Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture

TL;DR

This paper introduces a lightweight Seq-2-Seq model to improve the accuracy of capturing person names from spoken input in human-machine interactions, outperforming traditional rule-based methods.

Contribution

The paper presents a novel Seq-2-Seq approach for extracting names from speech, inspired by spell correction and text normalization, with better performance than existing rule-based systems.

Findings

Outperforms rule-based baseline in name capture accuracy

Effective in handling varied user input for name spelling

Lightweight model suitable for real-time applications

Abstract

Person name capture from human speech is a difficult task in human-machine conversations. In this paper, we propose a novel approach to capture the person names from the caller utterances in response to the prompt "say and spell your first/last name". Inspired from work on spell correction, disfluency removal and text normalization, we propose a lightweight Seq-2-Seq system which generates a name spell from a varying user input. Our proposed method outperforms the strong baseline which is based on LM-driven rule-based approach.