Discriminative training for speech recognition is compensating for statistical dependence in the HMM framework
| Autor: | Steven Wegmann, Daniel Gillick, Larry Gillick |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Computer science
business.industry Speech recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Word error rate Pattern recognition Mutual information ComputingMethodologies_PATTERNRECOGNITION Discriminative model Conditional independence Computer Science::Sound Phone Artificial intelligence business Hidden Markov model |
| Zdroj: | ICASSP |
| DOI: | 10.1109/icassp.2012.6288979 |
| Popis: | The parameters of the standard Hidden Markov Model framework for speech recognition are typically trained via Maximum Likelihood. However, better recognition performance is achievable with discriminative training criteria like Maximum Mutual Information or Minimum Phone Error. While it is generally accepted that these discriminative criteria are better suited to minimizing Word Error Rate, there is very little qualitative intuition for how the improvements are achieved. Through a series of “resampling” experiments, we show that discriminative training (MPE in particular) appears to be compensating for a specific incorrect assumption of the HMM—that speech frames are conditionally independent. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|