arXiv:2607. 21180v1 Announce Type: new Abstract: Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood.
arXiv:2609.35812v1 Announce Type: new Abstract: In-car conversational assistants (ICAs) are increasingly integrated into vehicles to support route planning, vehicle control, and information access. E...
arXiv:2609.38867v1 Announce Type: new Abstract: Large language model (LLM) computer-use agents are typically evaluated with clean written instructions, despite speech being an increasingly popular in...
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.
Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged. Yet existing benchmarks typically evaluate prosodic perception, response appropriateness, and task-oriented dialogue in isolation, making it difficult to test whether prosodic evidence changes downstream decisions.
The paper presents a new wake‑up system for voice assistants that goes beyond simple keyword spotting by adding contextual trigger detection. After the wake word is heard, the system reasons to differentiate between actual user commands and unrelated speech, enabling more efficient and context‑aware interactions. A data‑generation architecture is introduced that creates a 62.3‑hour corpus of controllable multi‑speaker conversations, including direct invocations, contextual follow‑ups, and non‑addressed speech, and experimental results confirm the approach’s effectiveness across varied synthetic scenarios.
arXiv:2603.16783v2 Announce Type: replace Abstract: Robust voice agents require exposure to the full diversity of how people interact through speech. However, obtaining enough spoken interactions is...
arXiv:2608. 19515v1 Announce Type: new Abstract: Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged.
Scalable Context Orchestration for Serving LLMs Over Voice presents llmovoice, a middleware that explicitly models voice context—including speaking rate, background noise, and packet loss—to guide large language model responses. By constructing a bounded voice context at each turn, llmovoice improves alignment with user preferences and reduces errors, achieving a 52.4% drop in speaking‑rate alignment error and a 0.9% false‑interruption rate under packet loss. In addition, it cuts model usage costs dramatically, lowering per‑turn cost by up to 24.9× while maintaining 98.7% of baseline answer quality in long sessions.
arXiv:2609.09852v1 Announce Type: new Abstract: The advance of multimodal large language models (MLLMs) has fundamentally reshaped the paradigm of human-computer interaction, especially speech intera...
The paper introduces a 202-scenario benchmark to evaluate how large language models (LLMs) handle safety-critical authorization decisions for vehicle voice commands. It tests two local open-weight models and three API-based LLMs, finding alignment scores ranging from 40.1% to 89.1% and noting persistent false execution errors. The study concludes that structured LLM decisions alone are insufficient for safety, recommending an independent enforcement layer to verify tool permissions and vehicle-state constraints before any vehicle function is invoked.
The paper introduces Jarvis, an offline, edge‑deployable voice assistant designed for autonomous racecars. It combines speech recognition, synthesis, and a lightweight text‑to‑command classifier fine‑tuned from the Mistral 7B model to provide high‑level behavioral commands. Experiments show 97.63 % intent recognition accuracy with an average latency of 1.39 s, outperforming larger online‑hosted models and enabling quick response times for time‑critical driving tasks.
SCB: SpeechConversationBench (SCB) evaluates multi-turn reasoning in speech-to-speech models by using 103 sharded GSM8K mathematical problems. The benchmark compares three delivery modes: a full single-turn problem, a concatenated multi-shard version, and an incremental spoken disclosure across turns. Results show that sharded accuracy drops by 5.0–25.3 percentage points for four commercial systems, while the internal LEGO pipeline maintains 77.5% accuracy across all conditions, outperforming GPT‑4o Realtime’s 76.6% sharded accuracy.