System and method of using acoustic models for automatic speech recognition which distinguish pre- and post-vocalic consonants

1. The method of improving output from a speech recognizer by training models, the method comprising;

receiving a speech signal;

defining at least one syllable boundary position for a word in the speech signal;

based on the at least one syllable boundary position, generating for each consonant in a syllable of the word one of a pre-vocalic position label and a post-vocalic position label;

expanding a portion of a consonant phoneme inventory associated with the word to include the one of the pre-vocalic position label and the post-vocalic position label to yield an expanded consonant phoneme inventory;

reformulating a lexicon to reflect the expanded consonant phoneme inventory and yield a reformulated lexicon; and

training a language model for an automated speech recognition system based on the reformulated lexicon.

2. The method of claim 1 , wherein the at least one syllable boundary position uses the one of the pre-vocalic position label and the post-vocalic position label.

3. The method of claim 1 , wherein the at least one syllable boundary position reflects acoustic changes based on the post-vocalic consonant position label relative to the vowels within the syllable.

4. The method of claim 1 , wherein the at least one syllable boundary position reflects acoustic changes based on the pre-vocalic consonant position label relative to the vowels within the syllable.

5. The method of claim 1 , wherein at least one training model is built by using hidden Markov models, support vector machines or neural networks.

6. The method of claim 1 , wherein the expanded consonant phoneme inventory creates two labels for each consonant to be used by the lexicon.

7. A non-transitory computer-readable medium storing instructions for controlling a computing device to train a language model, the instructions comprising:

receiving a speech signal;

defining at least one syllable boundary position for a word in the speech signal;

based on the at least one syllable boundary position, generating for each consonant in a syllable of the word one of a pre-vocalic position label and a post-vocalic position label;

expanding a portion the consonant phoneme inventory associated with the word to include the one of the pre-vocalic position label and the post-vocalic position label to yield an expanded consonant phoneme inventory;

reformulating a lexicon to reflect the expanded consonant phoneme inventory and yield a reformulated lexicon; and

training language model for an automated speech recognition system based on the reformulated lexicon.

8. The non-transitory computer-readable medium of claim 1 , wherein the at least one syllable boundary position uses the one of the pre-vocalic position label and the post-vocalic position label.

9. The non-transitory computer-readable medium of claim 1 , wherein the at least one syllable boundary position reflects acoustic changes based on the post-vocalic consonant position label relative to the vowels within the syllable.

10. The non-transitory computer-readable medium of claim 1 , wherein the at least one syllable boundary position reflects acoustic changes based on the pre-vocalic consonant position label relative to the vowels within the syllable.

11. The non-transitory computer-readable medium of claim 1 , wherein at least one training model is built by using hidden Markov models, support vector machines or neural networks.

12. The non-transitory computer-readable medium of claim 1 , wherein the expanded consonant phoneme inventory creates two labels for each consonant to be used by the lexicon.

13. A system for improving output from a speech recognizer by training models, the system comprising;

a processor;

a first module configured to cause the processor to receive a speech signal;

a second module configured to cause the processor to define at least one syllable boundary position for a word in the speech signal;

a third module to cause the processor configured to generate for each consonant in a syllable of the word a pre-vocalic position label and a post-vocalic position label based on the at least one syllable boundary position;

a fourth module configured to cause the processor to expand a portion of a consonant phoneme inventory associated with the word to include the one of the pre-vocalic position label and the post-vocalic position label to yield an expanded consonant phoneme inventory;

a fifth module configured to cause the processor to reformulate a lexicon to reflect an expanded consonant phoneme inventory and yield a reformulated lexicon; and

a sixth module configured cause the processor to train a language model for an automated speech recognition system based on the reformulated lexicon.

14. The system of claim 1 , wherein the at least one syllable boundary position uses the one of the pre-vocalic position label and the post-vocalic position label.

15. The system of claim 1 , wherein the at least one syllable boundary position reflects acoustic changes based on the post-vocalic consonant position label relative to the vowels within the syllable.

16. The system of claim 1 , wherein the at least one syllable boundary position reflects acoustic changes based on the pre-vocalic consonant position label relative to the vowels within the syllable.

17. The system of claim 1 , wherein at least one training model is built by using hidden Markov models, support vector machines or neural networks.

18. The system of claim 1 , wherein the expanded consonant phoneme inventory creates two labels for each consonant to be used by the lexicon.