The South African directory enquiries (SADE) name corpus

We present the design and development of a South African directory enquiries corpus. It contains audio and orthographic transcriptions of a wide range of South African names produced by first-language speakers of four languages, namely Afrikaans, English, isiZulu and Sesotho. Useful as a resource to understand the effect of name language and speaker language on pronunciation, this is the first corpus to also aim to identify the “intended language”: an implicit assumption with regard to word origin made by the speaker of the name. We describe the design, collection, annotation, and verification of the corpus. This includes an analysis of the algorithms used to tag the corpus with meta information that may be beneficial to pronunciation modelling tasks.

[1]  Etienne Barnard,et al.  The NCHLT speech corpus of the South African languages , 2014, SLTU.

[2]  Jean-Pierre Martens,et al.  Improving Proper Name Recognition by Adding Automatically Learned Pronunciation Variants to the Lexicon , 2010, LREC.

[3]  Thomas Niesler,et al.  Automatic conversion between pronunciations of different English accents , 2011, Speech Commun..

[4]  Marelie H. Davel,et al.  Language identification of individual words with joint sequence models , 2014, INTERSPEECH.

[5]  Marelie H. Davel,et al.  Consistency of cross-lingual pronunciation of South African personal names , 2010 .

[6]  Marelie H. Davel,et al.  Pronunciation modelling of foreign words for Sepedi ASR , 2010 .

[7]  Murray F. Spiegel.  Proper Name Pronunciations for Speech Technology Applications , 2003, Int. J. Speech Technol..

[8]  Geoffrey Zweig,et al.  Automated directory assistance system - from theory to practice , 2007, INTERSPEECH.

[9]  Jean-Pierre Martens,et al.  Pronunciation-based ASR for names , 2009, INTERSPEECH.

[10]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[11]  Marelie Hattingh Davel,et al.  Performance Analysis of a Multilingual Directory Enquiries Application , 2014 .

[12]  Isabel Trancoso,et al.  Issues in the pronunciation of proper names: the experience of the Onomastica project , 2001 .

[13]  Etienne Barnard,et al.  ASR corpus design for resource-scarce languages , 2009, INTERSPEECH.

[14]  Neil Kleynhans,et al.  Improving the Lwazi ASR Baseline , 2016, INTERSPEECH.

[15]  Marelie H. Davel,et al.  Text-based language identification of multilingual names , 2015, 2015 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech).

[16]  Etienne Barnard,et al.  Orthographic measures of language distances between the official South African languages , 2008 .

[17]  Bart D'hoore,et al.  How speaker tongue and name source language affect the automatic recognition of spoken names , 2009, INTERSPEECH.

[18]  Javier Macías Guarasa,et al.  An interactive directory assistance service for Spanish with large-vocabulary recognition , 2001, INTERSPEECH.

[19]  Qian Yang,et al.  Development of a phoneme-to-phoneme (p2p) converter to improve the grapheme-to-phoneme (g2p) conversion of names , 2006, LREC.

[20]  Helmer Strik,et al.  Modeling pronunciation variation for ASR: A survey of the literature , 1999, Speech Commun..

[21]  Jing Zheng.  Pronunciation Variation Modeling for Automatic Speech Recognition , 2014 .

[22]  Etienne Barnard,et al.  Speech Technology for Information Access: a South African Case Study , 2010, AAAI Spring Symposium: Artificial Intelligence for Development.

[23]  Candace A. Kamm,et al.  Speech recognition issues for directory assistance applications , 1995, Speech Commun..

[24]  Frédéric Béchet,et al.  Dynamic generation of proper name pronunciations for directory assistance , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[25]  Kenneth Ward Church.  Stress assignment in letter to sound rules for speech synthesis , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[26]  Marelie H. Davel,et al.  ASR performance analysis of an experimental call routing system , 2009 .

[27]  Lori Lamel,et al.  Chapter 5 – Multilingual Dictionaries , 2006 .

[28]  F. Bechet,et al.  Very large vocabulary proper name recognition for directory assistance , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

[29]  Joakim Gustafson.  ONOMASTICA - Creating a multi-lingual dictionary of European names , 2009 .

[30]  Ariadna Font Llitjós,et al.  Knowledge of language origin improves pronunciation accuracy of proper names , 2001, INTERSPEECH.

[31]  Benoit Maison,et al.  Pronunciation modeling for names of foreign origin , 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

[32]  Hermann Ney,et al.  Joint-sequence models for grapheme-to-phoneme conversion , 2008, Speech Commun..

[33]  Marelie H. Davel,et al.  The predictability of name pronunciation errors in four South African languages , 2011 .

[34]  Etienne Barnard,et al.  A Southern African corpus for multilingual name pronunciation , 2011 .

[35]  Hauke Schramm,et al.  Strategies for name recognition in automatic directory assistance systems , 2000, Speech Commun..

[36]  Marelie H. Davel,et al.  Pronunciation dictionary development in resource-scarce environments , 2009, INTERSPEECH.

[37]  Ariadna Font Llitjós,et al.  Improving Pronunciation Accuracy of Proper Names with Language Origin Classes , 2001 .

[38]  Jean-Pierre Martens,et al.  Improving proper name recognition by means of automatically learned pronunciation variants , 2012, Speech Commun..

[39]  Etienne Barnard,et al.  Multilingual pronunciations of proper names in a Southern African corpus , 2012 .

[40]  Bart D'hoore,et al.  The AUTONOMATA Spoken Names Corpus , 2008, LREC.