CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis

Yash Raj Singh presents CrossOracle, a production-deployed spoken dialogue system for real-time Hinglish voice interaction across eleven Expert Persona identities, achieving a mean TTS Real-Time Factor of 0.107 and a 100% barge-in resolution rate. The system, deployed at crossoracle.io, uses parallelized acoustic synthesis, language-aware semantic boundary heuristics, and a deterministic AbortController-based barge-in protocol to overcome latency bottlenecks in cascaded ASR-LLM-TTS pipelines.

CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis https://aclanthology.org/2026.sigdial-1.18.pdf Abstract We present CrossOracle, a production-deployed spoken dialogue system for real-time Hinglish Hindi-English code-switched voice interaction across eleven Expert Persona identities. The system addresses the latency bottleneck of cascaded ASR-LLM-TTS pipelines through three contributions: 1 a parallelized First-In-First-Stream TTS worker that overlaps synthesis with ongoing LLM generation, mathematically ensuring gapless audio playback; 2 a language-aware semantic boundary heuristic that flushes text chunks at Hindi danda and Latin punctuation boundaries, preserving prosodic integrity across code-switched utterances; and 3 a deterministic AbortController-based barge-in protocol that resolves user interruptions in under 1 ms. Empirical evaluation of live conversational logs demonstrates a mean TTS Real-Time Factor of 0.107 and a 100% barge-in resolution rate. The live system is deployed at crossoracle.io and supports persona switching, custom persona creation from natural language descriptions, and robust Hinglish ASR error tolerance via a Devanagari ratio mishear filter. The demonstration invites attendees to hold unscripted Hinglish conversations, stress-test the barge-in protocol, and construct novel personas on-the-fly.- Anthology ID: - 2026.sigdial-1.18 - Volume: Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue /volumes/2026.sigdial-1/ - Month: - August - Year: - 2026 - Address: - Atlanta, Georgia, USA - Editors: Jinho D. Choi /people/jinho-d-choi/ , Yun-Nung Chen /people/yun-nung-chen/ , Kotaro Funakoshi /people/kotaro-funakoshi/ , Ali Emami /people/ali-emami/ - Venue: SIGDIAL /venues/sigdial/ - SIG: SIGDIAL /sigs/sigdial/ - Publisher: - Association for Computational Linguistics - Note: - Pages: - 254–257 - Language: - URL: https://aclanthology.org/2026.sigdial-1.18/ https://aclanthology.org/2026.sigdial-1.18/ - DOI: - Cite ACL : - Yash Raj Singh. 2026. CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis https://aclanthology.org/2026.sigdial-1.18/ . In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue , pages 254–257, Atlanta, Georgia, USA. Association for Computational Linguistics. - Cite Informal : CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis https://aclanthology.org/2026.sigdial-1.18/ Singh, SIGDIAL 2026 - PDF: https://aclanthology.org/2026.sigdial-1.18.pdf https://aclanthology.org/2026.sigdial-1.18.pdf