Review of Research on Keyword Spotting in Low-Resource Environments

doi:10.19678/j.issn.1000-3428.0068739

Abstract

Abstract:

Keyword Spotting (KWS) is a crucial technology for enabling human-computer interaction and has long been a focal point in speech technology research. As deep learning technology has advanced, research methodologies have transitioned from traditional Large-Vocabulary Continuous Speech Recognition (LVCSR) techniques to neural network-based approaches. However, challenges remain in achieving efficient KWS on small devices and training models with limited sample data, particularly in the design of low-resource KWS systems. This review begins by defining the concept of low-resource KWS, distinguishing it from general speech recognition and related terminology. It then introduces classic KWS models and their applicable scenarios while detailing the current global state of research on low-resource KWS. Next, mainstream technologies and optimization strategies for acoustic feature extraction and modeling are explained, with a focus on the structural components of KWS systems. An analysis of model lightweight methods is then conducted, where their advantages and disadvantages are compared. Common solutions for low-resource KWS, such as few- and zero-shot learning as well as transfer learning, are summarized, and common KWS datasets and evaluation metrics are introduced. Finally, future research directions for low-resource KWS technology are discussed.

Key words: Keyword Spotting(KWS), low-resource, model quantization, few-shot learning, human-computer interaction

摘要：

语音唤醒作为实现人机交互的关键技术, 一直是语音领域的研究热点。随着深度学习技术的发展, 其研究方法的重心已从传统的大词汇连续语音识别(LVCSR)技术逐渐转向基于神经网络的技术, 然而如何在小型设备上实现高效唤醒并利用有限的样本数据进行模型训练仍是低资源语音唤醒系统设计面临的挑战。首先, 定义了语音唤醒中的低资源概念, 区分了语音唤醒和语音识别以及相关术语, 介绍了经典的语音唤醒模型及其适配场景, 阐述了低资源语音唤醒的国内外研究现状。其次, 从语音唤醒系统的结构组成的角度分别说明了声学特征提取与声学模型的主流技术和优化策略。然后, 对语音唤醒模型的轻量化方法展开分析并对其优缺点进行比较, 总结了数据低资源语音唤醒中常见的小样本学习、零样本学习、迁移学习等解决方法, 并介绍了常见语音唤醒数据集和评价指标。最后, 探讨并展望了低资源语音唤醒技术未来的研究方向。

关键词: 语音唤醒, 低资源, 模型量化, 小样本学习, 人机交互

WANG Yuehao, ZHOU Ruohua. Review of Research on Keyword Spotting in Low-Resource Environments[J]. Computer Engineering, 2025, 51(2): 35-53.

王月昊, 周若华. 低资源环境下的语音唤醒研究综述[J]. 计算机工程, 2025, 51(2): 35-53.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0068739

