A survey proposing an L0-L3 architectural hierarchy, T×I×R interaction ontology, and IDLE/LISTEN/SPEAK/WAIT/DUAL decision state machine for full-duplex spoken dialogue systems, documenting a realization gap between architectural potential and observed behavior due to training data limits.
Personaplex: V oice and role control for full duplex conversational speech models
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 13roles
background 1polarities
background 1representative citing papers
FD-SLMs exhibit state inertia during abrupt interruptions that a training-free perception-vector steering intervention mitigates, lifting correctness from 28% to 45% and IWOR from 40% to 72% on the Zero-Buffer Benchmark.
PolySpeech-100 is a new benchmark for native-level speech comprehension across 110 linguistic variants that evaluates 22 models and reports E2E advantages on dialects, robustness gaps on low-resource languages, and degradation from Chain-of-Thought prompting.
Introduces the first full-duplex audio-visual-to-audio-visual benchmark, showing current agents fail to use visual nonverbal cues in live conversation.
DuplexSLA introduces a three-channel full-duplex architecture that synchronizes continuous user audio, discrete assistant audio, and rate-limited textual actions inside a single backbone for native turn-taking and in-conversation tool use.
TiCo enables spoken dialogue models to follow explicit time constraints in generated responses using Spoken Time Markers and reinforcement learning with verifiable rewards, cutting duration error by 2.7x over its backbone.
FacePlex introduces a unified streaming model with Rolling Flow Matching and Rolling Cross-Attention to enable full-duplex joint real-time generation of speech and facial motion tokens.
A multi-axis RL alignment technique improves pause handling, turn-taking, backchanneling, and interruption response in full-duplex spoken dialogue models by optimizing axis-specific rewards derived from human audio segments.
DyaPlex introduces a dual-tower Transformer that adds a streaming motion pathway to a frozen full-duplex speech model using dyadic token interleaving and time-aligned RoPE for synchronized multimodal dyadic interaction.
ASPIRin decouples speaking timing from token content via binary action space projection and applies GRPO with rule-based rewards to optimize interactivity in SLMs without semantic collapse or repetition.
A speech-based model forecasts conversation turn endpoints up to 2.56 seconds ahead to enable lower-latency spoken dialogue via speculative LLM and TTS execution.
A VAE-plus-diffusion model jointly restores and separates degraded monaural two-speaker dialogue into clean full-duplex speaker tracks with better intelligibility and faster inference than a baseline.
IRAF introduces an adaptive fusion module that uses a predicted scalar reliability gate to reduce the impact of interfering speakers on user audio representations in end-to-end full-duplex spoken dialogue systems, with reported gains on MS-MARCO and InstructS2S-200K.
citing papers explorer
-
A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine
A survey proposing an L0-L3 architectural hierarchy, T×I×R interaction ontology, and IDLE/LISTEN/SPEAK/WAIT/DUAL decision state machine for full-duplex spoken dialogue systems, documenting a realization gap between architectural potential and observed behavior due to training data limits.
-
Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering
FD-SLMs exhibit state inertia during abrupt interruptions that a training-free perception-vector steering intervention mitigates, lifting correctness from 28% to 45% and IWOR from 40% to 72% on the Zero-Buffer Benchmark.
-
PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
PolySpeech-100 is a new benchmark for native-level speech comprehension across 110 linguistic variants that evaluates 22 models and reports E2E advantages on dialects, robustness gaps on low-resource languages, and degradation from Chain-of-Thought prompting.
-
VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents
Introduces the first full-duplex audio-visual-to-audio-visual benchmark, showing current agents fail to use visual nonverbal cues in live conversation.
-
DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action
DuplexSLA introduces a three-channel full-duplex architecture that synchronizes continuous user audio, discrete assistant audio, and rate-limited textual actions inside a single backbone for native turn-taking and in-conversation tool use.
-
TiCo: Time-Controllable Spoken Dialogue Model
TiCo enables spoken dialogue models to follow explicit time constraints in generated responses using Spoken Time Markers and reinforcement learning with verifiable rewards, cutting duration error by 2.7x over its backbone.
-
FacePlex: Full-Duplex Joint Speech-Facial Motion Generation for Conversational Avatars
FacePlex introduces a unified streaming model with Rolling Flow Matching and Rolling Cross-Attention to enable full-duplex joint real-time generation of speech and facial motion tokens.
-
Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
A multi-axis RL alignment technique improves pause handling, turn-taking, backchanneling, and interruption response in full-duplex spoken dialogue models by optimizing axis-specific rewards derived from human audio segments.
-
DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction
DyaPlex introduces a dual-tower Transformer that adds a streaming motion pathway to a frozen full-duplex speech model using dyadic token interleaving and time-aligned RoPE for synchronized multimodal dyadic interaction.
-
ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
ASPIRin decouples speaking timing from token content via binary action space projection and applies GRPO with rule-based rewards to optimize interactivity in SLMs without semantic collapse or repetition.
-
Endpoint Anticipation for Low-Latency Spoken Dialogue
A speech-based model forecasts conversation turn endpoints up to 2.56 seconds ahead to enable lower-latency spoken dialogue via speculative LLM and TTS execution.
-
DialogueSidon: Recovering Full-Duplex Dialogue Tracks from In-the-Wild Dialogue Audio
A VAE-plus-diffusion model jointly restores and separates degraded monaural two-speaker dialogue into clean full-duplex speaker tracks with better intelligibility and faster inference than a baseline.
-
IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems
IRAF introduces an adaptive fusion module that uses a predicted scalar reliability gate to reduce the impact of interfering speakers on user audio representations in end-to-end full-duplex spoken dialogue systems, with reported gains on MS-MARCO and InstructS2S-200K.