Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-P11.3 |
| Session: | Topics in Large Vocabulary Continuous Speech Recognition |
| Time: | Thursday, May 20, 09:30 - 11:30 |
| Presentation: |
Poster |
| Topic: |
Speech Processing: Confidence Measures/Rejection |
| Title: |
HYBRID LANGUAGE MODELS FOR OUT OF VOCABULARY WORD DETECTION IN LARGE VOCABULARY CONVERSATIONAL SPEECH RECOGNITION |
| Authors: |
Ali Yazgan; Johns Hopkins University | | |
| | Murat Saraclar; AT&T Labs - Research | | |
| Abstract: |
In this paper, we propose a method for out-of-vocabulary (OOV) word detection and taking a step toward open vocabulary automatic speech recognition. The proposed method uses a hybrid language model combining words and sub-word units such as phones or syllables. We describe a detection algorithm based on the posterior count of the OOV words given the hybrid model, and compare it to using the posterior probability of the best word string given a conventional word only model. Experimental results on the Switchboard corpus are presented for different vocabulary sizes. The new method yields a gain of over 10% in OOV word detection. In addition, a modest number of the OOV word pronunciations are found correctly. |
| |
| Back | |