https://www.ecice06.com/EN/Y2025/V51/I2/35

Figures/Tables 16

Fig.1 Principles of speech recognition and KWS

Fig.2 Implementation process of LVCSR

Fig.3 Process of HMM-based Keyword/filler KWS

Fig.4 Process of neural network-based KWS technology

Fig.5 Comparison of process of common feature extraction

Fig.6 Comparison of differences between 2D convolution and time convolution

Fig.7 Development history of KWS models based on deep learning

Fig.8 Schematic diagram of few-shot learning

Fig.9 Schematic diagram of transfer learning principle

Fig.10 Schematic diagram of two systems for KWS at 90% accuracy

References 115

1	杨世强, 梁丁宏, 傅卫平. 智能机器人语音远程控制系统的设计. 计算机工程与应用, 2009, 45 (25): 71-73, 88. doi: 10.3778/j.issn.1002-8331.2009.25.022
	YANG S Q , LIANG D H , FU W P . Design for speech remote control system of intelligent robot. Computer Engineering and Applications, 2009, 45 (25): 71-73, 88. doi: 10.3778/j.issn.1002-8331.2009.25.022
2	DABBABI K , MARS A . Spoken utterance classification task of Arabic numerals and selected isolated words. Arabian Journal for Science and Engineering, 2022, 47 (8): 10731- 10750. doi: 10.1007/s13369-022-06649-0
3	杨鹏, 谢磊, 张艳宁. 低资源语言的无监督语音关键词检测技术综述. 中国图象图形学报, 2015, 20 (2): 211- 218.
	YANG P , XIE L , ZHANG Y N . Survey on unsupervised spoken term detection for low-resource languages. Journal of Image and Graphics, 2015, 20 (2): 211- 218.
4	TSAKALIDIS S, HSIAO R, KARAKOS D, et al. The 2013 BBN Vietnamese telephone speech keyword spotting system[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2014: 7829-7833.
5	YU D , DENG L . Automatic speech recognition. Berlin, Germany: Springer, 2016.
6	KËPUSKA V Z , KLEIN T B . A novel wake-up-word speech recognition system, wake-up-word recognition task, technology and evaluation. Nonlinear Analysis: Theory, Methods [WT《Times New Roman》] & Applications, 2009, 71 (12): 2772- 2789. doi: 10.1016/j.na.2009.06.089
7	XIE G K , HAO S , ZHANG P P , et al. Research and implementation of intelligent home pension system based on speech and semantic recognition. Advances in Multimedia, 2022, (1): 6141295.
8	WEINTRAUB M. Keyword-spotting using SRI's DECIPHER large-vocabulary speech-recognition system[C]//Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Washington D.C., USA: IEEE Press, 1993: 463-466.
9	DAHL G E, SAINATH T N, HINTON G E. Improving deep neural networks for LVCSR using rectified linear units and dropout[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Washington D.C., USA: IEEE Press, 2013: 8609-8613.
10	DO C T, STYLIANOU Y. Weighting time-frequency representation of speech using auditory saliency for automatic speech recognition[C]//Proceedings of the Interspeech 2018. [S. l. ]: ISCA, 2018: 1591-1595.
11	WEINTRAUB M. LVCSR log-likelihood ratio scoring for keyword spotting[C]//Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. Washington D.C., USA: IEEE Press, 1995: 297-300.
12	AMODEI D, ANUBHAI R, BATTENBERG E, et al. Deep speech 2: end-to-end speech recognition in English and mandarin[EB/OL]. [2023-10-17]. http://arxiv.org/abs/1512.02595.
13	MILLER D R H, KLEBER M, KAO C, et al. Rapid and accurate spoken term detection[EB/OL]. [2023-10-17]. https://www.isca-archive.org/interspeech_2007/miller07_interspeech.pdf.
14	WANG Y Y, LONG Y H. Keyword spotting based on CTC and RNN for mandarin Chinese speech[C]//Proceedings of the 11th International Symposium on Chinese Spoken Language Processing (ISCSLP). Washington D.C., USA: IEEE Press, 2018: 374-378.
15	SZOKE I, SCHWARZ P, MATEJKA P, et al. Comparison of keyword spotting approaches for informal continuous speech[C]//Proceedings of the Interspeech 2005. [S. l. ]: ISCA, 2005: 633-663.
