Name
Abstract | ||
|---|---|---|
Several methods have been proposed recently for modeling posterior representations derived from local classifiers [1, 2]. In recent work, Sainath et al. have proposed the use of a tied-mixture-based posterior modeling approach [3] to enhance exemplar-based posterior representations for phone recognition tasks. In this work, we conduct a detailed evaluation to determine the effectiveness of this technique on three representative posterior systems. In addition, we propose and evaluate an alternative discriminative formulation of the posterior modeling objective function that seeks to minimize frame-level errors. In experimental evaluations on the TIMIT corpus, we find that posterior modeling results in relative phone error rate (PER) reductions of between 1.1-5.5 % across the systems tested. In fact, using S-pif-NN [4, 3] posteriors, we are able to achieve a PER of 18.5; to the best of our knowledge, this is the best result reported in the literature to date. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICASSP.2013.6639053 | 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
posterior modeling, TIMIT, phone recognition, tied-mixture smoothing | TIMIT,Pattern recognition,Computer science,Word error rate,Speech recognition,Phone,Artificial intelligence,Gaussian process,Hidden Markov model,Discriminative model | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
8 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rohit Prabhavalkar | 1 | 163 | 22.56 |
| Tara N. Sainath | 2 | 3497 | 232.43 |
| David Nahamoo | 3 | 907 | 452.13 |
| Bhuvana Ramabhadran | 4 | 1779 | 153.83 |
| Dimitri Kanevsky | 5 | 477 | 54.37 |