Towards automatic inspection of nuclear fuel elements in spent fuel pools: Audio analysis
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this article, we propose and explore a novel step in the digitization of the mapping of the spent fuel pool of nuclear power plants, in which the audio signal from the operator’s microphone is used to obtain the identification codes of those components that are in each of the cells of the pool. In this way, we have not only an acquisition system but also a verification system that can be used in combination with the outcome of the analysis of the video signal. We developed an algorithm that uses at its core one of the latest models of multilingual Automatic Speech Recognition to transcribe audio signal, and with a post-processing of the timed transcriptions we build the identification code of fuel heads and other components. Results show a very high accuracy in audios from real recording of Spanish nuclear facilities, and the methodology proposed is easily extensible to other nuclear facilities in the world.
Abstract
In this article, we propose and explore a novel step in the digitization of the mapping of the spent fuel pool of nuclear power plants, in which the audio signal from the operator’s microphone is used to obtain the identification codes of those components that are in each of the cells of the pool. In this way, we have not only an acquisition system but also a verification system that can be used in combination with the outcome of the analysis of the video signal. We developed an algorithm that uses at its core one of the latest models of multilingual Automatic Speech Recognition to transcribe audio signal, and with a post-processing of the timed transcriptions we build the identification code of fuel heads and other components. Results show a very high accuracy in audios from real recording of Spanish nuclear facilities, and the methodology proposed is easily extensible to other nuclear facilities in the world.
참고문헌 (23)
- IAEA, "Classification of Radioactive Waste", ~ (2009)
- Data Requirements and Maintenance of Records for Spent Fuel Management:A Review, "IAEA", ~ (2006)
- CSN, "GS 01-07 Revision ´ 2 - Informacion ´ a Remitir al CSN Por Los Titulares Sobre La Explotacion ´ de Las Centrales Nucleares", ~ (2003)
- N. Shoman, "Inspecta 1.0: implementation challenges for on-device speech and vision tasks", Proc. F the INMM, 2023, ~
- C. Tang, "Deep learning in nuclear industry : a survey", Big Data Mining and Analytics, 5(2), pp.140~160 (2022)
- G. Hinton, "Deep neural networks for acoustic modeling in speech recognition : the shared views of four research groups", IEEE Signal Process. Mag, 29, pp.82~97 (2012)[DOI]
- "Wav2Letter: an End-To-End Convnet-Based Speech Recognition System" (2016)[URL]
- R. Prabhavalkar, "A comparison of sequence-to-sequence models for speech recognition", Interspeech 2017, ISCA, ISCA (2017)
- "Achieving Human Parity in Conversational Speech Recognition" (2016)[URL]
- A. Vaswani, "Attention is all you need", Adv. Neural Inf. Process. Syst, 30 (2017)
- J. Devlin, "BERT: pre-training of deep bidirectional Transformers for language understanding", Proceedings of NAACLHLT, pp.4171~4186 (2019)
- A. Conneau, "Unsupervised cross-lingual representation learning at scale", Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020), Association for Computational Linguistics
- A. Baevski, "wav2vec 2. 0 : a framework for selfsupervised learning of speech representations", Adv. Neural Inf. Process. Syst, 33, pp.12449~12460 (2020)
- "Fine-Tuned XLSR-53 Large Model for Speech Recognition in English" (2021)[URL]
- "Facebook’s Wav2Vec2" (2020)[URL]
- A. Radford, "Robust speech recognition via large-scale weak supervision", International Conference on Machine Learning, PMLR, pp.28492~28518 (2023)
- "Google, Gemini: A Family of Highly Capable Multimodal Models" (2024)[URL]
- "Whisper-Large-v3" (2024)[URL]
- "WhisperX: Time-Accurate Speech Transcription of Long-form Audio" (2023)[URL]
- T. Giorgino, "Computing and visualizing dynamic time warping alignments in R: the dtw package", J. Stat. Software, 31 (2009)[DOI]
- "Whisper-timestamped: multilingual automatic speech recognition with word-level timestamps and confidence, GitHub Repository" (2023)[URL]
- D. Liu, "Low-latency sequence-to-sequence speech recognition and translation by partial hypothesis selection", Interspeech 2020, pp.3620~3624 (2020)
- D. Macha´ˇcek, "Turning whisper into real-time transcription system", Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations, pp.17~24 (2023)