# ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet

Source: [ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet](<https://www.sota2.com/research/paper/68fa6bf51e209131cea3138b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:13:32.822Z

Authors: Siddhant Arora, Siddharth Dalmia, Pavel Denisov, Xuankai Chang, Yushi Ueda, Yifan Peng, Yuekai Zhang, Sujay Kumar, Karthik Ganesan, Brian Yan, Ngoc Thang Vu, Alan W Black, Shinji Watanabe

Published: 2021-11-29T17:05:49.000Z

## Abstract

As Automatic Speech Processing (ASR) systems are getting better, there is an increasing interest of using the ASR output to do downstream Natural Language Processing (NLP) tasks. However, there are few open source toolkits that can be used to generate reproducible results on different Spoken Language Understanding (SLU) benchmarks. Hence, there is a need to build an open source standard that can be used to have a faster start into SLU research. We present ESPnet-SLU, which is designed for quick development of spoken language understanding in a single framework. ESPnet-SLU is a project inside end-to-end speech processing toolkit, ESPnet, which is a widely used open-source standard for various speech processing tasks like ASR, Text to Speech (TTS) and Speech Translation (ST). We enhance the toolkit to provide implementations for various SLU benchmarks that enable researchers to seamlessly mix-and-match different ASR and NLU models. We also provide pretrained models with intensively tuned hyper-parameters that can match or even outperform the current state-of-the-art performances. The toolkit is publicly available at https://github.com/espnet/espnet.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Speech Intent Classification and Slot Filling on SLURP (test)](<https://www.sota2.com/research/sota/speech-intent-classification-and-slot-filling-on-slurp-test.md>): Speech Intent Classification and Slot Filling; SLURP (test); Intent Accuracy: 86.52.

- [Slot Filling on SLURP (test)](<https://www.sota2.com/research/sota/slot-filling-on-slurp-test.md>): Slot Filling; SLURP (test); F1 Score: 76.91.

- [Intent Classification on SLURP (test)](<https://www.sota2.com/research/sota/intent-classification-on-slurp-test.md>): Intent Classification; SLURP (test); Accuracy (IC): 86.52.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2111.14706>)

[PDF](<https://arxiv.org/pdf/2111.14706.pdf>)