Bag-of-Words Modelling for Speech Recognition
2009Vol. 3, pp. 646–650
Citations Over TimeTop 19% of 2009 papers
Abstract
A semantic language modelling method for speech recognition is presented. The method is somehow similar to latent semantic analysis, but it does not need so much memory and training data. Even though it gave better experimental results, provided as percentage of correctly recognized sentences from a corpus. It differentiate from latent semantic analysis by a choice of similar topics influencing a matrix describing probability of words appearing in topics.
Related Papers
- → lsemantica: A command for text similarity based on latent semantic analysis(2019)20 cited
- Comparison of Latent Semantic Analysis and Probabilistic Latent Semantic Analysis for Documents Clustering(2015)
- Video Retrieval Based on Latent Semantic Analysis(2007)
- → How Does Latent Semantic Analysis Work? A Visualisation Approach(2014)1 cited