A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers

arXiv:2608.26194 · cs.CL, cs.AI, cs.IR · Submitted 2026-08-24 · Read on arXiv

cs.CL, cs.AI, cs.IR

Submitted: 2026-08-24

Updated: 2026-08-24

Code: https://github.com/fixie-ai/ultravox

Terminology

• RAG — 11× in this paper · explained in 3 episodes
• Hallucination — 4× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation — 4× in this paper
• Adaptation — 3× in this paper · explained in 1 episode
• Robustness — 3× in this paper · explained in 5 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Automatic Speech Recognition — 2× in this paper
• Embeddings — 2× in this paper · explained in 2 episodes
• F1 Score — 2× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Modality Gap — 2× in this paper · explained in 4 episodes
• Modularity — 2× in this paper · explained in 9 episodes
• Question Answering — 2× in this paper
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Exact Match — 1× in this paper
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Late Fusion — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Matthews Correlation Coefficient — 1× in this paper
• Mean Reciprocal Rank — 1× in this paper
• Objective Function — 1× in this paper · explained in 2 episodes
• Parameter Efficiency — 1× in this paper · explained in 3 episodes
• Reciprocal Rank Fusion — 1× in this paper
• Representation Learning — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• Gemini: A Family of Highly Capable Multimodal Models
• Qwen2-Audio Technical Report
• Speech Retrieval-Augmented Generation without Automatic Speech Recognition
• WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
• Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation
• Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension
• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

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