16	CHEN G G, YILMAZ O, TRMAL J, et al. Using proxies for OOV keywords in the keyword search task[C]//Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding. Washington D. C., USA: IEEE Press, 2013: 416-421.
17	PARLAK S, SARACLAR M. Spoken term detection for Turkish broadcast news[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Washington D. C., USA: IEEE Press, 2008: 5244-5247.
18	WILPON J G , RABINER L R , LEE C H , et al. Automatic recognition of keywords in unconstrained speech using hidden Markov models. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1990, 38 (11): 1870- 1878. doi: 10.1109/29.103088
19	GAUVAIN J L , LEE C H . Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio Processing, 1994, 2 (2): 291- 298. doi: 10.1109/89.279278
20	DE GREVE Z. Application in automatic speech recognition: keyword spotting based on online garbage modeling[EB/OL]. [2023-10-17]. https://scholar.google.com/scholar?q=Z.+De+Greve%2C+Application+in+Automatic+Speech+Recognition%3A+Keyword+Spotting+Based+On+On-Line+Garbage+Modeling%2C+IDIAP+Research+Institute%2C+2006.
21	YUE X H , LIN J R , GUTIERREZ F R , et al. Self-supervised learning with segmental masking for speech representation. IEEE Journal of Selected Topics in Signal Processing, 2022, 16 (6): 1367- 1379. doi: 10.1109/JSTSP.2022.3191845
22	YAPANEL V. Garbage modeling techniques for a Turkish keyword spotting system[EB/OL]. [2023-10-17]. https://www.semanticscholar.org/paper/GARBAGE-MODELING-TECHNIQUES-FOR-A-TURKISH-KEYWORD-Yapanel/8933238d3398f2967f19d0ce68ea071bb1ee1120.
23	OUALI Y, HUDELOT C, TAMI M. An overview of deep semi-supervised learning[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2006.05278v2.
24	SEO D , OH H S , JUNG Y . Wav2KWS: transfer learning from speech representations for keyword spotting. IEEE Access, 2021, 9, 80682- 80691. doi: 10.1109/ACCESS.2021.3078715
25	JIA Y, CAI Z, MA M, et al. Training wake word detection with synthesized speech data on confusion words[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2011.01460.
26	LIM H , KIM Y , KIM H . Cross-informed domain adversarial training for noise-robust wake-up word detection. IEEE Signal Processing Letters, 2020, 27, 1769- 1773. doi: 10.1109/LSP.2020.3026947
27	ZHANG Y D, GLASS J R. Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams[C]//Proceedings of the IEEE Workshop on Automatic Speech Recognition [WT《Times New Roman》] & Understanding. Washington D.C., USA: IEEE Press, 2009: 398-403.
28	AO C W, LEE H. Query-by-example spoken term detection using attention-based multi-hop networks[EB/OL]. [2023-10-17]. https://arxiv.org/abs/1709.00354.
29	WILPON J G, MILLER L G, MODI P. Improvements and applications for key word recognition using hidden Markov modeling techniques[C]//Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. Washington D.C., USA: IEEE Press, 1991: 309-312.
30	ALDARMAKI H , ULLAH A , RAM S , et al. Unsupervised automatic speech recognition: a review. Speech Communication, 2022, 139, 76- 91. doi: 10.1016/j.specom.2022.02.005
31	ROSENBERG A, AUDHKHASI K, SETHY A, et al. End-to-end speech recognition and keyword search on low-resource languages[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2017: 5280-5284.
32	杨润延, 程高峰, 刘建. 基于端到端语音识别的关键词检索技术研究. 计算机科学, 2022, 49 (1): 53- 58. doi: 10.11896/jsjkx.210800269
	YANG R Y , CHENG G F , LIU J . Study on keyword search framework based on end-to-end automatic speech recognition. Computer Science, 2022, 49 (1): 53- 58. doi: 10.11896/jsjkx.210800269
33	马晗, 唐柔冰, 张义, 等. 语音识别研究综述. 计算机系统应用, 2022, 31 (1): 1- 10.
	MA H , TANG R B , ZHANG Y , et al. Survey on speech recognition. Computer Systems [WT《Times New Roman》] & Applications, 2022, 31 (1): 1- 10.
34	SEKI H, YAMAMOTO K, NAKAGAWA S. A deep neural network integrated with filterbank learning for speech recognition[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2017: 5480-5484.
