{"ID":5346744,"CreatedAt":"2026-06-30T04:09:55.830587294Z","UpdatedAt":"2026-07-02T14:12:34.668891255Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30356","arxiv_id":"2606.30356","title":"OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL","abstract":"We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and synthesis objectives. OLIVE combines view-augmented masked latent prediction with waveform reconstruction under a unified objective. Reconstruction constrains early encoder features to retain signal-level information, while masked latent prediction shapes later contextual representations toward invariance for robust downstream performance. We show that these objectives enable representations that support a broad range of tasks. In particular, OLIVE improves results on generation and speaker tasks, maintains competitive performance on recognition and semantic tasks, and improves waveform reconstruction.","short_abstract":"We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and synthesis objectives. OLIVE combines view-augmented masked latent prediction with waveform reconstruction under a unified objective. Reconst...","url_abs":"https://arxiv.org/abs/2606.30356","url_pdf":"https://arxiv.org/pdf/2606.30356v1","authors":"[\"Karl El Hajal\",\"Mathew Magimai. -Doss\"]","published":"2026-06-29T14:24:19Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\",\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false}