Exploiting Chinese Character Models to Improve Speech Recognition Performance.
Studies have shown that articulatory information helps model speech variability and, consequently, improves speech recognition performance.
These recognition units are compared in terms of vocabulary size, coverage, bigram perplexity and speech recognition performance.
This study proposes a novel model composition method to improve speech recognition performance in time-varying background noise conditions.
To enhance speech recognition performance, a decision tree-based method is incorporated to predict possible errors made by non-native speakers for each generated sentence on the fly.
In extensive test runs, different feature front-ends, network training targets, and network topologies are evaluated in terms of frame-wise regression error and speech recognition performance.
Our findings also suggest that phoneme dedifferentiation may be a neural correlate for difficulty with speech in noise perception, and the binding of bottom-up sensory processing with top-down articulatory predictions substantially impacts speech recognition performance in the elderly.
We used word error rate (WER) to evaluate the speech recognition performance for each method.
In contrast, the power SS-based dereverberation using Equation (9) markedly improved the speech recognition performance.
In Section 6, we analyze our experimental results on adapted mean vectors and speech recognition performance.
Generally, late reverberation mainly degrades speech recognition performance and early reverberation can be ignored.