35	MISHRA J, MAHADEVA PRASANNA S R. Challenges in spoken language diarization in code-switched scenario[C]//Proceedings of the National Conference on Communications (NCC). Washington D.C., USA: IEEE Press, 2023: 1-6.
36	GAO Y, STEIN N D, KAO C C, et al. On front-end gain invariant modeling for wake word spotting[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2010.06676.
37	RIVIELLO A, DAVID J P. Binary speech features for keyword spotting tasks[C]//Proceedings of the Interspeech 2019. [S. l. ]: ISCA, 2019: 3460-3464.
38	LEI L , YUAN G S , ZHANG T L , et al. Low-power feature-attention Chinese keyword spotting framework with distillation learning. ACM Transactions on Asian and Low-Resource Language Information Processing, 2023, 22 (2): 1- 14.
39	IBRAHIM E A, HUISKEN J, FATEMI H, et al. Keyword spotting using time-domain features in a temporal convolutional network[C]//Proceedings of the 22nd Euromicro Conference on Digital System Design (DSD). Washington D.C., USA: IEEE Press, 2019: 313-319.
40	CHOI S, SEO S, SHIN B, et al. Temporal convolution for real-time keyword spotting on mobile devices[C]//Proceedings of the Interspeech 2019. [S. l. ]: ISCA, 2019: 3372-3337.
41	LIM H, KIM Y, YEOM K, et al. Lightweight feature encoder for wake-up word detection based on self-supervised speech representation[C]//Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2023: 1-5.
42	LEE S , KANG T , BELL J , et al. An eight-element frequency-selective acoustic beamformer and bitstream feature extractor. IEEE Journal of Solid-State Circuits, 2022, 57 (6): 1812- 1823. doi: 10.1109/JSSC.2021.3103727
43	CHEN G G, PARADA C, HEIGOLD G. Small-footprint keyword spotting using deep neural networks[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2014: 4087-4091.
44	CHEN H T, WANG Y H, XU C J, et al. AdderNet: do we really need multiplications in deep learning? [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 1465-1474.
45	LECUN Y, BENGIO Y, LABORATORIES T B. Convolutional networks for images, speech, and time-series[EB/OL]. [2023-10-17]. https://www.researchgate.net/publication/216792820_Convolutional_Networks_for_Images_Speech_and_Time-Series.
46	HIGUCHI T, GHASEMZADEH M, YOU K, et al. Stacked 1D convolutional networks for end-to-end small footprint voice trigger detection[C]//Proceedings of the Interspeech 2020. Washington D.C., USA: IEEE Press, 2020: 1-7.
47	GRUENSTEIN A, ALVAREZ R, THORNTON C, et al. A cascade architecture for keyword spotting on mobile devices[EB/OL]. [2023-10-17]. http://arxiv.org/abs/1712.03603.
48	SIRI H. An on-device DNN-powered voice trigger for apple's personal assistant-apple[EB/OL]. [2023-10-17]. https://machinelearning.apple.com/research/hey-siri.
49	CHEN J J , WU Z , WANG Z , et al. Practical accuracy estimation for efficient deep neural network testing. ACM Transactions on Software Engineering and Methodology, 2020, 29 (4): 1- 35.
50	WANG Y M, LV H, POVEY D, et al. Wake word detection with streaming Transformers[2023-10-17]. http://arxiv.org/abs/2102.04488.
51	TANG R, LIN J. Deep residual learning for small-footprint keyword spotting[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2018: 5484-5488.
52	LI X M, WEI X D, QIN X W. Small-footprint keyword spotting with multi-scale temporal convolution[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2010.09960.
53	MAJUMDAR S, GINSBURG B. MatchboxNet: 1D time-channel separable convolutional neural network architecture for speech commands recognition[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2004.08531.
54	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2016: 770-778.
