AI & ML
StepAudio 3 Realtime Technical Report
arXiv cs.SD0 views
arXiv:2609.14005v3 Announce Type: replace Abstract: Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a continuous listen-converse-think-act loop. Deep Perception captures rich acoustic cues to interpret user intent, while Seamless Duplex models synchronized audio streams to handle pauses, backchannels, and interruptions naturally. Crucially, we resolve the tension between deep deliberation and latency via Think-While-Speaking, executing private reasoning in parallel with spoken delivery. In reasoning mode, StepAudio 3 reaches a 73.0 macro average on StepAudioChat. With Think-While-Speaking, it achieves dialogue and reasoning performance comparable to dedicated reasoning models while speaking in real time. Furthermore, an integrated Voice Agent handles asynchronous tool execution without disrupting the dialogue flow. StepAudio 3 Realtime achieves top-tier performance across key dimensions: an exceptional 90.6 on the MMSU benchmark, 98.9 Overall on the Artificial Analysis Full-Duplex Bench, and a 56.0% macro task-success rate on $\tau$-Voice.
Source：https://arxiv.org/abs/2609.14005PreviousTontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded ContextNextRobust Cross-Domain Speech-Based Alzheimer's Disease Detection via Iterative Adversarial Self-Training
Related posts
Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
0arXiv stat.ML
Toward Optimal Switching Regret for Multi-Armed Bandits with Oblivious Adversary
0arXiv stat.ML
Spectral Condition for $\mu$P under Width-Depth Scaling
0arXiv stat.ML
A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems
0arXiv stat.ML
Who Gets Watched? Allocating Scarce Escalation Resources on Pediatric Wards with Neural Index Policies
0arXiv stat.ML
Minimax Alternating Regret for the Experts Problem and Online Convex Optimization
0arXiv stat.ML