Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations
The paper proposes an ontology memory-augmented ASR correction framework for long text-speech interleaved conversations.
The paper introduces a novel approach to ASR correction that uses a dynamically updatable ontology memory.
Before reading this…
Applications
- →improving conversational AI systems
- →enhancing speech recognition accuracy
To understand this paper, make sure you know these concepts first:
- automatic speech recognitionfind papers →
- conversational AIfind papers →
Abstract
More Like ThisAutomatic speech recognition (ASR) correction has traditionally focused on isolated utterances or short local contexts. However, as text and speech become increasingly interleaved in long interactions, ASR correction requires conversation-level contextual evidence. Existing ASR correction methods often rely on the current hypothesis or concatenate raw dialogue history. In such contexts, sparse correction evidence can be difficult to locate amid redundancy and noise. Addressing these challenges, we propose an ontology memory-augmented ASR correction framework for long text-speech interleaved conversations. The framework organizes preceding interaction history into a dynamically updatable ontology memory, where entities, terminology, surface variants, potential ASR confusions, and semantic relations are stored as retrievable nodes for context-grounded correction. To evaluate this setting, we construct RAMC-Corr, a dataset derived from MAGIC-RAMC for long-range ASR correction with grounded context. Experiments on RAMC-Corr show that our method improves over direct correction in 9 out of 10 paired backbone-setting combinations and encourages more selective and evidence-grounded corrections for context-dependent ASR errors.