Detecting and Correcting Speech Repairs

TL;DR

This paper introduces a novel algorithm for detecting and correcting speech repairs in spoken dialog systems, which dynamically builds repair patterns and achieves high accuracy without relying on prosody or parsing.

Contribution

The method constructs repair patterns on the fly using word matches and replacements, improving repair detection and correction in spoken dialog systems.

Findings

80% repair detection and correction rate

No reliance on prosodic cues or parsing

Effective in real-time spoken dialog scenarios

Abstract

Interactive spoken dialog provides many new challenges for spoken language systems. One of the most critical is the prevalence of speech repairs. This paper presents an algorithm that detects and corrects speech repairs based on finding the repair pattern. The repair pattern is built by finding word matches and word replacements, and identifying fragments and editing terms. Rather than using a set of prebuilt templates, we build the pattern on the fly. In a fair test, our method, when combined with a statistical model to filter possible repairs, was successful at detecting and correcting 80\% of the repairs, without using prosodic information or a parser.