Morpholexical and discriminative language models for Turkish automatic speech recognition


Sak H., SARAÇLAR M., GÜNGÖR T.

IEEE Transactions on Audio, Speech and Language Processing, cilt.20, sa.8, ss.2341-2351, 2012 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 20 Sayı: 8
  • Basım Tarihi: 2012
  • Doi Numarası: 10.1109/tasl.2012.2201477
  • Dergi Adı: IEEE Transactions on Audio, Speech and Language Processing
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.2341-2351
  • Anahtar Kelimeler: Automatic speech recognition (ASR), disambiguation, discriminative model, morpholexical language model, morphology, reranking
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

This paper introduces two complementary language modeling approaches for morphologically rich languages aiming to alleviate out-of-vocabulary (OOV) word problem and to exploit morphology as a knowledge source. The first model, morpholexical language model, is a generative $n$-gram model, where modeling units are lexical-grammatical morphemes instead of commonly used words or statistical sub-words. This paper also proposes a novel approach for integrating the morphology into an automatic speech recognition (ASR) system in the finite-state transducer framework as a knowledge source. We accomplish that by building a morpholexical search network obtained by the composition of lexical transducer of a computational lexicon with a morpholexical language model. The second model is a linear reranking model trained discriminatively with a variant of the perceptron algorithm using morpholexical features. This variant of the perceptron algorithm, WER-sensitive perceptron, is shown to perform better for reranking n -best candidates obtained with the generative model. We apply the proposed models in Turkish broadcast news transcription task and give experimental results. The morpholexical model leads to an elegant morphology-integrated search network with unlimited vocabulary. Thus, it is highly effective in alleviating OOV problem and improves the word error rate (WER) over word and statistical sub-word models by 1.8% and 0.4% absolute, respectively. The discriminatively trained morpholexical model further improves the WER of the system by 0.8% absolute. © 2012 IEEE.