← Back to all news
arXiv Computation and Language By Yizhou Peng, Ziyang Ma, Changsong Liu, Yi-Wen Chao, Xie Chen, Eng Siong Chng

Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems

Read the original on arXiv Computation and Language →

The paper introduces a cause-aware error recovery framework for cascaded Automatic Speech Recognition – Large Language Model (ASR‑LLM) pipelines in Spoken Dialogue Systems. It replaces simple ASR confidence filtering with precision‑focused detectors that use deep ASR latent representations to classify token‑level errors into perception, comprehension, and deletion failures. This fine‑grained diagnosis enables the LLM to execute targeted, multi‑turn clarification strategies, leading to a more than two‑fold increase in recall on domain‑shift errors and significant reductions in word error rate and downstream task errors across varied accents, distortions, and domains.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Aug 28

When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue

The paper introduces ContraTalk, a benchmark that tests whether dialogue models truly use acoustic cues or rely on transcript shortcuts. It formalizes cross‑modal disagreement, creates conflict and consistent QA examples, and proposes an Audio Twin representation to expose acoustic evidence to models. Experiments show that while text‑only LLMs perform well on consistent cases, they falter on conflict cases, and AudioLLMs only partially mitigate this issue.

By Yen-Ju Lu, Yuzhe Wang, Yaohan Guan, Xiluo He, Jiarui Hai, Mingrui Liang, Kaavya Chaparala, Thomas Thebaud, Laureano Moro-Velazquez, Najim Dehak, Jesus Villalba
llmsagentsmultimodalbenchmarkssafety
More like this →
arXiv AI
3d ago

Audio LLMs Know When They Can't Hear You

The paper investigates whether audio large language models (Audio LLMs) can detect when their own transcriptions are unreliable. It finds that the models are poor at self-assessment and that existing methods offer limited detection. By leveraging audio-encoder representations, the authors develop a lightweight predictor that accurately flags unreliable transcriptions and can prompt user clarification without altering the underlying model.

By Amirhosein Javadi, Richa Dixit, Mehrdad Farajtabar, Minsik Cho, Devang Naik, Mohammad Samragh
llmssafety
More like this →
arXiv Computation and Language
Sep 14

Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up

The paper introduces ASCIL, a post‑ASR correction framework that re‑evaluates wake‑up intent by combining acoustic embeddings, linguistic cues, device context, and past misclassifications. ASCIL interprets both implicit (hesitation, disengagement, silence) and explicit (cancellation, repetition) signals as noisy indicators of misclassification, enabling online pattern updates without manual annotation. On a proprietary dataset of 3,667 interactions, ASCIL reduces errors by up to 54.27% relative on a session‑disjoint subset and 24.39% at a 0.90 threshold, while adding less than 60 ms of latency and improving intentional acceptance rates.

By Preeti Saraswat, Divya Neelagiri, Anil Yadav
ragmultimodalbenchmarks
More like this →
arXiv Computation and Language
Sep 22

The Bairong System for MLC-SLM 2026: Dynamic Question-Aware Evidence Routing for Multilingual Conversational Speech Understanding

arXiv:2609.22214v1 Announce Type: new Abstract: Long multilingual conversational spoken question answering requires systems to balance long-range transcript semantics with sparse acoustic and speaker...

By Shangkun Huang, Junchao Hu, Huan Shen, Guoji Wang, Yingao Wang, Shaosai Li, Wei Zou, Yunzhang Chen
nlpmultimodal
More like this →
arXiv Computation and Language
Sep 11

Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)

The paper introduces LOGIC (Logit‑Space Integration for Contextual Biasing), a new framework that injects contextual entity information directly into the decoding layer of Speech Large Language Models, bypassing the limitations of prompt‑based methods. LOGIC operates with constant‑time complexity regardless of the size of the entity list, and experiments with the Phi‑4‑MM model across 11 multilingual locales show an average 9% relative reduction in Entity WER while adding only a 0.30% increase in False Alarm Rate.

By Peidong Wang, Jian Xue, Jinyu Li
llmsefficiencysafety
More like this →