55	虞秋辰, 周若华, 袁庆升. 基于Ghost-SE-Res2Net的多模型融合语音唤醒词检测方法. 计算机工程, 2024, 50 (3): 52- 59. doi: 10.19678/j.issn.1000-3428.0067197
	YU Q C , ZHOU R H , YUAN Q S . Multi-model fusion speech wake-up word detection method based on Ghost-SE-Res2Net. Computer Engineering, 2024, 50 (3): 52- 59. doi: 10.19678/j.issn.1000-3428.0067197
56	PAN J, SHAPIRO J, WOHLWEND J, et al. ASAPP-ASR: multistream CNN and self-attentive SRU for SOTA speech recognition[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2005.10469.
57	SAINATH T N, PARADA C. Convolutional neural networks for small-footprint keyword spotting[C]//Proceedings of the Interspeech 2015. [S. l. ]: ISCA, 2015: 1478-1482.
58	LIMONOVA E, ALFONSO D, NIKOLAEV D, et al. ResNet-like architecture with low hardware requirements[C]//Proceedings of the 25th International Conference on Pattern Recognition (ICPR). Washington D.C., USA: IEEE Press, 2021: 6204-6211.
59	ZHANG B, LI W F, LI Q Y, et al. AutoKWS: keyword spotting with differentiable architecture search[EB/OL]. [2023-10-17]. http://arxiv.org/abs/2009.03658.
60	XU M L, ZHANG X L. Depthwise separable convolutional ResNet with squeeze-and-excitation blocks for small-footprint keyword spotting[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2004.12200.
61	PETER D, ROTH W, PERNKOPF F. End-to-end keyword spotting using neural architecture search and quantization[C]//Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2022: 3423-3427.
62	MITTERMAIER S, KVRZINGER L, WASCHNECK B, et al. Small-footprint keyword spotting on raw audio data with Sinc-convolutions[C]//Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2020: 7454-7458.
63	OLALEYE K , ONEAŢǍ D , KAMPER H . Keyword localisation in untranscribed speech using visually grounded speech models. IEEE Journal of Selected Topics in Signal Processing, 2022, 16 (6): 1454- 1466. doi: 10.1109/JSTSP.2022.3180220
64	WU J B , YILMAZ E , ZHANG M L , et al. Deep spiking neural networks for large vocabulary automatic speech recognition. Frontiers in Neuroscience, 2020, 14, 199. doi: 10.3389/fnins.2020.00199
65	CÁMBARA G , LÓPEZ F , BONET D , et al. TASE: task-aware speech enhancement for wake-up word detection in voice assistants. Applied Sciences, 2022, 12 (4): 1974. doi: 10.3390/app12041974
66	HINTON G, VINYALS O, DEAN J. Distilling the knowledge in a neural network[EB/OL]. [2023-10-17]. https://arxiv.org/abs/1503.02531.
67	DENG X , ZHANG Z . Sparsity-control ternary weight networks. Neural Networks, 2022, 145, 221- 232. doi: 10.1016/j.neunet.2021.10.018
68	AVILA A R, BIBI K, YANG R H, et al. Low-bit shift network for end-to-end spoken language understanding[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2207.07497.
69	王澳回, 张珑, 宋文宇, 等. 端到端流式语音识别研究综述. 计算机工程与应用, 2023, 59 (2): 22- 33.
	WANG A H , ZHANG L , SONG W Y , et al. Review of end-to-end streaming speech recognition. Computer Engineering and Applications, 2023, 59 (2): 22- 33.
70	BAGCHI D, HARTMANN W. Learning from the best: a teacher-student multilingual framework for low-resource languages[C]//Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2019: 6051-6055.
71	TAKASHIMA R, LI S, KAWAI H. An investigation of a knowledge distillation method for CTC acoustic models[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2018: 5809-5813.
72	KURATA G, AUDHKHASI K. Improved knowledge distillation from bi-directional to uni-directional LSTM CTC for end-to-end speech recognition[C]//Proceedings of the IEEE Spoken Language Technology Workshop (SLT). Washington D.C., USA: IEEE Press, 2018: 411-417.
73	DIGHE D, MARCHI E, VISHNUBHOTLA S, et al. Knowledge transfer for efficient on-device false trigger mitigation[C]//Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2021: 6838-6842.
