Thumbnail
Access Restriction
Open

Author Huet, Stéphane ♦ Gravier, Guillaume ♦ Sébillot, Pascale
Source Hyper Articles en Ligne (HAL)
Content type Text
File Format PDF
Language English
Subject Keyword natural language generation ♦ recurrent neural network ♦ adversarial bandit ♦ online learning ♦ user adaptation ♦ Index Terms: speech recognition ♦ parts of speech ♦ confidence measures ♦ info ♦ Computer Science [cs]/Computation and Language [cs.CL] ♦ Computer Science [cs]/Signal and Image Processing
Abstract We study the use of morphosyntactic knowledge to process N-best lists. We propose a new score function that combines the parts of speech (POS), language model, and acoustic scores at the sentence level. Experimental results, obtained for French broadcast news transcription, show a significant improvement of the word error rate with various decoding criteria commonly used in speech recognition. Interestingly, we observed more grammatical transcriptions, which translates into a better sentence error rate. Finally, we show that POS knowledge also improves posterior based confidence measures.
Educational Use Research
Learning Resource Type Proceeding
Page Count 4
Starting Page 1741
Ending Page 1744