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

arXiv:2605.25404 · cs.CL, eess.AS · Submitted 2026-05-25 · Read on arXiv

cs.CL, eess.AS

Submitted: 2026-05-25

Updated: 2026-09-24

Code: https://github.com/tatsu-lab/stanford_alpaca

Terminology

• Accuracy — 11× in this paper · explained in 1 episode
• Benchmark — 9× in this paper · explained in 2 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Embeddings — 8× in this paper · explained in 2 episodes
• Large Language Model — 8× in this paper
• False Positive Rate — 7× in this paper
• Robustness — 7× in this paper · explained in 5 episodes
• Spoken Dialogue Systems — 7× in this paper
• Ablation — 5× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• F1 Score — 3× in this paper · explained in 3 episodes
• Sound Event Detection — 3× in this paper
• Adaptation — 2× in this paper · explained in 1 episode
• Domain Shift — 2× in this paper · explained in 4 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Latent Representations — 2× in this paper · explained in 3 episodes
• Verifiability — 2× in this paper · explained in 2 episodes
• Word Error Rate — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• False Negative — 1× in this paper
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Hybrid System — 1× in this paper · explained in 2 episodes
• IEEE Spoken Language Technology Workshop — 1× in this paper
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Room Impulse Response — 1× in this paper
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Self-Supervised Learning (SSL) — 1× in this paper · explained in 4 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Token-and-Duration Transducer — 1× in this paper
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• True Negative — 1× in this paper
• True Positive — 1× in this paper
• Word Error Rate Reduction — 1× in this paper

Sources

• Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
• FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
• GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
• Qwen2-Audio Technical Report
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
• Moshi: a speech-text foundation model for real-time dialogue
• Resolving Intent Ambiguities by Retrieving Discriminative Clarifying Questions
• CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
• Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks
• SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription
• Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
• X-Talk: On the Underestimated Potential of Modular Speech-to-Speech Dialogue System
• ASR Error Correction using Large Language Models
• BLSTM-Based Confidence Estimation for End-to-End Speech Recognition
• MUSAN: A Music, Speech, and Noise Corpus
• SALMONN: Towards Generic Hearing Abilities for Large Language Models
• Word-level confidence estimation for RNN transducers
• Step-Audio 2 Technical Report
• Qwen3-Omni Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering