Abstract
Keyword spotting (KWS) refers to the spotting and retrieval of predefined keywords from audio database. Different supervised as well as unsupervised approaches have been implemented to do keyword spotting. Keyword spotting is considered to be the first among speech searching. Later, keyword spotting paved the way to Spoken Term Detection (STD) and Query by Example STD (QbE-STD). In the early days, researchers have used HMM for KWS, where the speech data is converted into corresponding text data for text-level matching. But, the latest techniques make use of MLP and DNN for doing search, so that the speech to text conversion is not necessary. All such techniques for keyword spotting are discussed briefly in this chapter.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Salehinejad H, Barfett J, Aarabi P, Valaee S, Colak E, Gray B, Dowdell T (2017) A convolutional neural network for search term detection. In: Proceedings of IEEE 28th annual international symposium on personal, indoor, and mobile radio communications (PIMRC), Montreal, QC, pp 1–6
Alumäe T, Karakos D, Hartmann W, Hsiao R, Zhang L, Nguyen L, Tsakalidis S, Schwartz, R (2017) The 2016 BBN Georgian telephone speech keyword spotting system. In: ICASSP, pp 5755–5759
Gupta V, Ajmera J, Kumar A, Verma A, (2011) A language independent approach to audio search. In: Proceedings of INTERSPEECH, pp 1125–01128
Barnwal S, Sahni K, Singh R, Raj B (2012) Spectrographic seam patterns for discriminative word spotting. In: Proceedings of ICASSP, pp 4725–4728
Ezzat T, Poggio T (2008) Discriminative word-spotting using ordered spectro-temporal patch features. In: Proceedings of SAPA workshop, in INTERSPEECH, pp 35–40
James DA, Young SJ (1994) A fast lattice-based approach to vocabulary independent word spotting. In: Proceedings of ICASSP, pp 337–380
Bridle JS (1973) An efficient elastic-template method for detecting given words in running speech. In: British acoustical society spring meeting, pp 1–4
Higgins AL, Wohlford RE, Bahler LG (1986) Keyword recognition system using template-concatenation model, European Patent Application, Publication No. 0 177 854
Rose RC, Paul DB (1990) A hidden Markov model based keyword recognition system. In: Proceedings of ICASSP, vol 1, pp 129–132
Weintraub M (1993) Keyword-spotting using SRI’s DECIPHER large-vocabulary speech-recognition system. In: Proceedings of ICASSP, vol 2, pp 463–466
Weintraub M (1995) LVSCR log-likelihood ratio scoring for keyword spotting. In: Proceedings of ICASSP, vol 1, pp 297–300
Iso K, Watanabe T (1990) Speaker-independent word recognition using a neural prediction model. In: Proceedings of ICASSP, pp 441–444
Suhardi S, Felbaum K (1997) Wordspotting using a predictive neural model for the telephone speech corpus. In: Proceedings of ICASSP, vol 2, pp 915–918
Thambiratnam K, Sridharan S (2005) Dynamic match phone-lattice searches for very fast and accurate unrestricted vocabulary keyword spotting. In: Proceedings of ICASSP, vol 1, pp 465–468
Garcia A, Gish H (2006) Keyword spotting of arbitrary words using minimal speech resources. In: Proceedings of ICASSP, vol 1, pp 949–952
Audhkhasi K, Verma A (2007) Keyword spotting using modified minimum edit distance measure. In: Proceedings of ICASSP, vol 4, pp 929–932
Xin L, Wang BX (2001) Utterance verification for spontaneous Mandarin speech keyword spotting. In: IEEE international conference on Info-tech and Info-net (ICII), vol 3, pp 397–401
Ou J, Chen K, Wang X, Li Z (2001) Utterance verification of short keywords using hybrid neural-network/HMM approach. In: IEEE international conference on Info-tech and Info-net (ICII), vol 2, pp 671–676
Thambiratnam K, Sridharan S (2003) Isolated word verification using cohort word-level verification. In: EUROSPEECH, pp 905–908
Chen G, Parada C, Heigold G (2014) Small-footprint keyword spotting using deep neural networks. In: Proceedings of ICASSP, pp 4087–4091
Sainath TN, Parada C (2015) Convolutional neural networks for small-footprint keyword spotting. In: INTERSPEECH, pp 1478–1482
Lim H, Kim Y, Kim Y, Kim H (2017) CNN-based bottleneck feature for noise robust query-by-example spoken term detection. In: Proceedings of Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC), Kuala Lumpur, pp 1278–1281
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2019 The Author(s), under exclusive licence to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Mary, L., G, D. (2019). Keyword Spotting Techniques. In: Searching Speech Databases. SpringerBriefs in Speech Technology. Springer, Cham. https://doi.org/10.1007/978-3-319-97761-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-97761-4_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97760-7
Online ISBN: 978-3-319-97761-4
eBook Packages: EngineeringEngineering (R0)