Ginisupport vector machines for segmental minimum Bayes risk decoding of continuous speech
Computer Speech and Language
| Hi-index | 0.01 |
Code Breaking is a divide and conquer approach for sequential pattern recognition tasks where we identify weaknesses of an existing system and then use specialized decoders to strengthen the overall system. We study the technique in the context of Automatic Speech Recognition. Using the lattice cutting algorithm, we first analyze lattices generated by a state-of-the-art speech recognizes to spot possible errors in its first-pass hypothesis. We then train specialized decoders for each of these problems and apply them to refine the first-pass hypothesis. We study the use of Support Vector Machines (SVMs) as discriminative models over each of these problems. The estimation of a posterior distribution over hypothesis in these regions of acoustic confusion is posed as a logistic regression problem. GiniSVMs, a variant of SVMs, can be used as an approximation technique to estimate the parameters of the logistic regression problem. We first validate our approach on a small vocabulary recognition task, namely, alphadigits. We show that the use of GiniSVMs can substantially improve the performance of a well trained MMI-HMM system. We also find that it is possible to derive reliable confidence scores over the GiniSVM hypotheses and that these can be used to good effect in hypothesis combination. We will then analyze lattice cutting in terms of its ability to reliably identify, and provide good alternatives for incorrectly hypothesized words in the Czech MALACH domain, a large vocabulary task. We describe a procedure to train and apply SVMs to strengthen the first pass system, resulting in small but statistically significant recognition improvements. We conclude with a discussion of methods including clustering for obtaining further improvements on large vocabulary tasks.