@inproceedings{singh-2026-crossoracle,
title = "{C}ross{O}racle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis",
author = "Singh, Yash Raj",
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.18/",
pages = "254--257",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-2026-crossoracle">
<titleInfo>
<title>CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="given">Raj</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">singh-2026-crossoracle</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.18/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>254</start>
<end>257</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis
%A Singh, Yash Raj
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F singh-2026-crossoracle
%X 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.
%U https://aclanthology.org/2026.sigdial-1.18/
%P 254-257
Markdown (Informal)
[CrossOracle: An Agentic Framework for Real-Time Expert Personas with Parallelized Acoustic Synthesis](https://aclanthology.org/2026.sigdial-1.18/) (Singh, SIGDIAL 2026)
ACL