ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet
This work addresses the need for a standardized open-source toolkit to accelerate SLU research, making it easier for researchers to develop and benchmark models, though it is incremental as it builds on the existing ESPnet framework.
The authors tackled the lack of open-source toolkits for reproducible Spoken Language Understanding (SLU) research by developing ESPnet-SLU, an integrated framework that provides implementations for various SLU benchmarks and pretrained models, achieving state-of-the-art or better performance.
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.