Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01HSB5QBCX18VRHCVM35PYXTVS> ?p ?o. }
Showing items 1 to 25 of
25
with 100 items per page.
- 01HSB5QBCX18VRHCVM35PYXTVS classification C1.
- 01HSB5QBCX18VRHCVM35PYXTVS date "2024".
- 01HSB5QBCX18VRHCVM35PYXTVS language "eng".
- 01HSB5QBCX18VRHCVM35PYXTVS type conference.
- 01HSB5QBCX18VRHCVM35PYXTVS hasPart 01HSB5SJHNAD87JK1YCHC1AVRE.pdf.
- 01HSB5QBCX18VRHCVM35PYXTVS hasPart 01HSB5SRFNFKFRBNTEA0K4RP0B.pdf.
- 01HSB5QBCX18VRHCVM35PYXTVS subject "Technology and Engineering".
- 01HSB5QBCX18VRHCVM35PYXTVS doi "10.1109/ICEIC61013.2024.10457271".
- 01HSB5QBCX18VRHCVM35PYXTVS isbn "9798350371888".
- 01HSB5QBCX18VRHCVM35PYXTVS issn "2767-7699".
- 01HSB5QBCX18VRHCVM35PYXTVS presentedAt urn:uuid:480f38cc-58f7-4e36-a8f5-4cfc537142fa.
- 01HSB5QBCX18VRHCVM35PYXTVS abstract "This paper conducts an analysis of latent embeddings generated by a range of pre-trained, self-supervised learning (SSL) models. Departing from conventional practices that predominantly focus on examining these embeddings within the realm of speech recognition tasks, our study investigates the characteristics associated with speakers and their behavior under the influence of input distortions. We establish a controlled setting with varying background noise levels and different room impulse response conditions to assess the robustness of these embeddings. We measure speaker-related information by utilizing repetitive sentences spoken by multiple speakers. The results demonstrate that the robustness of pre-trained SSL models is influenced by the type and severity of distortion, whereas the inclusion of speaker information is determined by the specific pre-training approach employed. This distinct perspective offers valuable insights into the versatility and limitations of SSL models.".
- 01HSB5QBCX18VRHCVM35PYXTVS author 4118DE52-A6F4-11E7-8878-09B7AD28A064.
- 01HSB5QBCX18VRHCVM35PYXTVS author 95CB9188-A74C-11E9-951A-2F1C5707D3EF.
- 01HSB5QBCX18VRHCVM35PYXTVS author urn:uuid:10205119-9a24-4135-8bc7-cadbb161d8d2.
- 01HSB5QBCX18VRHCVM35PYXTVS author urn:uuid:14aa8a95-7f07-42ec-839b-20c79bce18b7.
- 01HSB5QBCX18VRHCVM35PYXTVS dateCreated "2024-03-19T10:57:12Z".
- 01HSB5QBCX18VRHCVM35PYXTVS dateModified "2024-10-29T18:38:48Z".
- 01HSB5QBCX18VRHCVM35PYXTVS name "On the disentanglement and robustness of self-supervised speech representations".
- 01HSB5QBCX18VRHCVM35PYXTVS pagination urn:uuid:b425f3fd-99da-4822-ba09-d2403a89e04c.
- 01HSB5QBCX18VRHCVM35PYXTVS publisher urn:uuid:28d527fa-d8e0-43fd-805e-1eeffb9b32dd.
- 01HSB5QBCX18VRHCVM35PYXTVS sameAs LU-01HSB5QBCX18VRHCVM35PYXTVS.
- 01HSB5QBCX18VRHCVM35PYXTVS sourceOrganization urn:uuid:7d3052f0-2d1f-4328-af31-6c0930d9bfdd.
- 01HSB5QBCX18VRHCVM35PYXTVS sourceOrganization urn:uuid:9a198c61-a4d1-48ef-ac02-715523201a43.
- 01HSB5QBCX18VRHCVM35PYXTVS type C1.