# "I've Heard of You!": Generate Spoken Named Entity Recognition Data for Unseen Entities

arXiv: https://arxiv.org/abs/2412.19102 · HTML: https://mlsanity.com/paper/2412.19102/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 27 references that are in the map.
- First posted on arXiv 26 Dec 2024.

## Builds on (most cited first, 3 of 3)

- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [End-to-end Named Entity Recognition from English Speech](https://mlsanity.com/paper/2005.11184/) (2020)
- [MSNER: A Multilingual Speech Dataset for Named Entity Recognition](https://mlsanity.com/paper/2405.11519/) (2024)

## Built on by (most cited first, 2 of 2)

- [SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings](https://mlsanity.com/paper/2509.04473/) (2025)
- [τ-Elicitation: Benchmarking multi-turn entity extraction in voice agents](https://mlsanity.com/paper/2609.13602/) (2026)

## Abstract (arXiv)

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.