Dynamic speech sharpening
View Patent ↗An enhanced system for speech interpretation is provided. The system may include receiving a user verbalization and generating one or more preliminary interpretations of the verbalization by identifying one or more phonemes in the verbalization. An acoustic grammar may be used to map the phonemes to syllables or words, and the acoustic grammar may include one or more linking elements to reduce a search space associated with the grammar. The preliminary interpretations may be subject to various post-processing techniques to sharpen accuracy of the preliminary interpretation. A heuristic model may assign weights to various parameters based on a context, a user profile, or other domain knowledge. A probable interpretation may be identified based on a confidence score for each of a set of candidate interpretations generated by the heuristic model. The model may be augmented or updated based on various information associated with the interpretation of the verbalization.
1. A method for reducing a search space for a recognition grammar used when interpreting natural language speech utterances, the method comprising:
creating a phonemic representation of acoustic elements associated with an acoustic speech model, the acoustic elements including at least an unstressed central vowel and plurality of phonemic elements;
representing syllables associated with the acoustic speech model using the phonemic representation, each of the represented syllables including a series of acoustic elements;
constructing, via an electronic device, an acoustic grammar that contains transitions between the acoustic elements of the represented syllables, the transitions constrained according to phonotactic rules of the acoustic speech model; and
using the unstressed central vowel as a linking element between sequential phonemic elements contained in the constructed acoustic grammar.
2. The method of claim 1 , the series of acoustic elements defining an onset, a nucleus, and a coda for a given one of the represented syllables.
3. The method of claim 1 , the unstressed central vowel including a schwa acoustic element.
4. A system for reducing a search space for a recognition grammar used when interpreting natural language speech utterances, the system comprising:
at least one input device that receives an utterance from a user and generates an electronic signal corresponding to the utterance; and
a speech interpretation engine that receives the electronic signal corresponding to the utterance, the speech interpretation engine operable to:
create a phonemic representation of acoustic elements associated with an acoustic speech model, the acoustic elements including at least an unstressed central vowel and plurality of phonemic elements;
represent syllables associated with the acoustic speech model using the phonemic representation, each of the represented syllables including a series of acoustic elements;
construct an acoustic grammar that contains transitions between the acoustic elements of the represented syllables, the transitions constrained according to phonotactic rules of the acoustic speech model; and
use the unstressed central vowel as a linking element between sequential phonemic elements contained in the constructed acoustic grammar.
5. The system of claim 4 , the series of acoustic elements defining an onset, a nucleus, and a coda for a given one of the represented syllables.
6. The system of claim 4 , the unstressed central vowel including a schwa acoustic element.