Performance comparison of training algorithms for semi-supervised discriminative language modeling
13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, Portland, OR, Amerika Birleşik Devletleri, 9 - 13 Eylül 2012, cilt.1, ss.206-209, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 1
- Doi Numarası: 10.21437/interspeech.2012-68
- Basıldığı Şehir: Portland, OR
- Basıldığı Ülke: Amerika Birleşik Devletleri
- Sayfa Sayıları: ss.206-209
- Anahtar Kelimeler: Discriminative training, Hypothesis simulation, Language modeling, Ranking perceptron, Semi-supervised learning
- Boğaziçi Üniversitesi Adresli: Evet
Özet
Discriminative language modeling (DLM) has been shown to improve the accuracy of automatic speech recognition (ASR) systems, but it requires large amounts of both acoustic and text data for training. One way to overcome this is to use simulated hypotheses instead of real hypotheses for training, which is called semi-supervised training. In this study, we compare six different perceptron algorithms with the semi-supervised training approach. We formulate the DLM both as a structured prediction and a reranking problem, optimizing different criteria in each. We find that ranking variants achieve similar or better word error rate (WER) reduction with respect to structured perceptrons when used with real, simulated, or a combination of such data.