Loading...
Please wait, while we are loading the content...
Similar Documents
Automatically Finding Semantically Consistent N-grams to Add New Words in LVCSR Systems
| Content Provider | Hyper Articles en Ligne (HAL) |
|---|---|
| Author | Lecorvé, Gwénolé Gravier, Guillaume Sébillot, Pascale |
| Copyright Year | 2011 |
| Abstract | This paper presents a new method to automatically add n-grams containing out-of-vocabulary (OOV) words to a baseline language model (LM), where these n-grams are sought to be grammatically correct and to make sense according to the meaning of OOV words. First, this method consists in determining the word sequences, i.e., n-grams, in which the usage of a given OOV word is the most semantically consistent. Then, conditional probabilities of these n-grams have to be computed. To do this, semantic relations between words are used to assimilate each OOV word to several equivalent in-vocabulary words. Based on these last words, n-grams from the baseline LM are re-used to find the word sequences to be added and to compute their probabilities. After augmenting the vocabulary and launching a recognition process, experiments show that our method results in WER improvements which are comparable to those obtained using a state-of-the-art open vocabulary LM. |
| Related Links | https://hal.science/hal-00645223/file/lecorve_icassp2011.pdf |
| Conference Proceedings | IEEE International Conference on Acoustics |
| Language | English |
| Publisher | HAL CCSD |
| Publisher Date | 2011-05-01 |
| Access Restriction | Open |
| Subject Keyword | Vocabulary adaptation Automatic speech recognition Natural language processing Language modeling |
| Content Type | Text |
| Resource Type | Conference Proceedings |
| Subject | Computer Science |
