SAI: AI-Enabled Speech Assistant Interface for Science Gateways in HPC
Authors: 
Pouya Kousha, Arpan Jain, Ayyappa Kolli, Matthew Lieber, Mingzhe Han, Nicholas Contini, Hari Subramoni, Dhableswar K. PandaAuthors Info & Claims
Pouya Kousha, Arpan Jain, Ayyappa Kolli, Matthew Lieber, Mingzhe Han, Nicholas Contini, Hari Subramoni, Dhableswar K. PandaAuthors Info & ClaimsPages 402 - 424
Abstract
High-Performance Computing (HPC) is increasingly being used in traditional scientific domains as well as emerging areas like Deep Learning (DL). This has led to a diverse set of professionals who interact with state-of-the-art HPC systems. The deployment of Science Gateways for HPC systems like Open On-Demand has a significant positive impact on these users in migrating their workflows to HPC systems. Although computing capabilities are ubiquitously available (as on-premises or in the cloud HPC infrastructure), significant effort and expertise are required to use them effectively. This is particularly challenging for domain scientists and other users whose primary expertise lies outside of computer science. In this paper, we seek to minimize the steep learning curve and associated complexities of using state-of-the-art high-performance systems by creating SAI: an AI-Enabled Speech Assistant Interface for Science Gateways in High Performance Computing. We use state-of-the-art AI models for speech and text and fine-tune them for the HPC arena by retraining them on a new HPC dataset we create. We use ontologies and knowledge graphs to capture the complex relationships between various components of the HPC ecosystem. We finally show how one can integrate and deploy SAI in Open OnDemand and evaluate its functionality and performance on real HPC systems. To the best of our knowledge, this is the first effort aimed at designing and developing an AI-powered speech-assisted interface for science gateways in HPC.
References
[1]
TIMIT acoustic-phonetic continuous speech corpus. https://hdl.handle.net/11272.1/AB2/SWVENO
[2]
SPARQL query language (2020). https://www.w3.org/TR/sparql11-query/. Accessed 17 April 2023
[3]
Voicebot research (2020). https://tinyurl.com/4kw4bmz7
[4]
The future of conversational AI (2021). https://tinyurl.com/2dzxe2w8
[5]
Open onDemand (2022). https://osc.github.io/ood-documentation/latest/#
[6]
The impact of voice assistants (2022). https://tinyurl.com/mrx36afk
[7]
Hosseini-Asl, E., McCann, B., Wu, C.S., Yavuz, S., Socher, R.: A simple language model for task-oriented dialogue (2020). CoRR abs/2005.00796. https://arxiv.org/abs/2005.00796
[8]
Wen, T.H., Gasic, G., Mrksic, N.S., Vandyke, D., Young, S.J.: A network-based end-to-end trainable task-oriented dialogue system (2016). CoRR abs/1604.04562, http://arxiv.org/abs/1604.04562
[9]
Baevski, A., Zhou, H., Mohamed, A., Auli, M.: Wav2vec 2.0: a framework for self-supervised learning of speech representations (2020). https://arxiv.org/abs/2006.11477
[10]
Castellucci, G., Bellomaria, V., Favalli, A., Romagnoli, R.: Multi-lingual intent detection and slot filling in a joint bert-based model (2019). https://arxiv.org/abs/1907.02884
[11]
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2018). CoRR abs/1810.04805, http://arxiv.org/abs/1810.04805
[12]
Goasduff, L.: Chatbots will appeal to modern workers (2019). https://www.gartner.com/smarterwithgartner/chatbots-will-appeal-to-modern-workers
[13]
Hauptmann, A., Rudnicky, A.: A comparison of speech and typed input (1990).
[14]
Kousha P et al. Varbanescu AL, Bhatele A, Luszczek P, Marc B, et al. “Hey CAI” - conversational AI enabled user interface for HPC tools High Perform. Comput. 2022 Cham Springer International Publishing 87-108
[15]
Kousha, P., et al.: INAM: cross-stack profiling and analysis of communication in MPI-based applications. In: Association for Computing Machinery, New York, NY, USA (2021).
[16]
Kudo, T., Richardson, J.: Sentencepiece: a simple and language independent subword tokenizer and detokenizer for neural text processing (2018). arXiv preprint arXiv:1808.06226
[17]
Liao, C., Lin, P.H., Verma G., Vanderbruggen, T., Emani, M.: Hpc ontology: towards a unified ontology for managing training datasets and AI models for high-performance computing. In: 2021 IEEE/ACM Workshop on MLHPC, pp. 69–80 (2021).
[18]
National Geographic: LiDAR and Archaeology. https://education.nationalgeographic.org/resource/lidar-and-archaeology
[19]
OSU Micro-benchmarks. http://mvapich.cse.ohio-state.edu/benchmarks/
[20]
Palogiannidi, E., Gkinis, I., Mastrapas, G., Mizera, P., Stafylakis, T.: End-to-end architectures for ASR-free spoken language understanding. In: (ICASSP), pp. 7974–7978 (2020).
[21]
Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206–5210. IEEE (2015)
[22]
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library (2019)
[23]
Qin, L., Che, W., Li, Y., Wen, H., Liu, T.: A stack-propagation framework with token-level intent detection for spoken language understanding (2019). arXiv preprint arXiv:1909.02188
[24]
Rothwell, B., Sgambati, M., Evans, G. Biggs, B., Anderson, M.: Quantifying the impact of advanced web platforms on high performance computing usage, PEARC’22. ACM (2022).
[25]
Schmidt, A.: The rise of conversational interfaces and their impact on business (2019). https://tinyurl.com/45ppfz9t
[26]
Serdyuk, D., Wang, Y., Fuegen, C., Kumar, A., Liu, B., Bengio, Y.: Towards end-to-end spoken language understanding (2018). CoRR abs/1802.08395, http://arxiv.org/abs/1802.08395
[27]
Wang, C., Tang, Y., Ma, X., Wu, A., Okhonko, D., Pino, J.: Fairseq s2t: fast speech-to-text modeling with fairseq (2020). https://arxiv.org/abs/2010.05171
Recommendations
“Hey CAI” - Conversational AI Enabled User Interface for HPC Tools
High Performance ComputingAbstractHPC system users depend on profiling and analysis tools to obtain insights into the performance of their applications and tweak them. The complexity of modern HPC systems have necessitated advances in the associated HPC tools making them equally ...
Providing Accessible Software Environments Across Science Gateways and HPC
PEARC '24: Practice and Experience in Advanced Research Computing 2024: Human Powered ComputingWhile High-Performance Computing (HPC) resources are powerful for tackling complex, computationally intensive analysis and modeling problems, access to these resources varies across disciplines. Domain scientists in a variety of fields such as social ...
Comparing Open Ondemand and Jupyterhub as Interactive HPC Gateways
PEARC '23: Practice and Experience in Advanced Research Computing 2023: Computing for the Common GoodThe Minnesota Supercomputing Institute (MSI) at the University of Minnesota has adopted a goal of supporting Interactive high performance computing (HPC) as a first class service. For several years MSI has used Jupyterhub to provide a web gateway to ...
Comments
Information & Contributors
Information
Published In
May 2023
431 pages
ISBN:978-3-031-32040-8
DOI:10.1007/978-3-031-32041-5
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 21 May 2023
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Aug 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in