English
Related papers

Related papers: FireRedChat: A Pluggable, Full-Duplex Voice Intera…

200 papers

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges. For example, downstream modules are affected by earlier modules, and the performance…

Computation and Language · Computer Science 2018-02-13 Xiujun Li , Yun-Nung Chen , Lihong Li , Jianfeng Gao , Asli Celikyilmaz

We present X-Talk, an open-source framework that champions a decoupled, modular design for LLM-driven speech-to-speech (S2S) systems. While the dominant trend favors end-to-end (E2E) modeling to optimize information flow, these…

Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely on noisy, low-quality human conversation data. This…

Computation and Language · Computer Science 2026-05-06 Yuqin Dai , Ning Gao , Wei Zhang , Jie Wang , Zichen Luo , Jinpeng Wang , Yujie Wang , Ruiyuan Wu , Chaozheng Wang

As spoken dialogue systems expand beyond traditional assistant roles to encompass diverse personas -- such as authoritative instructors, uncooperative merchants, or distracted workers -- they require distinct, human-like turn-taking…

Computation and Language · Computer Science 2026-05-08 Hyunbae Jeon , Jinho D. Choi

Full-duplex interaction is crucial for natural human-machine communication, yet remains challenging as it requires robust turn-taking detection to decide when the system should speak, listen, or remain silent. Existing solutions either rely…

Computation and Language · Computer Science 2025-09-30 Guojian Li , Chengyou Wang , Hongfei Xue , Shuiyuan Wang , Dehui Gao , Zihan Zhang , Yuke Lin , Wenjie Li , Longshuai Xiao , Zhonghua Fu , Lei Xie

End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain…

The emergence of instruction-tuned large language models (LLMs) has advanced the field of dialogue systems, enabling both realistic user simulations and robust multi-turn conversational agents. However, existing research often evaluates…

Computation and Language · Computer Science 2025-07-22 Chalamalasetti Kranti , Sherzod Hakimov , David Schlangen

Most end-to-end (E2E) spoken dialogue systems (SDS) rely on voice activity detection (VAD) for turn-taking, but VAD fails to distinguish between pauses and turn completions. Duplex SDS models address this by predicting output continuously,…

Computation and Language · Computer Science 2025-10-03 Siddhant Arora , Jinchuan Tian , Hayato Futami , Jiatong Shi , Yosuke Kashiwagi , Emiru Tsunoo , Shinji Watanabe

The rapid advances in text-to-speech (TTS) technologies have made audio deepfakes increasingly realistic and accessible, raising significant security and trust concerns. While existing research has largely focused on detecting…

Sound · Computer Science 2026-02-03 Alabi Ahmed , Vandana Janeja , Sanjay Purushotham

Despite broad interest in modeling spoken dialogue agents, most approaches are inherently "half-duplex" -- restricted to turn-based interaction with responses requiring explicit prompting by the user or implicit tracking of interruption or…

Computation and Language · Computer Science 2024-09-25 Bandhav Veluri , Benjamin N Peloquin , Bokai Yu , Hongyu Gong , Shyamnath Gollakota

Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o, have captured significant attention in the speech domain. Compared to traditional three-tier cascaded spoken dialogue models that comprise speech recognition…

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and…

This work proposes FireRedTTS, a foundation text-to-speech framework, to meet the growing demands for personalized and diverse generative speech applications. The framework comprises three parts: data processing, foundation system, and…

Sound · Computer Science 2025-04-14 Hao-Han Guo , Yao Hu , Kun Liu , Fei-Yu Shen , Xu Tang , Yi-Chen Wu , Feng-Long Xie , Kun Xie , Kai-Tuo Xu

The intelligent dialogue system, aiming at communicating with humans harmoniously with natural language, is brilliant for promoting the advancement of human-machine interaction in the era of artificial intelligence. With the gradually…

Artificial Intelligence · Computer Science 2022-07-05 Hao Wang , Bin Guo , Yating Zeng , Yasan Ding , Chen Qiu , Ying Zhang , Lina Yao , Zhiwen Yu

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's needs is key to a smooth interaction. Traditionally TOD systems are composed of several modules that interact with one another. While each…

Computation and Language · Computer Science 2023-11-21 Lucas Druart , Léo Jacqmin , Benoît Favre , Lina Maria Rojas-Barahona , Valentin Vielzeuf

Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between…

Computation and Language · Computer Science 2025-11-13 Yejin Yoon , Yuri Son , Namyoung So , Minseo Kim , Minsoo Cho , Chanhee Park , Seungshin Lee , Taeuk Kim

Recent advancements in large language models (LLMs) have led to significant progress in text-based dialogue systems. These systems can now generate high-quality responses that are accurate and coherent across a wide range of topics and…

Computation and Language · Computer Science 2025-01-10 Long Mai , Julie Carson-Berndsen

Despite recent advances, efficient and robust turn-taking detection remains a significant challenge in industrial-grade Voice AI agent deployments. Many existing systems rely solely on acoustic or semantic cues, leading to suboptimal…

Computation and Language · Computer Science 2026-03-30 Guangzhao Yang , Yu Pan , Shi Qiu , Ningjie Bai

Despite the growing popularity of audio platforms, fact-checking spoken content remains significantly underdeveloped. Misinformation in speech often unfolds across multi-turn dialogues, shaped by speaker interactions, disfluencies,…

Social and Information Networks · Computer Science 2025-08-19 Chaewan Chun , Lysandre Terrisse , Delvin Ce Zhang , Dongwon Lee

Real-time voice assistants must revise task state when users interrupt mid-response, but existing spoken-dialog benchmarks largely evaluate turn-based interaction and miss this failure mode. We introduce EchoChain, a controlled benchmark…

Computation and Language · Computer Science 2026-04-21 Smit Nautambhai Modi , Gandharv Mahajan , Marc Wetter , Randall Welles