Text-based language identification (T-LID) of isolated words has been shown to be useful for various speech processing tasks, including pronunciation modelling and data categorisation. When the words to be categorised are proper names, the task becomes more difficult: not only do proper names often have idiosyncratic spellings, they are also often considered to be multilingual. We, therefore, investigate how an existing T-LID technique can be adapted to perform multilingual word classification. That is, given a proper name, which may be either mono-or multilingual, we aim to determine how accurately we can predict how many possible source languages the word has, and what they are. Using a Joint Sequence Modelbased approach to T-LID and the SADE corpus-a newly developed proper names corpus of South African names-we experiment with different approaches to multilingual T-LID. We compare posterior-based and likelihood-based methods and obtain promising results on a challenging task.

Within a multilingual automatic speech recognition (ASR) system, knowledge of the language of origin of unknown words can improve pronunciation modelling accuracy. This is of particular importance for ASR systems required to deal with codeswitched speech or proper names of foreign origin. For words that occur in the language model, but do not occur in the pronunciation lexicon, text-based language identification (T-LID) of a single word in isolation may be required. This is a challenging task, especially for short words. We motivate for the importance of accurate T-LID in speech processing systems and introduce a novel way of applying Joint Sequence Models to the T-LID task. We obtain competitive results on a real-world 4language task: for our best JSM system, an F-measure of 97.2% is obtained, compared to a F-measure of 95.2% obtained with a state-of-the-art Support Vector Machine (SVM).

Utilising the known language of origin of a name can be useful when predicting the pronunciation of the name. When this language is not known, automatic language identification (LID) can be used to influence which language-specific grapheme-to-phoneme (G2P) predictor is triggered to produce a pronunciation for the name. We investigate the implications when both the LID system and the G2P system generate errors: what influence does this have on a resulting speech recognition system? We experiment with different approaches to LID-based dictionary creation and report on results in four South African languages: Afrikaans, English, Sesotho and isiZulu.

We present the design and development of a South African directory enquiries (DE) corpus. It contains audio and orthographic transcriptions of a wide range of South African names produced by firstlanguage 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.