Classification and ranking approaches to discriminative language modeling for ASR


Dikici E., Semerci M., SARAÇLAR M., Alpaydin E.

IEEE Transactions on Audio, Speech and Language Processing, cilt.21, sa.2, ss.291-300, 2013 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 21 Sayı: 2
  • Basım Tarihi: 2013
  • Doi Numarası: 10.1109/tasl.2012.2221461
  • Dergi Adı: IEEE Transactions on Audio, Speech and Language Processing
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.291-300
  • Anahtar Kelimeler: Discriminative language modeling (DLM), feature selection, data sampling, language modeling, ranking perceptron, ranking support vector machine (SVM), margin infused relaxed algorithm (MIRA), ranking MIRA, speech recognition
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

Discriminative language modeling (DLM) is a feature-based approach that is used as an error-correcting step after hypothesis generation in automatic speech recognition (ASR). We formulate this both as a classification and a ranking problem and employ the perceptron, the margin infused relaxed algorithm (MIRA) and the support vector machine (SVM). To decrease training complexity, we try count-based thresholding for feature selection and data sampling from the list of hypotheses. On a Turkish morphology based feature set we examine the use of first and higher order n-grams and present an extensive analysis on the complexity and accuracy of the models with an emphasis on statistical significance. We find that we can save significantly from computation by feature selection and data sampling, without significant loss in accuracy. Using the MIRA or SVM does not lead to any further improvement over the perceptron but the use of ranking as opposed to classification leads to a 0.4% reduction in word error rate (WER) which is statistically significant. © 2006-2012 IEEE.