Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition

TL;DR

This paper introduces a novel FST-based intent recognition method to correct ASR errors in spontaneous human conversations, significantly improving intent detection despite speech disfluencies and limited labeled data.

Contribution

The paper presents a new FST framework and fuzzy search algorithm for intent recognition that enhances transcript accuracy and insight extraction in spontaneous dialogues.

Findings

Increased intent recognition by 25% over baseline

Effective handling of disfluencies and speech errors

Improved transcript rescoring using intent indexing

Abstract

In this paper, we present a method for correcting automatic speech recognition (ASR) errors using a finite state transducer (FST) intent recognition framework. Intent recognition is a powerful technique for dialog flow management in turn-oriented, human-machine dialogs. This technique can also be very useful in the context of human-human dialogs, though it serves a different purpose of key insight extraction from conversations. We argue that currently available intent recognition techniques are not applicable to human-human dialogs due to the complex structure of turn-taking and various disfluencies encountered in spontaneous conversations, exacerbated by speech recognition errors and scarcity of domain-specific labeled data. Without efficient key insight extraction techniques, raw human-human dialog transcripts remain significantly unexploited. Our contribution consists of a novel FST for intent indexing and an algorithm for fuzzy intent search over the lattice - a compact graph encoding of ASR's hypotheses. We also develop a pruning strategy to constrain the fuzziness of the FST index search. Extracted intents represent linguistic domain knowledge and help us improve (rescore) the original transcript. We compare our method with a baseline, which uses only the most likely transcript hypothesis (best path), and find an increase in the total number of recognized intents by 25%.