{"ID":2874562,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.04072","arxiv_id":"2509.04072","title":"Computational Narrative Understanding for Expressive Text-to-Speech","abstract":"Recent advances in text-to-speech (TTS) have been driven by large, multi-domain speech corpora, yet the expressive potential of audiobook data remains underexamined. We argue that human-narrated audiobooks, particularly fictional works, contain rich and diverse prosodic cues arising from the natural alternation between neutral narration and expressive character dialogue. Building from this observation, we introduce LibriQuote, a large-scale 5.3K hours of expressive speech drawn from character quotations. Each quote is supplemented with contextual pseudo-labels for speech verbs and adverbs that characterize the intended delivery of direct speech (e.g., \"he whispered softly\"). We found that fine-tuning a flow-matching model on LibriQuote yields substantial improvements in expressivity and intelligibility, while training from scratch enhances expressiveness of an autoregressive TTS model. Benchmarking on LibriQuote-test highlights significant variability across systems in generating expressive speech. We publicly release the dataset, code, and evaluation resources to facilitate reproducibility. Audio samples can be found at https://libriquote.github.io/.","short_abstract":"Recent advances in text-to-speech (TTS) have been driven by large, multi-domain speech corpora, yet the expressive potential of audiobook data remains underexamined. We argue that human-narrated audiobooks, particularly fictional works, contain rich and diverse prosodic cues arising from the natural alternation between...","url_abs":"https://arxiv.org/abs/2509.04072","url_pdf":"https://arxiv.org/pdf/2509.04072v2","authors":"[\"Gaspard Michel\",\"Elena V. Epure\",\"Christophe Cerisara\"]","published":"2025-09-04T10:05:06Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.CL\",\"cs.SD\"]","methods":"[]","has_code":false}