74	GHOSH A, FUHS M, BAGCHI D, et al. Low-resource low-footprint wake-word detection using knowledge distillation[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2207.03331.
75	HOU J Y, SHI Y Y, OSTENDORF M, et al. Mining effective negative training samples for keyword spotting[C]//Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2020: 7444-7448.
76	PETER D, ROTH W, PERNKOPF F. Resource-efficient DNNs for keyword spotting using neural architecture search and quantization[C]//Proceedings of the 25th International Conference on Pattern Recognition (ICPR). Washington D.C., USA: IEEE Press, 2021: 9273-9279.
77	BLUCHE T, PRIMET M, GISSELBRECHT T. Small-footprint open-vocabulary keyword spotting with quantized LSTM networks[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2002.10851.
78	LI Y H, GONG R H, TAN X, et al. BRECQ: pushing the limit of post-training quantization by block reconstruction[EB/OL]. [2023-10-17]. http://arxiv.org/abs/2102.05426.
79	TUCKER G, WU M H, SUN M, et al. Model compression applied to small-footprint keyword spotting[C]//Proceedings of the Interspeech 2016. [S. l. ]: ISCA, 2016: 1878-1882.
80	WANG Z W, WU Z Y, LU J W, et al. BiDet: an efficient binarized object detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 2046-2055.
81	SINGH A , KABRA R , KUMAR R , et al. On-device system for device directed speech detection for improving human computer interaction. IEEE Access, 2021, 9, 131758- 131766. doi: 10.1109/ACCESS.2021.3114371
82	SIMONS T , LEE D J . A review of binarized neural networks. Electronics, 2019, 8 (6): 661. doi: 10.3390/electronics8060661
83	WANG P S , HE X Y , CHENG J . Toward accurate binarized neural networks with sparsity for mobile application. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35 (1): 272- 284.
84	ZHANG B C, WANG R Q, WANG X D, et al. Modulated convolutional networks[EB/OL]. [2023-10-17]. https://paperswithcode.com/paper/modulated-convolutional-networks.
85	YE J , WANG J , ZHANG S . Distillation-guided residual learning for binary convolutional neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33 (12): 7765- 7777.
86	SHAN W W , YANG M H , WANG T , et al. A 510 nW wake-up keyword-spotting chip using serial-FFT-based MFCC and binarized depthwise separable CNN in 28 nm CMOS. IEEE Journal of Solid-State Circuits, 2021, 56 (1): 151- 164.
87	LENG C, DOU Z S, LI H, et al. Extremely low bit neural network: squeeze the last bit out with ADMM[EB/OL]. [2023-10-17]. https://arxiv.org/abs/1707.09870.
88	LIU B, CAI H, WANG Z, et al. A 22 nm, 10.8 μW/15.1 μW dual computing modes high power-performance-area efficiency domained background noise aware keyword-spotting processor[J]. IEEE Transactions on Circuits and Systems I, 2020, 67(12): 4733-4746.
89	PARNAMI A, LEE M. Learning from few examples: a summary of approaches to few-shot learning[EB/OL]. [2023-10-17]. http://arxiv.org/abs/2203.04291.
90	LEE D, KIM M, MUN S H, et al. Fully unsupervised training of few-shot keyword spotting[C]//Proceedings of the IEEE Spoken Language Technology Workshop (SLT). Washington D.C., USA: IEEE Press, 2023: 266-272.
91	陈良臣, 傅德印. 面向小样本数据的机器学习方法研究综述. 计算机工程, 2022, 48 (11): 1- 13. doi: 10.19678/j.issn.1000-3428.0065347
	CHEN L C , FU D Y . Survey on machine learning methods for small sample data. Computer Engineering, 2022, 48 (11): 1- 13. doi: 10.19678/j.issn.1000-3428.0065347
92	FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]// Proceedings of the 34th International Conference on Machine Learning. New York, USA: ACM Press, 2017: 1126-1135.
93	PARNAMI A, LEE M. Few-shot keyword spotting with prototypical networks[C]//Proceedings of the 2022 7th International Conference on Machine Learning Technologies (ICMLT). New York, USA: ACM Press, 2022: 277-283.
