arXiv AI
Aug 11
PACE: A Playback-Aligned Context Engine for LLM-Based Full-Duplex Voice Dialogue
arXiv:2608. 07631v1 Announce Type: cross Abstract: LLM-based full-duplex voice services allow users to speak while the assistant is responding.
HyWA: Architecture-Preserving Personalized Voice Activity Detection for Full-Duplex Voice Assistants
arXiv:2510. 12947v3 Announce Type: replace-cross Abstract: Voice activity detection (VAD) serves as an early gate in voice-assistant pipelines for smart devices.
Related stories
arXiv AI
Jun 8
IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems
arXiv:2606. 06559v1 Announce Type: cross Abstract: Full-duplex spoken dialogue models allow voice agents to listen and speak concurrently, enabling natural interaction with real-time overlap.
arXiv AI
Jun 18
Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation
arXiv:2603. 10827v2 Announce Type: replace-cross Abstract: Speech-aware large language models (LLMs) can accept speech inputs, yet their training objectives largely emphasize linguistic content or specific fields such as emotions or the speaker's gender, leaving it unclear whether they encode speaker identity.
arXiv AI
Jul 17
Large Audio Language Models for Spoofing-Aware Speaker Verification
arXiv:2607. 14753v1 Announce Type: cross Abstract: Recent advances in text-to-speech and voice cloning make high-quality spoofing inexpensive and scalable, threatening voice authentication systems, especially automatic speaker verification (ASV).
Hugging Face Trending Papers
Jul 7
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs
Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP community. Despite notable progress, recent endeavors are fundamentally constrained by severe modality interference, which causes substantial knowledge degradation and compromises semantic integrity -- ultimately making full-duplex SLMs feel unnatural and unintelligent.
arXiv AI
Jun 30
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
arXiv:2606. 29031v1 Announce Type: cross Abstract: In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from modern text-to-speech (TTS) is an appealing alternative for training automatic speech recognition (ASR) without exposing sensitive customer recordings.
arXiv AI
2d ago
Teffic-Audio: Tell Fact from Fiction
arXiv:2607. 28351v2 Announce Type: replace-cross Abstract: Speech deepfake detection has expanded in scope with increasingly heterogeneous spoofing mechanisms, including speech synthesis, voice conversion, vocoder reconstruction, and neural-codec resynthesis.
arXiv Machine Learning
Jun 8
SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview Guardrails
arXiv:2606. 06837v1 Announce Type: cross Abstract: Scripted vs spontaneous speech detection is appealing for interview guardrails, but benchmark performance can be inflated by shortcuts tied to corpus identity, channel conditions, and recording artifacts rather than speaking style itself.
arXiv AI
Aug 11
Scaling Audio Models Efficiently: A Joint Study of Compute Constraints and Optimization Behavior
arXiv:2606. 22790v2 Announce Type: replace-cross Abstract: In this paper, we investigate the tradeoffs between compute allocation and model performance for two speech processing tasks: Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER).
arXiv AI
Aug 5
UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search
arXiv:2503. 00340v2 Announce Type: cross Abstract: Lightweight models are essential for real-time speech enhancement applications.
arXiv AI
Jun 9
Liberating LLM Capabilities in Full-Duplex Speech Models
arXiv:2606. 07547v1 Announce Type: cross Abstract: Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabilities such as code generation, structured analysis, and multi-step reasoning in realtime interaction, for tasks that require persistent, structured, and inspectable intermediate outputs.
arXiv Machine Learning
Jun 4
FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
arXiv:2606. 05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models.