Phonetic analysis of Afrikaans, English, Xhosa and Zulu using South African speech databases

  title={Phonetic analysis of Afrikaans, English, Xhosa and Zulu using South African speech databases},
  author={Thomas R. Niesler and Philippa H. Louw and Justus C. Roux},
  journal={Southern African Linguistics and Applied Language Studies},
  pages={459 - 474}
We present a corpus-based analysis of the Afrikaans, English, Xhosa and Zulu languages, comparing these in terms of phonetic content, diversity and mutual overlap. Our aim is to shed light on the fundamental phonetic interrelationships between these languages, with a view to furthering progress in multilingual automatic speech recognition in general, and in the South African region in particular. 
Formant Analysis of Punjabi Non-nasalized Vowel Phonemes
  • Pardeep Singh, Kamlesh Dutta
  • Computer Science
    2011 International Conference on Computational Intelligence and Communication Networks
  • 2011
This paper shows formant analysis of vowels produced by speakers of Punjabi as a first language from Punjab and indicates that both language have different vowel phonemes.
Language-dependent state clustering for multilingual speech recognition in Afrikaans, South African English, Xhosa and Zulu
The development of automatic speech recognition systems requires significant quantities of annotated acoustic data. In South Africa, the large number of spoken languages hampers such data collection
Data-driven phonetic comparison and conversion between south african, british and american English pronunciations
It is found that pronunciations of unknown words can be more accurately determined from a known pronunciation in a different accent than by means of G2P methods.
Educated mother-tongue South African English: A corpus approach
Abstract South Africa is anecdotally known for its complex system of speech varieties correlating with variables such as ethnicity, first language, class and education. These intuitions (e.g. Lass
Phonetic Analysis of Clicks, Plosives and Implosives of IsiXhosa: A Preliminary Report
This pilot study examined the effectiveness of locus equations in differentiating places of articulation among stop consonants (clicks, plosives and implosives) in IsiXhosa in the context of the
Automatic conversion between pronunciations of different English accents
It is substantially more accurate to derive pronunciations in this way than directly from the orthography and available target accent pronunciationations using more conventional grapheme-to-phoneme (G2P) conversion.
Language identification and multilingual speech recognition using discriminatively trained acoustic models
Experiments indicate that discriminative training leads to a small overall improvement in language identification accuracy while not affecting the speech recognition performance strongly, indicating that these may require special treatment within a multilingual speech recognition system.
Core vocabulary intervention for an isiXhosa-English speaking child with speech sound difficulties
Abstract In this paper we describe speech difficulties observed in a bilingual child (aged 3 years, 0 months at the time of assessment) acquiring isiXhosa and English in South Africa. Speech
Language-dependent state clustering for multilingual acoustic modelling
It is found that multilingual acoustic models obtained in this way show a small but consistent improvement over separate-language systems as well as systems based on IPA-based data pooling.
Sounds Affecting the Moments of Stuttering in Multilingualism: A Case Study
Research involving stuttering in multilingual individuals is limited. Speech-language therapists face the challenge of treating a diverse client base, which includes multilingual individuals. The aim


African speech technology (AST) telephone speech databases: corpus design and contents
The design and contents of the speech corpus that is currently being collected over both mobile and fixed networks are described and language coverage is discussed within the framework of the multilingual character of the South African population.
A course in phonetics
Part I Introductory concepts: articulatory phonetics phonology and phonetic transcription. Part II English phonetics: the Consonants of English English vowels English words and sentences. Part III
Relative clause formation in the Bantu languages of South Africa
This article discusses (verbal) relative clauses in the Bantu languages spoken in South Africa. The first part of the article offers a comparison of the relative clause formation strategies in Sotho,
The African Speech Technology Project: An Assessment
This paper reflects on the recently completed African Speech Technology (AST) Project. The AST Project successfully developed eleven annotated telephone speech databases for five languages spoken in
Voice quality differences associated with stops and clicks in Xhosa
It is argued that extensive larynx lowering and vocal fold slackening can explain the specifics of the voicing feature in Xhosa and suggested that “slack voice” is a more appropriate term for the relevantXhosa sounds than “breathy voice’.
Language-independent and language-adaptive acoustic modeling for speech recognition
Different methods for multilingual acoustic model combination and a polyphone decision tree specialization procedure are introduced for estimating acoustic models for a new target language using speech data from varied source languages, but only limited data from the target language.
Multilingual phone models for vocabulary-independent speech recognition tasks
Three different methods to develop multilingual phone models for flexible speech recognition tasks are presented and a huge reduction of the number of densities in the multilingual system is observed.
Handbook of the International Phonetic Association: a guide to the use of the International Phonetic Alphabet (1999). Cambridge: Cambridge University Press. Pp. ix+204.
As stated in its Foreword, the Handbook is a ‘user’s manual’ for the International Phonetic Alphabet (IPA). It provides a variety of information about the philosophy and practice of IPA usage and in
A Maximum Likelihood Approach to Continuous Speech Recognition
This paper describes a number of statistical models for use in speech recognition, with special attention to determining the parameters for such models from sparse data, and describes two decoding methods appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks.
Estimation of probabilities from sparse data for the language model component of a speech recognizer
  • S. Katz
  • Computer Science
    IEEE Trans. Acoust. Speech Signal Process.
  • 1987
The model offers, via a nonlinear recursive procedure, a computation and space efficient solution to the problem of estimating probabilities from sparse data, and compares favorably to other proposed methods.