Large Vocabulary Speech Recognition on Parallel Architectures
| Autor: | Patrick Cardinal, Gilles Boulianne, Pierre Dumouchel |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Vocabulary
Acoustics and Ultrasonics Computer science Heuristic (computer science) media_common.quotation_subject Computation Graphics processing unit Parallel computing Vocabulary speech recognition Computer Science::Hardware Architecture Constant (computer programming) Factor (programming language) Scalability Electrical and Electronic Engineering computer computer.programming_language media_common |
| Zdroj: | IEEE Transactions on Audio, Speech, and Language Processing. 21:2290-2300 |
| ISSN: | 1558-7924 1558-7916 |
| DOI: | 10.1109/tasl.2013.2271591 |
| Popis: | The speed of modern processors has remained constant over the last few years but the integration capacity continues to follow Moore's law and thus, to be scalable, applications must be parallelized. The parallelization of the classical Viterbi beam search has been shown to be very difficult on multi-core processor architectures or massively threaded architectures such as Graphics Processing Unit (GPU). The problem with this approach is that active states are scattered in memory and thus, they cannot be efficiently transferred to the processor memory. This problem can be circumvented by using the A* search which uses a heuristic to significantly reduce the number of explored hypotheses. The main advantage of this algorithm is that the processing time is moved from the search in the recognition network to the computation of heuristic costs, which can be designed to take advantage of parallel architectures. Our parallel implementation of the A* decoder on a 4-core processor with a GPU led to a speed-up factor of 6.13 compared to the Viterbi beam search at its maximum capacity and an improvement of 4% absolute in accuracy at real-time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|