Corrective language modeling for large vocabulary ASR with the perceptron algorithm


Roark B., SARAÇLAR M., Collins M.

Proceedings - IEEE International Conference on Acoustics, Speech, and Signal Processing, Montreal, Kanada, 17 - 21 Mayıs 2004, cilt.1, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 1
  • Basıldığı Şehir: Montreal
  • Basıldığı Ülke: Kanada
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

This paper investigates error-corrective language modeling using the perceptron algorithm on word lattices. The resulting model is encoded as a weighted finite-state automaton, and is used by intersecting the model with word lattices, making it simple and inexpensive to apply during decoding. We present results for various training scenarios for the Switchboard task, including using n-gram features of different orders, and performing n-best extraction versus using full word lattices. We demonstrate the importance of making the training conditions as close as possible to testing conditions. The best approach yields a 1.3 percent improvement in first pass accuracy, which translates to 0.5 percent improvement after other rescoring passes.