Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2509.20410

Phoenix-VAD: Streaming Semantic Endpoint Detection for Full-Duplex Speech Interaction

Weijie Wu·Wenhao Guan·Kaidi Wang·Peijie Chen·Zhuanling Zha·Junbo Li·Jun Fang·Lin Li·Qingyang Hong
View original source ↗Read source document ↗Export metadata ↓

Abstract

Spoken dialogue models have significantly advanced intelligent human-computer interaction, yet they lack a plug-and-play full-duplex prediction module for semantic endpoint detection, hindering seamless audio interactions. In this paper, we introduce Phoenix-VAD, an LLM-based model that enables streaming semantic endpoint detection. Specifically, Phoenix-VAD leverages the semantic comprehension capability of the LLM and a sliding window training strategy to achieve reliable semantic endpoint detection while supporting streaming inference. Experiments on both semantically complete and incomplete speech scenarios indicate that Phoenix-VAD achieves excellent and competitive performance. Furthermore, this design enables the full-duplex prediction module to be optimized independently of the dialogue model, providing more reliable and flexible support for next-generation human-computer interaction.

Explore related subjects

eess.AScs.SD

Keep this discovery

BibTeXRIS

Weijie Wu, Wenhao Guan, Kaidi Wang, Peijie Chen, Zhuanling Zha, Junbo Li, Jun Fang, Lin Li, Qingyang Hong. 2026-09-03. Phoenix-VAD: Streaming Semantic Endpoint Detection for Full-Duplex Speech Interaction. https://arxiv.org/abs/2509.20410

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.SD subjecteess.AS subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related papers

arXiv2026

BFA: Real-time Multilingual Text-to-speech Forced Alignment

We present Bournemouth Forced Aligner (BFA), a system that combines a Contextless Universal Phoneme Encoder (CUPE) with a connectionist temporal classification (CTC)based decoder. BFA introduces explicit modelling of inter-phoneme gaps and silences and hierarchical decoding strategies, enabling fine-grained boundary prediction. Evaluations on TIMIT and Buckeye corpora show that BFA achieves competitive recall relative to Montreal Forced Aligner at relaxed tolerance levels, while predicting both onset and offset boundaries for richer temporal structure. BFA processes speech up to 240x faster than MFA, enabling faster than real-time alignment. This combination of speed and silence-aware alignment opens opportunities for interactive speech applications previously constrained by slow aligners.

eess.AS↗
arXiv2024

BUT Systems and Analyses for the ASVspoof 5 Challenge

This paper describes the BUT submitted systems for the ASVspoof 5 challenge, along with analyses. For the conventional deepfake detection task, we use ResNet18 and self-supervised models for the closed and open conditions, respectively. In addition, we analyze and visualize different combinations of speaker information and spoofing information as label schemes for training. For spoofing-robust automatic speaker verification (SASV), we introduce effective priors and propose using logistic regression to jointly train affine transformations of the countermeasure scores and the automatic speaker verification scores in such a way that the SASV LLR is optimized.

cs.SD↗
arXiv2026

Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition

Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing while keeping language-specific orthography in a separate module. While large language models (LLMs) are promising for P2G, multilingual P2G remains challenging due to language-aware generation and severe cross-language data imbalance. We study multilingual LLM-based P2G on the ten-language CV-Lang10 benchmark. We examine robustness strategies that account for S2P uncertainty, including DANP and Simplified SKM (S-SKM). S-SKM is a Monte Carlo approximation that avoids CTC-based S2P probability weighting in P2G training. Robust training and low-resource oversampling reduce the average WER from 10.56% to 7.66%.

eess.AS↗