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.
Cite
@article{arxiv.2203.15833,
title = {Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture},
author = {Karan Singla and Shahab Jalalvand and Yeon-Jun Kim and Ryan Price and Daniel Pressel and Srinivas Bangalore},
journal= {arXiv preprint arXiv:2203.15833},
year = {2022}
}