--- _id: '15814' abstract: - lang: eng text: Once a popular theme of futuristic science fiction or far-fetched technology forecasts, digital home assistants with a spoken language interface have become a ubiquitous commodity today. This success has been made possible by major advancements in signal processing and machine learning for so-called far-field speech recognition, where the commands are spoken at a distance from the sound capturing device. The challenges encountered are quite unique and different from many other use cases of automatic speech recognition. The purpose of this tutorial article is to describe, in a way amenable to the non-specialist, the key speech processing algorithms that enable reliable fully hands-free speech interaction with digital home assistants. These technologies include multi-channel acoustic echo cancellation, microphone array processing and dereverberation techniques for signal enhancement, reliable wake-up word and end-of-interaction detection, high-quality speech synthesis, as well as sophisticated statistical models for speech and language, learned from large amounts of heterogeneous training data. In all these fields, deep learning has occupied a critical role. author: - first_name: Reinhold full_name: Haeb-Umbach, Reinhold id: '242' last_name: Haeb-Umbach - first_name: Shinji full_name: Watanabe, Shinji last_name: Watanabe - first_name: Tomohiro full_name: Nakatani, Tomohiro last_name: Nakatani - first_name: Michiel full_name: Bacchiani, Michiel last_name: Bacchiani - first_name: Bjoern full_name: Hoffmeister, Bjoern last_name: Hoffmeister - first_name: Michael L. full_name: Seltzer, Michael L. last_name: Seltzer - first_name: Heiga full_name: Zen, Heiga last_name: Zen - first_name: Mehrez full_name: Souden, Mehrez last_name: Souden citation: ama: 'Haeb-Umbach R, Watanabe S, Nakatani T, et al. Speech Processing for Digital Home Assistance: Combining Signal Processing With Deep-Learning Techniques. IEEE Signal Processing Magazine. 2019;36(6):111-124. doi:10.1109/MSP.2019.2918706' apa: 'Haeb-Umbach, R., Watanabe, S., Nakatani, T., Bacchiani, M., Hoffmeister, B., Seltzer, M. L., Zen, H., & Souden, M. (2019). Speech Processing for Digital Home Assistance: Combining Signal Processing With Deep-Learning Techniques. IEEE Signal Processing Magazine, 36(6), 111–124. https://doi.org/10.1109/MSP.2019.2918706' bibtex: '@article{Haeb-Umbach_Watanabe_Nakatani_Bacchiani_Hoffmeister_Seltzer_Zen_Souden_2019, title={Speech Processing for Digital Home Assistance: Combining Signal Processing With Deep-Learning Techniques}, volume={36}, DOI={10.1109/MSP.2019.2918706}, number={6}, journal={IEEE Signal Processing Magazine}, author={Haeb-Umbach, Reinhold and Watanabe, Shinji and Nakatani, Tomohiro and Bacchiani, Michiel and Hoffmeister, Bjoern and Seltzer, Michael L. and Zen, Heiga and Souden, Mehrez}, year={2019}, pages={111–124} }' chicago: 'Haeb-Umbach, Reinhold, Shinji Watanabe, Tomohiro Nakatani, Michiel Bacchiani, Bjoern Hoffmeister, Michael L. Seltzer, Heiga Zen, and Mehrez Souden. “Speech Processing for Digital Home Assistance: Combining Signal Processing With Deep-Learning Techniques.” IEEE Signal Processing Magazine 36, no. 6 (2019): 111–24. https://doi.org/10.1109/MSP.2019.2918706.' ieee: 'R. Haeb-Umbach et al., “Speech Processing for Digital Home Assistance: Combining Signal Processing With Deep-Learning Techniques,” IEEE Signal Processing Magazine, vol. 36, no. 6, pp. 111–124, 2019, doi: 10.1109/MSP.2019.2918706.' mla: 'Haeb-Umbach, Reinhold, et al. “Speech Processing for Digital Home Assistance: Combining Signal Processing With Deep-Learning Techniques.” IEEE Signal Processing Magazine, vol. 36, no. 6, 2019, pp. 111–24, doi:10.1109/MSP.2019.2918706.' short: R. Haeb-Umbach, S. Watanabe, T. Nakatani, M. Bacchiani, B. Hoffmeister, M.L. Seltzer, H. Zen, M. Souden, IEEE Signal Processing Magazine 36 (2019) 111–124. date_created: 2020-02-06T07:26:20Z date_updated: 2023-01-09T11:47:09Z ddc: - '000' department: - _id: '54' doi: 10.1109/MSP.2019.2918706 file: - access_level: open_access content_type: application/pdf creator: huesera date_created: 2020-02-06T07:28:26Z date_updated: 2020-02-06T07:28:26Z file_id: '15815' file_name: JournalIEEESignal ProcessingMagazine_2019_Haeb-Umbach_Paper.pdf file_size: 1085002 relation: main_file file_date_updated: 2020-02-06T07:28:26Z has_accepted_license: '1' intvolume: ' 36' issue: '6' language: - iso: eng oa: '1' page: 111-124 publication: IEEE Signal Processing Magazine publication_identifier: issn: - 1558-0792 status: public title: 'Speech Processing for Digital Home Assistance: Combining Signal Processing With Deep-Learning Techniques' type: journal_article user_id: '242' volume: 36 year: '2019' ...