{"ID":5936974,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T16:12:55.966383441Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05276","arxiv_id":"2607.05276","title":"ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions","abstract":"Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed speech segment to an x-vector, which is then used for downstream applications. We introduce ProPS, Prompted Profile Synthesis, a framework for generating distributions of speaker embeddings conditioned on natural language prompts such as \"a thirties male speaker with an Indian accent\". ProPS converts human-written profile descriptions into sentence embeddings and uses a mixture density network trained on a large-scale dataset to predict a Gaussian mixture model in the x-vector space. The model is trained by maximizing the likelihood that real speaker embeddings match the requested profile, and its generated distributions are evaluated by negative log-likelihood on held-out x-vectors and by attribute classification accuracies on sampled synthetic x-vectors. Experiments show that ProPS produces profile-conditioned distributions and generates x-vectors that preserve requested speaker attributes such as age, gender, accent, and prosodic characteristics. This design enables controllable speaker-profile synthesis for speech generation systems like Text-To-Speech (TTS) or Voice Conversion (VC) while anchoring generated distributions in observed speaker-embedding structure.","short_abstract":"Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed speech segment to an x-vector, which is then used for downstream applications. We introduce ProPS, Prom...","url_abs":"https://arxiv.org/abs/2607.05276","url_pdf":"https://arxiv.org/pdf/2607.05276v1","authors":"[\"Thomas Thebaud\",\"Junhyeok Lee\",\"Laureano Moro-Velazquez\",\"Jesus Villalba Lopez\",\"Najim Dehak\"]","published":"2026-07-06T16:21:34Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.AI\"]","methods":"[]","has_code":false}