相关论文: SoulX-Duplug: Plug-and-Play Streaming State Predic…
This paper presents a hybrid dialog state tracker enhanced by trainable Spoken Language Understanding (SLU) for slot-filling dialog systems. Our architecture is inspired by previously proposed neural-network-based belief-tracking systems.…
Speech-to-speech language models have recently emerged to enhance the naturalness of conversational AI. In particular, full-duplex models are distinguished by their real-time interactivity, including handling of pauses, interruptions, and…
Achieving a balance between high-fidelity visual quality and low-latency streaming remains a formidable challenge in audio-driven portrait generation. Existing large-scale models often suffer from prohibitive computational costs, while…
As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction. However, the development of such models is…
While full-duplex speech agents enable natural, low-latency interaction by speaking and listening simultaneously, their consistency and task performance in multi-turn settings remain underexplored. We introduce Full-Duplex-Bench-v2…
Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring complete transcription and full reasoning…
Human conversation is organized by an implicit chain of thought and manifests as temporally structured conversational behaviors. Capturing this perceptual pathway is critical for building natural full-duplex interactive systems. We propose…
We present a generative dialogue system capable of operating in a full-duplex manner, allowing for seamless interaction. It is based on a large language model (LLM) carefully aligned to be aware of a perception module, a motor function…
Achieving full-duplex communication in spoken dialogue systems (SDS) requires real-time coordination between listening, speaking, and thinking. This paper proposes a semantic voice activity detection (VAD) module as a dialogue manager (DM)…
Real-time speech conversation is essential for natural and efficient human-machine interactions, requiring duplex and streaming capabilities. Traditional Transformer-based conversational chatbots operate in a turn-based manner and exhibit…
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…
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…
Audio-visual speaker extraction isolates a target speaker's speech from a mixture speech signal conditioned on a visual cue, typically using the target speaker's face recording. However, in real-world scenarios, other co-occurring faces are…
Spoken conversational systems require more than accurate speech generation to have human-like conversations: to feel natural and engaging, they must produce conversational behaviour that adapts dynamically to the context. Current spoken…
The goal of dialogue state tracking (DST) is to predict the current dialogue state given all previous dialogue contexts. Existing approaches generally predict the dialogue state at every turn from scratch. However, the overwhelming majority…
While speech interaction finds widespread utility within the Extended Reality (XR) domain, conventional vocal speech keyword spotting systems continue to grapple with formidable challenges, including suboptimal performance in noisy…
Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited…
Real-time duplex interaction is essential for multimodal AI systems operating in real-world scenarios, where models must continuously process streaming inputs and respond at appropriate moments. However, most existing multimodal large…
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…
Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…