94	SNELL J, SWERSKY K, ZEMEL R S. Prototypical networks for few-shot learning[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2017: 4080-4090.
95	LIU X, LIU P, ZONG L. Transductive prototypical network for few-shot classification[EB/OL]. [2023-10-17]. https://www.researchgate.net/publication/347627805_Transductive_Prototypical_Network_For_Few-Shot_Classification.
96	LEE Y H, CHO N. PhonMatchNet: phoneme-guided zero-shot keyword spotting for user-defined keywords[EB/OL]. [2023-10-17]. https://arxiv.org/abs/2308.16511.
97	TIAN Y, YAO H T, CAI M, et al. Improving RNN transducer modeling for small-footprint keyword spotting[C]//Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2021: 5624-5628.
98	THOMAS S, GANAPATHY S, HERMANSKY H. Multilingual MLP features for low-resource LVCSR systems[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2012: 4269-4272.
99	CHOI S, SEO S, SHIN B, et al. Temporal convolution for real-time keyword spotting on mobile devices[EB/OL]. [2023-10-17]. https://arxiv.org/abs/1904.03814.
100	PATTANAYAK B , ROUT J K , PRADHAN G . Adaptive spectral smoothening for development of robust keyword spotting system. IET Signal Processing, 2019, 13 (5): 544- 550.
101	GOODFELLOW I J, SHLENS J, SZEGEDY C. Explaining and harnessing adversarial examples[EB/OL]. [2023-10-17]. https://arxiv.org/abs/1412.6572.
102	WANG X, SUN S N, SHAN C H, et al. Adversarial examples for improving end-to-end attention-based small-footprint keyword spotting[C]//Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2019: 6366-6370.
103	LÓPEZ-ESPEJO I , TAN Z H , HANSEN J H L , et al. Deep spoken keyword spotting: an overview. IEEE Access, 2022, 10, 4169- 4199.
104	WARDEN P. Launching the speech commands dataset[EB/OL]. [2023-10-17]. https://ai.googleblog.com/2017/08/launching-speech-commands-dataset.html.
105	COUCKE A, CHLIEH M, GISSELBRECHT T, et al. Efficient keyword spotting using dilated convolutions and gating[C]//Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2019: 6351-6355.
106	PARDEDE H F , ADHI P , ZILVAN V , et al. Deep convolutional neural networks-based features for Indonesian large vocabulary speech recognition. IAES International Journal of Artificial Intelligence, 2023, 12 (2): 610.
107	ZHAO Z Y , ZHANG W Q . End-to-end keyword search system based on attention mechanism and energy scorer for low resource languages. Neural Networks, 2021, 139, 326- 334.
108	MISHCHENKO Y, GOREN Y, SUN M, et al. Low-bit quantization and quantization-aware training for small-footprint keyword spotting[C]//Proceedings of the 18th IEEE International Conference on Machine Learning and Applications (ICMLA). Washington D.C., USA: IEEE Press, 2019: 706-711.
109	KIM B, LEE M G, LEE J, et al. Query-by-example on-device keyword spotting[EB/OL]. [2023-10-17]. http://arxiv.org/abs/1910.05171.
110	HUANG Y T, HUGHES T, SHABESTARY T Z, et al. Supervised noise reduction for multichannel keyword spotting[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2018: 5474-5478.
111	WARDEN P. Speech commands: a dataset for limited-vocabulary speech recognition[EB/OL]. [2023-10-17]. http://arxiv.org/abs/1804.03209.
112	COUCKE A, CHLIEH M, GISSELBRECHT T, et al. Efficient keyword spotting using dilated convolutions and gating[EB/OL]. [2023-10-17]. http://arxiv.org/abs/1811.07684.
113	DU J Y, NA X Y, LIU X C, et al. AISHELL-2: transforming mandarin ASR research into industrial scale[EB/OL]. [2023-10-17]. http://arxiv.org/abs/1808.10583.
114	HOU J Y , SHI Y Y , OSTENDORF M , et al. Region proposal network based small-footprint keyword spotting. IEEE Signal Processing Letters, 2019, 26 (10): 1471- 1475.
115	QIN X Y, BU H, LI M. Hi-Mia: a far-field text-dependent speaker verification database and the baselines[C]//Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2020: 7609-7613.

