arXiv Computation and Language September 14, 2026 By Qingxiang Guo, Wenke Fan, Shuofeng Zhao, Dawei Yang, Zhiyang Zhou, Yingxin Shang, Hongwei Cai, Zhou Wang, Weixu Wang, Lin Yang, Shuran Zhou, Yang Song

DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events

Read the original on arXiv Computation and Language →

DuplexDrama is a newly announced synthesized spoken dialogue dataset that uniquely combines complete persona and scenario settings, three full‑duplex behaviors (interruption, backchannel, incomplete), expressive speech with persona‑aligned emotion labels, and script‑aware sound events. The dataset was created through a four‑stage pipeline and validated for quality on both scripts and audio, yielding over 2,000 hours of audio featuring 64 voices across 13 personas and 5 age groups, with 3.8% of turns containing full‑duplex behaviors. A curated bilingual subset of 6,400 dialogues (800 hours total) will be released to support research in full‑duplex spoken dialogue models, and evaluation prompts will accompany the dataset.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

llms

arXiv Computation and Language

Oct 1

DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirements

arXiv:2609.39446v1 Announce Type: new Abstract: Existing full-duplex speech benchmarks cover only subsets of real-time interaction behaviors, often under limited contextual conditions. We introduce D...

By Keyue Xing, Wentao Ding, Mengmeng Wang, Wenming Tu, Zilong Zheng, Yipeng Kang

benchmarks

arXiv AI

Sep 30

MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation

arXiv:2609.36903v1 Announce Type: cross Abstract: End-to-end full-duplex speech models have brought open-source machine conversation closer to human-like interaction, yet existing systems remain limi...

By Ke Wang, Houxing Ren, Zimu Lu, Yunqiao Yang, Zhuofan Zong, Mingjie Zhan, Hongsheng Li

robotics benchmarks

Hugging Face Trending Papers

Sep 8

ConversationalVoice: Full-Duplex Speech Data from Real Conversations through Source-Faithful Reconstruction and Conversation-Grounded Expansion

Full-duplex speech models require training data that preserves turn-taking, overlap, interruption, and backchannel behavior, yet these signals are entangled across speakers in noisy real-world recordi...

llms safety

arXiv AI

Oct 15

D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones

arXiv:2610.17124v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken language models (HD...

By Cheng-Kuang Chang, Alexander H. Liu, Brian Kingsbury, Hilde Kuehne, Rogerio Feris, Samuel Thomas, James Glass, Kai-Wei Chang

llms fine-tuning efficiency benchmarks

arXiv AI

Oct 15

DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?

arXiv:2610.17738v1 Announce Type: new Abstract: End-to-end (E2E) full-duplex spoken language models (FD-SLMs) enable simutanous listening and speaking continously, requiring models to take appropriat...

By Jiaheng Dong, Shihong Tan, Gongping Huang, Jean Honorio, Abhirup Ghosh, Ting Dang

llms benchmarks

arXiv AI

Sep 25

A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations

The paper introduces a pipeline that generates intent‑labeled, two‑channel conversational speech from relational event lists, enabling controlled synthesis of full‑duplex dialogue with 42 phenomena across eight families in English and Mandarin. By having an LLM author each event’s speaker, text, conversational act, and attachment, and then aligning and timing these events independently, the system produces diverse, realistic turn‑taking signals. Experiments show that models trained on this synthetic corpus achieve higher floor‑occupancy accuracy and better start‑speaking/listening F1 scores compared to models trained on prior data.

By Matthew Sun, Vinay Kothapally, Meng Yu, Chao Huang, Hao Zhang, Yixuan Zhang, Steve Yves

llms fine-tuning

One email a morning, machine-written

Related stories

DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral Requirements

MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation

ConversationalVoice: Full-Duplex Speech Data from Real Conversations through Source-Faithful Reconstruction and Conversation-Grounded Expansion

D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones

DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?

A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations