TY - GEN
T1 - ESPNET-SLU
T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
AU - Arora, Siddhant
AU - Dalmia, Siddharth
AU - Denisov, Pavel
AU - Chang, Xuankai
AU - Ueda, Yushi
AU - Peng, Yifan
AU - Zhang, Yuekai
AU - Kumar, Sujay
AU - Ganesan, Karthik
AU - Yan, Brian
AU - Vu, Ngoc Thang
AU - Black, Alan W.
AU - Watanabe, Shinji
N1 - Funding Information:
This work used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by NSF grant number ACI-1548562. Specifically, it used the Bridges system, supported by NSF grant ACI-1445606, at the PSC.
Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - open-source
KW - spoken language understanding
UR - http://www.scopus.com/inward/record.url?scp=85130801848&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85130801848&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9747674
DO - 10.1109/ICASSP43922.2022.9747674
M3 - Conference contribution
AN - SCOPUS:85130801848
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 7167
EP - 7171
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 23 May 2022 through 27 May 2022
ER -