ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions
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 de
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Thomas Thebaud →
“ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions”
- LinkedLinked via arxiv author · 85%Junhyeok Lee →
“ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions”
- LinkedLinked via arxiv author · 85%Laureano Moro-Velazquez →
“ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions”
- LinkedLinked via arxiv author · 85%Jesus Villalba Lopez →
“ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions”
- LinkedLinked via arxiv author · 85%Najim Dehak →
“ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions”
- PossiblePossibly related (embedding) · 46%wq2012/awesome-diarization →
- PossiblePossibly related (embedding) · 54%Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers →