Parallel robust speech recognition

Más información sobre el libro

This book focuses on automatic speech recognition in clean and noisy or reverberant environments. Therefore, a parallel speech recognition system using TemporRAl Patterns (TRAPs) is described. The TRAPs are computed over a rather long temporal context for each critical band in the speech signal's spectrum. Then, the features of the different bands are combined. Thus, recognition only in certain bands is possible. This is beneficial if noise occurs only in parts of the spectrum. In this manner multiple speech recognizers are trained which analyze disjoint bands of the frequency domain. Each of the speech recognizers extracts a different word chain from the audio signal. In the end the word chains are merged to form a single recognition result. As shown on different data sets the parallel speech recognition system is much more robust to noise and reverberation than the state-of-the-art baseline system. The book explains all relevant parts of speech recognition and is, therefore, also suitable for readers who are not familiar with the subject.