"I've Heard of You!": Generate Spoken Named Entity Recognition Data for Unseen Entities
Preprint
Abstract
Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and then use a text-to-speech (TTS) system to generate the speech. Furthermore, we introduce a noise metric to filter out noisy data. To evaluate our approach, we release a novel Spoken NER benchmark along with a corresponding NED containing 8,853 entities. Experiment results show that our method achieves state-of-the-art (SOTA) performance in the in-domain, zero-shot domain adaptation, and fully zero-shot settings. Our data will be available at https://github.com/DeepLearnXMU/HeardU.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- MSNER: A Multilingual Speech Dataset for Named Entity Recognition2024
- SLUE: New Benchmark Tasks For Spoken Language Understanding Evaluation on Natural Speech2022
- End-to-End Named Entity Recognition from English Speech2020
- Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search2017
- Incorporating speech recognition confidence into discriminative named entity recognition of speech data2006