An investigation on training deep neural networks using probabilistic transcriptions

Research output: Contribution to journalConference article


In this study, a transfer learning technique is presented for crosslingual speech recognition in an adverse scenario where there are no natively transcribed transcriptions in the target language. The transcriptions that are available during training are transcribed by crowd workers who neither speak nor have any familiarity with the target language. Hence, such transcriptions are likely to be inaccurate. Training a deep neural network (DNN) in such a scenario is challenging; previously reported results have described DNN error rates exceeding the error rate of an adapted Gaussian Mixture Model (GMM). This paper investigates multi-task learning techniques using deep neural networks which are suitable for this scenario. We report, for the first time, absolute improvement in phone error rates (PER) in the range 1.3-6.2% over GMMs adapted to probabilistic transcriptions. Results are reported for Swahili, Hungarian, and Mandarin.

Original languageEnglish (US)
Pages (from-to)3858-3862
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
StatePublished - Jan 1 2016
Event17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016 - San Francisco, United States
Duration: Sep 8 2016Sep 16 2016



  • Cross-lingual speech recognition
  • Deep neural networks
  • Probabilistic transcription grant
  • Transfer learning

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modeling and Simulation

Cite this