MT-based artificial hypothesis generation for unsupervised discriminative language modeling


Dikici E., SARAÇLAR M.

23rd European Signal Processing Conference, EUSIPCO 2015, Nice, Fransa, 31 Ağustos - 04 Eylül 2015, ss.1401-1405, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/eusipco.2015.7362614
  • Basıldığı Şehir: Nice
  • Basıldığı Ülke: Fransa
  • Sayfa Sayıları: ss.1401-1405
  • Anahtar Kelimeler: confusion model, Discriminative language model, machine translation, unsupervised training
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

Discriminative language modeling (DLM) is used as a postprocessing step to correct automatic speech recognition (ASR) errors. Traditional DLM training requires a large number of ASR N-best lists together with their reference transcriptions. It is possible to incorporate additional text data into training via artificial hypothesis generation through confusion modeling. A weighted finite-state transducer (WFST) or a machine translation (MT) system can be used to generate the artificial hypotheses. When the reference transcriptions are not available, training can be done in an unsupervised way via a target output selection scheme. In this paper we adapt the MT-based artificial hypothesis generation approach to un-supervised discriminative language modeling, and compare it with the WFST-based setting. We achieve improvements in word error rate of up to 0.7% over the generative baseline, which is significant at p < 0.001.