[1]	Xingrui YANG, Bin MA, Senyao LI, Xian ZHONG. Large Language Model-based Idempotent Summarization Method for Educational Text [J]. Computer Engineering, 2024, 50(7): 32-41.
[2]	HOU Yutao, Abudukelimu Abulizi, SHI Yaqing, Mayilamu Musideke, Halidanmu Abudukelimu. Research on Low-Resource Language Machine Translation for the ″Belt and Road″ [J]. Computer Engineering, 2024, 50(4): 332-341.
[3]	SI Mingyue, QI Bin, ZHANG Wensheng, ZHANG Lei. Multi-Dimensional Data Calculation and Few-Shot Learning for Intelligent Transportation Based on Tensor Calculation [J]. Computer Engineering, 2024, 50(4): 41-49.
[4]	Beibei MA, Zhigang HU, Peng SHI, Xinzheng WANG, Feihu XIE, Kena SONG. Design and Implementation of Moxibustion Robot System [J]. Computer Engineering, 2024, 50(2): 214-223.
[5]	Xiongbo FENG, Yuxin HUANG, Hua LAI, Yumeng GAO. Research on Low-Resource Cross-Lingual Summarization Method Based on Multi-Strategy Reinforcement Learning [J]. Computer Engineering, 2024, 50(2): 68-77.
[6]	Haoxin LIU, Chao DONG, Zhinan GOU, Kai GAO. Few-Shot Relation Extraction Method Fusing with Hybrid Representation [J]. Computer Engineering, 2023, 49(8): 63-68.
[7]	Jinshuo LIU, Daichen WANG, Juan DENG, Lina WANG. Classification of Harmful Information on Internet Based on Long-Tailed Classification Algorithm [J]. Computer Engineering, 2023, 49(8): 13-19, 28.
[8]	Yuyan WANG, Jiapeng ZHAO, Jinqiao SHI, Liyan SHEN, Hongmeng LIU, Yanyan YANG. User Identity Information Aggregation Method for Darknet Web Page [J]. Computer Engineering, 2023, 49(11): 187-194, 210.
[9]	WU Zhaoyuan, YU Zhengtao, HUANG Yuxin. Chinese-Vietnamese Cross-Lingual Word-Embedding Combined with Word Cluster Constraints [J]. Computer Engineering, 2023, 49(1): 82-91.
[10]	WANG Ziheng, JIANG Zhongding. Enhanced Desktop Display System Supporting Multi-Modal Interaction [J]. Computer Engineering, 2022, 48(7): 177-188.
[11]	QIU Zhen, XI Xuefeng, CUI Zhiming, SHENG Shengli, HU Fuyuan. Few-Shot Image Classification Based on Multi-Resolution Self-Distillation Network [J]. Computer Engineering, 2022, 48(12): 232-240.
[12]	HU Bin, WANG Xiaojun, ZHANG Lei. A Semi-Supervised Adversarial Robust Model-Agnostic Meta-Learning Method [J]. Computer Engineering, 2022, 48(12): 112-118.
[13]	CHEN Liangchen, FU Deyin. Survey on Machine Learning Methods for Small Sample Data [J]. Computer Engineering, 2022, 48(11): 1-13.
[14]	WANG Huiyong, LU Chao, ZHANG Xiaoming. Image Caption Model Based on Few-Shot Learning and Semantic Information [J]. Computer Engineering, 2021, 47(8): 260-270.
[15]	FAN Xing, LIU Zhanwen, LIN Shan, DOU Ruijuan. Fatigue Driving Detection Model Fusing with Human Eye Features and Deep Learning [J]. Computer Engineering, 2021, 47(8): 243-250.

Please choose a citation manager

Content to export