Improving language model perplexity and recognition accuracy for medical dictations via within-domain interpolation with literal and semi-literal corpora
Guergana Savova, Michael Schonwetter, Sergey Pakhomov · 2000
We propose a technique for improving language modeling for automated speech recognition of medical dictations by interpolating finished text (25M words) with small human-generated literal or/and machine-generated semiliteral corpora. By building and testing interpolated (ILM) with literal (LILM), semiliteral (SILM) and partial (PILM) corpora, we show that both perplexity and recognition results improve significantly with LILM and SILM; the two yielding very close results. 1.