In standard template-based Automatic Speech Recognition
Recently, the use of phoneme class-conditional probabilities as features (posterior features) for template-based ASR has been proposed. These features have been found to generalize well to unseen data and yield better systems than standard spectral-based features. In this paper, motivated by the hig...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Text |
| Language: | English |
| Subjects: | |
| Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.1093 http://publications.idiap.ch/downloads/papers/2012/Soldo_INTERSPEECH_2012.pdf |
| Summary: | Recently, the use of phoneme class-conditional probabilities as features (posterior features) for template-based ASR has been proposed. These features have been found to generalize well to unseen data and yield better systems than standard spectral-based features. In this paper, motivated by the high quality of current text-to-speech systems and the robustness of posterior features toward undesired variability, we investigate the use of synthetic speech to generate reference templates. The use of synthetic speech in template-based ASR not only allows to ad-dress the issue of in-domain data collection but also expansion of vocabulary. Using 75- and 600-word task-independent and speaker-independent setup on Phonebook database, we investi-gate different synthetic voices produced by the Festival HTS-based synthesizer trained on CMU ARCTIC databases. Our study shows that synthetic speech templates can yield perfor-mance comparable to the natural speech templates, especially with synthetic voices that have high intelligibility. |
|---|