Conversational speech is characterized by rampant pronunciation vari- ations, where accurate pronunciation modeling can lead to high recognition performance.
Enhanced tree clustering with single pronunciation dictionary for conversational speech recognition. Hua Yu, Tanja Schultz. Modeling pronunciation variation ...
We show that accurate pronunciation modeling can be achieved through efficient parameter sharing in the acous- tic model. Combined with a single pronunciation ...
In this paper we present the results for building a grapheme-based speech recogni- tion system for Thai. We experiment with different settings for the initial ...
Enhanced Tree Clustering with Single Pronunciation Dictionary for Conversational Speech Recognition (Hua Yu, Tanja Schultz), In Proceedings of the 8th ...
Enhanced Tree Clustering with Single Pronunciation Dictionary for Conversational Speech Recognition ... International Speech Communication Association (ISCA).
Speech Translation Enhanced Automatic Speech Recognition ... Enhanced Tree Clustering with Single Pronunciation Dictionary for Conversational Speech Recognition
People also ask
What are the most commonly used algorithm for speech recognition?
What is a pronunciation lexicon for speech recognition?
This thesis revisits pronunciation modeling issues and focuses on implicit pronunciation modeling, where it is found that enhanced tree clustering, ...
[4] Hua Yu and Tanja Schultz, “Enhanced tree clustering with single pronunciation dictionary for conversational speech recognition,” in EUROSPEECH 2003 ...
We find that enhanced tree clustering, together with single pronunciation dictionary, improves performance significantly. • Gaussian transition modeling: By ...