default.
- W4283584039 startingPage "34" @default.
- W4283584039 abstract "Detection of speech and music is an essential preprocessing step for many high-level audio-based applications like speaker diarization and music information retrieval. Researchers have previously used various magnitude-based features in this task. In comparison, the phase spectrum has received lesser attention. The phase of a signal is believed to carry non-trivial information that can help determine its audio class. This work explores three existing phase-based features for speech vs. music classification. The potential of phase information is highlighted through statistical significance tests and canonical correlation analyses. The proposed approach is benchmarked against four baseline magnitude-based feature sets. This work also contributes an annotated audio dataset named Movie - MUSNOMIX of 8 h and 20 min duration, comprising seven audio classes, including speech and music. The Movie - MUSNOMIX dataset and widely used public datasets like MUSAN, GTZAN, Scheirer–Slaney, and Muspeak have been used for performance evaluations. In combination with magnitude-based ones, phase-based features improve upon the baseline performance consistently for the datasets used. Moreover, various combinations of phase and magnitude-based features show satisfactory generalization capability over the two datasets. The performances of phase-based features in identifying speech and music signals corrupted with different environmental noise at various SNR levels are also reported. Last but not least, a preliminary study on the efficacy of phase-based features in segmenting continuous sequences of speech and music signals is also provided. The codes used in this work and the contributed dataset have been made freely available." @default.
- W4283584039 created "2022-06-28" @default.
- W4283584039 creator A5006151531 @default.
- W4283584039 creator A5041308578 @default.
- W4283584039 creator A5052129812 @default.
- W4283584039 date "2022-07-01" @default.
- W4283584039 modified "2023-09-27" @default.
- W4283584039 title "Speech/music classification using phase-based and magnitude-based features" @default.
- W4283584039 cites W1703370492 @default.
- W4283584039 cites W1967248231 @default.
- W4283584039 cites W1976761624 @default.
- W4283584039 cites W1980993072 @default.
- W4283584039 cites W1982254271 @default.
- W4283584039 cites W1998131361 @default.
- W4283584039 cites W2015011382 @default.
- W4283584039 cites W2042419400 @default.
- W4283584039 cites W2042608483 @default.
- W4283584039 cites W2051353232 @default.
- W4283584039 cites W2109622017 @default.
- W4283584039 cites W2112844139 @default.
- W4283584039 cites W2130426352 @default.
- W4283584039 cites W2133824856 @default.
- W4283584039 cites W2164764235 @default.
- W4283584039 cites W2288613265 @default.
- W4283584039 cites W2551365680 @default.
- W4283584039 cites W2592511835 @default.
- W4283584039 cites W2625203547 @default.
- W4283584039 cites W2626065499 @default.
- W4283584039 cites W2766167392 @default.
- W4283584039 cites W2803417255 @default.
- W4283584039 cites W2919607591 @default.
- W4283584039 cites W2940820519 @default.
- W4283584039 cites W3160076412 @default.
- W4283584039 cites W79017063 @default.
- W4283584039 doi "https://doi.org/10.1016/j.specom.2022.06.005" @default.
- W4283584039 hasPublicationYear "2022" @default.
- W4283584039 type Work @default.
- W4283584039 citedByCount "0" @default.
- W4283584039 crossrefType "journal-article" @default.
- W4283584039 hasAuthorship W4283584039A5006151531 @default.
- W4283584039 hasAuthorship W4283584039A5041308578 @default.
- W4283584039 hasAuthorship W4283584039A5052129812 @default.
- W4283584039 hasConcept C115961682 @default.
- W4283584039 hasConcept C121332964 @default.
- W4283584039 hasConcept C126691448 @default.
- W4283584039 hasConcept C1276947 @default.
- W4283584039 hasConcept C138885662 @default.
- W4283584039 hasConcept C153180895 @default.
- W4283584039 hasConcept C154945302 @default.
- W4283584039 hasConcept C2776401178 @default.
- W4283584039 hasConcept C28490314 @default.
- W4283584039 hasConcept C34736171 @default.
- W4283584039 hasConcept C41008148 @default.
- W4283584039 hasConcept C41895202 @default.
- W4283584039 hasConcept C47401133 @default.
- W4283584039 hasConcept C99498987 @default.
- W4283584039 hasConceptScore W4283584039C115961682 @default.
- W4283584039 hasConceptScore W4283584039C121332964 @default.
- W4283584039 hasConceptScore W4283584039C126691448 @default.
- W4283584039 hasConceptScore W4283584039C1276947 @default.
- W4283584039 hasConceptScore W4283584039C138885662 @default.
- W4283584039 hasConceptScore W4283584039C153180895 @default.
- W4283584039 hasConceptScore W4283584039C154945302 @default.
- W4283584039 hasConceptScore W4283584039C2776401178 @default.
- W4283584039 hasConceptScore W4283584039C28490314 @default.
- W4283584039 hasConceptScore W4283584039C34736171 @default.
- W4283584039 hasConceptScore W4283584039C41008148 @default.
- W4283584039 hasConceptScore W4283584039C41895202 @default.
- W4283584039 hasConceptScore W4283584039C47401133 @default.
- W4283584039 hasConceptScore W4283584039C99498987 @default.
- W4283584039 hasFunder F4320320717 @default.
- W4283584039 hasFunder F4320325255 @default.
- W4283584039 hasLocation W42835840391 @default.
- W4283584039 hasOpenAccess W4283584039 @default.
- W4283584039 hasPrimaryLocation W42835840391 @default.
- W4283584039 hasRelatedWork W1502614025 @default.
- W4283584039 hasRelatedWork W2066259560 @default.
- W4283584039 hasRelatedWork W2126100045 @default.
- W4283584039 hasRelatedWork W2262783296 @default.
- W4283584039 hasRelatedWork W2380927352 @default.
- W4283584039 hasRelatedWork W2391959412 @default.
- W4283584039 hasRelatedWork W2728578317 @default.
- W4283584039 hasRelatedWork W3129710645 @default.
- W4283584039 hasRelatedWork W3197541072 @default.
- W4283584039 hasRelatedWork W4211209597 @default.
- W4283584039 hasVolume "142" @default.
- W4283584039 isParatext "false" @default.
- W4283584039 isRetracted "false" @default.
- W4283584039 workType "article" @default.