Deriving Phonetic Transcriptions and Discovering Word Segmentations for Speech-to-Speech Translation in Low-Resource Settings

@inproceedings{Wilkinson2016DerivingPT,
  title={Deriving Phonetic Transcriptions and Discovering Word Segmentations for Speech-to-Speech Translation in Low-Resource Settings},
  author={A. Wilkinson and Tiancheng Zhao and A. Black},
  booktitle={INTERSPEECH},
  year={2016}
}
We investigate speech-to-speech translation where one language does not have a well-defined written form. We use English-Spanish and Mandarin-English bitext corpora in order to provide both gold-standard text-based translations and experimental results for different levels of automatically derived symbolic representations from speech. We constrain our experiments such that the methods developed can be extended to low-resource languages. We derive different phonetic representations of the source… Expand
7 Citations
Unsupervised Phonetic and Word Level Discovery for Speech to Speech Translation for Unwritten Languages
  • 1
  • PDF
A segmental framework for fully-unsupervised large-vocabulary speech recognition
  • 67
  • PDF
Low-resource speech translation
Phone Features Improve Speech Translation
  • 9
  • PDF
Natural language processing for resource-poor languages
  • 11
UWSpeech: Speech to Speech Translation for Unwritten Languages
  • 2
  • PDF

References

SHOWING 1-8 OF 8 REFERENCES
Bootstrapping Text-to-Speech for speech processing in languages without an orthography
  • 21
  • PDF
Word segmentation through cross-lingual word-to-phoneme alignment
  • 27
  • PDF
Automatic discovery of a phonetic inventory for unwritten languages for statistical speech synthesis
  • P. Muthukumar, A. Black
  • Computer Science
  • 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
  • 26
  • PDF
An Attentional Model for Speech Translation Without Transcription
  • 89
  • PDF
A Bayesian framework for word segmentation: Exploring the effects of context
  • 406
  • PDF
Flite: a small fast run-time synthesis engine
  • 149
  • PDF
Dragon mapper
  • 2014–2015. [Online]. Available: https://pypi.python.org/pypi/dragonmapper 3090
  • 2014