@InProceedings{chen-EtAl:2016:WSSANLP2016,
  author    = {Chen, Wenda  and  Hasegawa-Johnson, Mark  and  Chen, Nancy  and  Jyothi, Preethi  and  Varshney, Lav},
  title     = {Clustering-based Phonetic Projection in Mismatched Crowdsourcing Channels for Low-resourced ASR},
  booktitle = {Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {133--141},
  abstract  = {Acquiring labeled speech for low-resource languages is a difficult task in the
	absence of native speakers of the language. One solution to this problem
	involves collecting speech transcriptions from crowd workers who are foreign or
	non-native speakers of a given target language. From these mismatched
	transcriptions, one can derive probabilistic phone transcriptions that are
	defined over the set of all target language phones using a noisy channel model.
	This paper extends prior work on deriving probabilistic transcriptions (PTs)
	from mismatched transcriptions by 1) modelling multilingual channels and 2)
	introducing a clustering-based phonetic mapping technique to improve the
	quality of PTs. Mismatched crowdsourcing for multilingual channels has certain
	properties of projection mapping, e.g., it can be interpreted as a clustering
	based on singular value decomposition of the segment alignments. To this end,
	we explore the use of distinctive feature weights, lexical tone confusions, and
	a two-step clustering algorithm to learn projections of phoneme segments from
	mismatched multilingual transcriber languages to the target language. We
	evaluate our techniques using mismatched transcriptions for Cantonese speech
	acquired from native English and Mandarin speakers. We observe a 5-9% relative
	reduction in phone error rate for the predicted Cantonese phone transcriptions
	using our proposed techniques compared with the previous PT method.},
  url       = {http://aclweb.org/anthology/W16-3714}
}