Abstract
Efficient methods for the similarity search in word databases play a significant role in various applications such as the robust search or indexing of names and addresses, spell-checking algorithms or the monitoring of trademark rights. The underlying distance measures are associated with similarity criteria of the users, and phonetic-based search algorithms are well-established since decades. Nonetheless, rule-based phonetic algorithms exhibit some weak points, e.g. their strong language dependency, the search overhead by tolerance or the risk of missing valid matches vice versa, which causes a pseudo-phonetic functionality in some cases. In contrast, we suggest a novel, adaptive method for similarity search in words, which is based on a trainable grapheme-to-phoneme (G2P) converter that generates most likely and widely correct pronunciations. Only as a second step, the similarity search in the phonemic reference data is performed by involving a conventional string metric such as the Levenshtein distance (LD). The G2P algorithm achieves a string accuracy of up to 99.5% in a German pronunciation lexicon and can be trained for different languages or specific domains such as proper names. The similarity tolerance can be easily adjusted by parameters like the admissible number or likability of pronunciation variants as well as by the phonemic or graphemic LD. As a proof of concept, we compare the G2P-based search method on a German surname database and a telephone book including first name, surname and street name to similarity matches by the conventional Cologne phonetic (Kölner Phonetik, KP) algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Baayen, R., Piepenbrock, R., Gulikers, L.: CELEX2 lexical database of German (Version 2.0). Linguistic Data Consortium Philadelphia (1995). https://catalog.ldc.upenn.edu/ldc96l14. Accessed 12 Oct 2016
Bisani, M., Ney, H.: Joint-sequence models for grapheme-to-phoneme conversion. Speech Commun. 50(5), 434–451 (2008). https://www-i6.informatik.rwth-aachen.de/web/Software/g2p.html, gPL software
D’Haro, L.F., Banchs, R.E.: Automatic correction of ASR outputs by using machine translation. In: Interspeech 2016, San Francisco, pp. 3469–3473 (2016). http://dx.doi.org/10.21437/Interspeech.2016-299
Hain, H.-U.: Graphem-Phonem-Konvertierung, Patent DE 100 42 944 C2 (2003). (in German)
Hain, H.-U.: Phonetische Transkription für ein multilinguales Sprachsynthesesystem. PhD thesis, TU Dresden (2004). (in German)
Kessler, B.: Phonetic comparison algorithms. Trans. Philol. Soc. 103(2), 243–260 (2005)
Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. Dokl. Akad. Nauk SSSR 163(4), 845–848 (1965). (in Russian)
Madden, R.: (2013). https://github.com/rockymadden/stringmetric/. Accessed 03 Apr 2017
Odell, M.K., Russell, R.C.: US patents 1 261 167 and 1 435 683 (1918, 1922). https://en.wikipedia.org/wiki/Soundex
Pardeshi, J.B., Nandwalkar, B.R.: Survey on rule based phonetic search for slavic surnames. J. Comput. Technol. Appl. 7(1), 65–68 (2016)
Parmar, V.P., Kumbharana, C.K.: Study existing various phonetic algorithms and designing and development of a working model for the new developed algorithm and comparison by implementing it with existing algorithms. J. Comput. Appl. 98(19), 45–49 (2014)
Philips, L.: Hanging on the metaphone. J. Comput. Lang. 7(12), 39–44 (1990)
Philips, L.: The double metaphone search algorithm. C/C++ Users J. 18(6), 38–43 (2000)
Plique, G.: (2014). http://yomguithereal.github.io/clj-fuzzy/. Accessed 03 Apr 2017
Postel, H.J.: Die Kölner Phonetik. Ein Verfahren zur Identifizierung von Personennamen auf der Grundlage der Gestaltanalyse. IBM-Nachrichten 19, 925–931 (1969). (in German)
Interface for data exchange in automated information process according to §112 TKG between Federal Network Agency and beneficiary (SBS, in German). Version 1.0, 27 October (2015). https://www.bundesnetzagentur.de/DE/Sachgebiete/Telekommunikation/Unternehmen_Institutionen/Anbieterpflichten/OeffentlicheSicherheit/AutomatisiertesAuskunftsverfahren/Automatisiertesauskunftsverfahren-node.html. Accessed 10 Dec 2016
Interface for data exchange in automated information process according to Section 112 TKG between Federal Network Agency and obligor (SBV, in German). Version 1.1 (Draft), 04 January (2016). https://www.bundesnetzagentur.de/DE/Sachgebiete/Telekommunikation/Unternehmen_Institutionen/Anbieterpflichten/OeffentlicheSicherheit/AutomatisiertesAuskunftsverfahren/Automatisiertesauskunftsverfahren-node.html. Accessed 10 Dec 2016
Shah, R., Singh, D.K.: Analysis and comparative study on phonetic matching techniques. Int. J. Comput. Appl. 87(9), 14–17 (2014)
Shah, R., Singh, D.K.: Improvement of Soundex algorithm for Indian language based on phonetic matching. Int. J. Comput. Sci. Eng. Appl. (IJCSEA) 4(3), 31–39 (2014)
http://yomguithereal.github.io/talisman/phonetics/. Accessed 03 Apr 2017
Das Telefonbuch Deutschland. https://www.telefoncd.de/DasTelefonbuch-CD-mit-Rueckwaertssuche.html (2016). German phone book DVD 2016–17, data status 01 September 2016
Supraregional collection of German family names from death certificates. Verein für Computergenealogie, Erkrath (2016). www.familienanzeigen.org/totzfanamen.php. Accessed 12 Oct 2016
Wells, J.: SAMPA - computer readable phonetic alphabet (1997). http://www.phon.ucl.ac.uk/home/sampa/. Accessed 10 Jan 2017
Zahoranský, D., Polasek, I.: Text search of surnames in some slavic and other morphologically rich languages using rule based phonetic algorithms. IEEE/ACM Trans. Audio Speech Lang. Process. 23(3), 553–563 (2015)
Acknowledgements
We would like to thank Haya Hadidi and Tristan Münz from the Federal Network Agency of Germany (Bundesnetzagentur) for initiating this research and their practical hints on AAV procedures. Further thanks goes to Viktor Iaroshenko from HfT Leipzig and to Gabor Pintér from Kobe University in Japan for their project support and advice.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Jokisch, O., Hain, HU. (2017). A Trainable Method for the Phonetic Similarity Search in German Proper Names. In: Karpov, A., Potapova, R., Mporas, I. (eds) Speech and Computer. SPECOM 2017. Lecture Notes in Computer Science(), vol 10458. Springer, Cham. https://doi.org/10.1007/978-3-319-66429-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-66429-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66428-6
Online ISBN: 978-3-319-66429-3
eBook Packages: Computer ScienceComputer Science (R0)