Difference between revisions of "Pereira and Riley, 1997"
(Created page with ''''Speech Recognition by Composition of Weighted Finite Automata''' is a [[Category::Paper|paper]] by Fernando Pereira and Michael Riley available [http://www.cis.upenn.edu/~pere…') |
|||
| Line 2: | Line 2: | ||
==Citation== | ==Citation== | ||
| − | Pereira and Riley. Speech Recognition by Composition of Weighted Finite Automata. In Finite-State Language Processing, pages: 431-453. | + | Pereira and Riley. Speech Recognition by Composition of Weighted Finite Automata. In Finite-State Language Processing, pages: 431-453, 1997. |
==Summary== | ==Summary== | ||
| + | They created a speech recognition system by using four finite state automata to model the entire pipeline of sound to phonemes to words. Since each step was fairly well understood, they wanted to use their knowledge in each step to improve the efficacy of the entire process. Unlike previous attempts, they didn't want to have to prune too early and leave out potentially fruitful matches. By using the composition of the various automata, they were able to search without pruning for some easier tasks. | ||
| + | |||
| + | ==Work== | ||
| + | They began by creating a speech recognition system using the composition of three finite state automata: a transducer A that converted acoustic signals to phone sequences, a transducer D that converts phone sequences to word sequences, and a finite state acceptor M that models a 5-gram model. | ||
| + | |||
| + | One of the immediate problems was that their context independent phone model A | ||
Revision as of 22:24, 2 November 2011
Speech Recognition by Composition of Weighted Finite Automata is a paper by Fernando Pereira and Michael Riley available online.
Citation
Pereira and Riley. Speech Recognition by Composition of Weighted Finite Automata. In Finite-State Language Processing, pages: 431-453, 1997.
Summary
They created a speech recognition system by using four finite state automata to model the entire pipeline of sound to phonemes to words. Since each step was fairly well understood, they wanted to use their knowledge in each step to improve the efficacy of the entire process. Unlike previous attempts, they didn't want to have to prune too early and leave out potentially fruitful matches. By using the composition of the various automata, they were able to search without pruning for some easier tasks.
Work
They began by creating a speech recognition system using the composition of three finite state automata: a transducer A that converted acoustic signals to phone sequences, a transducer D that converts phone sequences to word sequences, and a finite state acceptor M that models a 5-gram model.
One of the immediate problems was that their context independent phone model A
