VoiceLongMemEval (VLME) is a new benchmark that tests AI assistants on their ability to remember how users sounded by incorporating paralinguistic metadata—such as emotion labels, prosody descriptors, and voice events—into each conversational turn. The benchmark uses a three‑stage adversarial gate to ensure that models cannot succeed with transcript alone, revealing a significant affect gap: models gain 0.09 to 0.38 accuracy when provided with paralinguistic cues, and audio‑native models outperform standard ASR pipelines in extracting these signals. The dataset and code will be released upon acceptance.
By Ramit Pahwa, Parivesh Priye, Apoorva Beedu
arXiv:2606. 00851v1 Announce Type: cross Abstract: Empathetic spoken dialogue systems must infer a user's emotional state to respond appropriately, yet everyday speech often carries weak, neutral, or ambiguous affective cues.
By Sukru Samet Dindar, Riki Shimizu, Xilin Jiang, Nima Mesgarani
arXiv:2606. 24941v2 Announce Type: replace-cross Abstract: Reviewing recorded interviews for affective cues such as composure and agitation is slow and subjective, and cloud services that could automate the task require sensitive audio to leave the device.
By Wai Laam Mak, Isibor Kennedy Ihianle, Pedro Machado
arXiv:2607. 14846v1 Announce Type: cross Abstract: Current voice AI benchmarks typically evaluate isolated capabilities such as speech intelligibility, word error rate, or text-based dialogue quality, but they rarely test whether systems harness the acoustic information that distinguishes spoken language from its textual representation.
By David Ayllon, Alice Baird, Jeffrey Brooks, Franc Camps-Febrer, Jakub Piotr C{\l}apa, Theo Lebryk, Jens Madsen, Olya Ossipova, Sharath Rao, Hoon Shin, Tigran Soghbatyan, Georg Streich, Rashish Tandon, Panagiotis Tzirakis
The paper introduces an incongruence score that quantifies disagreement between a speaker’s verbal content and vocal expression in a shared valence‑arousal‑dominance space, validated against human judgments. Using this metric, the authors evaluate three audio‑capable large language models across acted, conversational, and spontaneous speech datasets, finding that higher incongruence consistently increases error rates when audio is present. The study also shows that supervised classifiers behave oppositely, suggesting the challenge lies in how models fuse multimodal evidence rather than in the signal itself, and that the score remains predictive even without an emotion lexicon.
By Fengji Jing, Guy Laban
The article surveys multi‑turn conversational AI, highlighting its shift from isolated text prompts to sustained, multimodal interactions that involve clarifying goals, revising requests, and switching topics. It reviews literature across text‑only dialogue, AudioLLMs, multimodal and omni‑modal systems, and tool‑augmented agents, organizing findings around datasets, models, training, evaluation, and cross‑cutting challenges. The analysis reveals that while multimodal perception and action have progressed rapidly, systems still struggle with persistent memory, cross‑turn grounding, full‑duplex interaction, robust evaluation, and cultural alignment.
By Syeda Faiza Ahmed, Zien Sheikh Ali, Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury