Corpus ID: 18870469

Developing a Multilingual Telephone Based Information System in African Languages

@inproceedings{Roux2000DevelopingAM,
  title={Developing a Multilingual Telephone Based Information System in African Languages},
  author={Justus C. Roux and Elizabeth C. Botha and Johan A. du Preez},
  booktitle={LREC},
  year={2000}
}
This paper introduces the first project of its kind within the Southern African language engineering context. It focuses on the role of idiosyncratic linguistic and pragmatic features of the different languages concerned and how these features are to be accommodated within (a) the creation of applicable speech corpora and (b) the design of the system at large. An introduction to the multilingual realities of South Africa and its implications for the development of databases is followed by a… Expand
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 inExpand
Collecting and evaluating speech recognition corpora for 11 South African languages
TLDR
The Lwazi corpus for automatic speech recognition (ASR) is described, a new telephone speech corpus which contains data from the eleven official languages of South Africa, and a surprisingly small number of speakers and around 10 to 20 h of speech per language are sufficient for acceptable phone-based recognition. Expand
The impact of accents on automatic recognition of South African English speech: a preliminary investigation
TLDR
Preliminary research indicates that there is merit to committing resources to the task of accented training, and two sets of hidden Markov Models for isolated word English speech were trained. Expand
African speech technology (AST) telephone speech databases: corpus design and contents
TLDR
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. Expand
Collecting and Evaluating Speech Recognition Corpora for Nine Southern Bantu Languages
TLDR
The Lwazi corpus for automatic speech recognition (ASR), a new telephone speech corpus which includes data from nine Southern Bantu languages, is described and the investigation of the stability of the ASR models derived from the corpus is reported on. Expand
Towards a Multilingual Recognition System Based on Phone-clustering Scheme for Decoding Local Languages
obviate problems of language boundary detection and language identification (LID) involved in the former scheme, the one-pass recognizer with a multilingual language and acoustic models is preferred.Expand
A new definition of Xhosa grapheme-to-phoneme rules for automatic transcription
A new definition of grapheme-to-phoneme rules was developed for automatically transcribing Xhosa text. An existing rule set was expanded and refined for the purposes of enhancing its accuracy andExpand
Rapid Development of an Afrikaans English Speech-to-Speech Translator
TLDR
The resulting system represent the first fully functional prototype built for Afrikaans to English speech translation, and the steps required to rapidly adapt ASR, MT and TTS component to AFrikaans under limited time and data constraints. Expand
Acoustic modelling of Sepedi affricates for ASR
TLDR
This approach reduces the Sepedi phoneme inventory from 45 to 32, resulting in simpler dictionary development and transcription processes, as well as more accurate acoustic modelling. Expand
Automatic speech recognition for under-resourced languages: A survey
TLDR
This paper proposes, in this paper, a survey that focuses on automatic speech recognition (ASR) for under-resourced languages, and a literature review of the recent contributions made. Expand
...
1
2
...

References

SHOWING 1-10 OF 21 REFERENCES
Evaluating the pronunciation component of text-to-speech systems for English: a performance comparison of different approaches
TLDR
Four representative approaches to automatic phonemization on the same test dictionary are compared, with best translation results obtained with PbA at approximately 72% words correct on a resonably large pronouncing dictionary, indicating that automatic pronunciation of text is not a solved problem. Expand
Towards modelling the acoustic differences between the diphthongs of Afrikaans and English L1 and L2 speech
  • C. P. Prinsloo, E. Botha
  • Computer Science
  • 1999 IEEE Africon. 5th Africon Conference in Africa (Cat. No.99CH36342)
  • 1999
TLDR
This paper presents aspects of a study which aims to model the acoustic differences between first language (L1) and secondlanguage (L2) speech to enable improvements in automatic speech recognition systems by applying the models to assist in speaker adaptation. Expand
A hidden Markov-model-based trainable speech synthesizer
TLDR
A set of cross-word decision-tree state-clustered context-dependent hidden Markov models are used to define a set of subphone units to be used in a concatenation synthesizer, which produces speech which is both natural sounding and highly intelligible. Expand
On automatic estimation of articulatory parameters in a text-to-speech system
TLDR
It is demonstrated that good quality speech synthesis is possible through a phoneme-level control of an articulatory model, and the synthesis is devoid of any artifacts, even in transitions, due to parameterization at the phoneme level. Expand
Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones
TLDR
In a common framework several algorithms that have been proposed recently, in order to improve the voice quality of a text-to-speech synthesis based on acoustical units concatenation based on pitch-synchronous overlap-add approach are reviewed. Expand
Temporal organisation in some varieties of South African English: Syllable compression effects in different types of foot structures
  • In Proceedings of Workshop on Black South African English,
  • 2000
Temporal organisation in some varieties of South African English: Syllable compression effects in different types of foot structures Cape Town
  • Proceedings of Workshop on Black South African English, International Conference on Linguistics in South Africa
  • 2000
Voicing Phenomena in Zulu-English
  • In Proceedings of Workshop on Black South African English,
  • 2000
Voicing Phenomena in Zulu-English Cape Town
  • Proceedings of Workshop on Black South African English, International Conference on Linguistics in South Africa
  • 2000
Towards an acoustic comparison of first and second language South African English
  • In Proceedings of the Tenth South African Workshop on Pattern Recognition (paper #0009)
  • 1999
...
1
2
3
...