Hallucinated n-best lists for discriminative language modeling
2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012, Kyoto, Japonya, 25 - 30 Mart 2012, ss.5001-5004, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/icassp.2012.6289043
- Basıldığı Şehir: Kyoto
- Basıldığı Ülke: Japonya
- Sayfa Sayıları: ss.5001-5004
- Anahtar Kelimeler: automatic speech recognition, discriminative training, language modeling, semi-supervised methods
- Boğaziçi Üniversitesi Adresli: Evet
Özet
This paper investigates semi-supervised methods for discriminative language modeling, whereby n-best lists are "hallucinated" for given reference text and are then used for training n-gram language models using the perceptron algorithm. We perform controlled experiments on a very strong baseline English CTS system, comparing three methods for simulating ASR output, and compare the results with training with "real" n-best list output from the baseline recognizer. We find that methods based on extracting phrasal cohorts - similar to methods from machine translation for extracting phrase tables - yielded the largest gains of our three methods, achieving over half of the WER reduction of the fully supervised methods. © 2012 IEEE.