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...
arXiv:2605.13841v3 Announce Type: replace-cross Abstract: Voice agents are increasingly deployed across enterprise applications. However, no existing benchmark jointly addresses realistic conversatio...
The paper introduces Inquesto Score (IS), a protocol that measures voice‑agent reliability by calculating the percentage of calls that reach the caller’s goal without functional failure. IS defines explicit failure events and severity levels, evaluates timing, semantic, and state‑dependent failures using audio, scenario predicates, tool traces, and a pinned open‑model judge, and provides diagnostic views on behavior, acoustic robustness, identity handling, and speaker groups. The authors evaluate IS v0.1 on 30 scenarios, three acoustic conditions, four speaker groups, and 306 calls per agent across 13 configurations, demonstrating that reliable measurement requires evidence beyond transcripts and explicit treatment of deployment conditions.
The paper evaluates the use of large language models (LLMs) as judges for assessing conversational voice agents, comparing human judgments with GPT‑4.1 and GPT‑5 across telecom and retail interactions. It examines agreement, metric‑level correlations, and consistency across three evaluation configurations (p0, p1, p2) to determine how reliably LLMs can judge conversational quality and safety. The study finds that LLM‑based evaluation can be effective but its reliability varies by metric and configuration, suggesting a hybrid approach where LLMs handle scalable assessment while humans focus on metrics requiring contextual interpretation.
arXiv:2608.27783v3 Announce Type: replace-cross Abstract: Speech language models (speech LLMs) can generate plausible outputs from audio that contains no usable speech evidence. We study this failure...
The paper introduces llmovoice, a middleware that explicitly models voice context for large language model (LLM) serving in voice AI applications. By incorporating speaking rate, background noise, packet loss, and other paralinguistic factors into a bounded context, llmovoice guides the LLM to generate more aligned responses. Experiments show significant reductions in speaking‑rate errors, false interruptions, and model usage costs, especially in long voice sessions.
The paper introduces SITAR, a situational distortion metric for evaluating automatic speech recognition (ASR) systems. SITAR aggregates situational severity and cumulative extent into a unified score using a bounded recursive formulation, and is implemented as a lightweight BERT-family regressor that requires minimal runtime cost. The authors validate SITAR through extrinsic and intrinsic protocols, showing it tracks capability scaling and provides diagnostic utility across diverse datasets and models.
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: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.
arXiv:2608. 02235v1 Announce Type: cross Abstract: Recent advances in neural text-to-speech (TTS) systems have substantially improved speech naturalness and intelligibility across many languages.
The paper investigates how to evaluate generative audio large language models (Audio‑LLMs) on known closed‑set tasks by separating the decision to call a generative model from the use of acoustic evidence. It introduces a controlled call‑decision framework where a policy can choose between a transcript label, encoder evidence from CLAP, AST, or WavLM, or a generative call to Qwen2‑Audio, Qwen2.5‑Omni, or MOSS‑Audio, and measures the impact of generative calls on accuracy. Results on the VocalSound dataset show that while transcript‑only accuracy is low (0.296), encoder‑based controls achieve high accuracy (≈0.85) without any generative calls, and adding generative calls yields only a marginal improvement (0.925 vs. 0.921).
arXiv:2609.20995v1 Announce Type: cross Abstract: Natural spoken interaction requires more than streaming ASR, language generation, and speech synthesis: a system must react to overlap without cancel...