Method and system for unsupervised discovery of unigrams in speech recognition systems
AssigneeGenesys Cloud Services, Inc.
InventorsLEV HAIKIN, ARNON MAZZA, EYAL ORBACH, AVRAHAM FAIZAKOF
Life of this patent
Estimating the term…
Loading patent…
AssigneeGenesys Cloud Services, Inc.
InventorsLEV HAIKIN, ARNON MAZZA, EYAL ORBACH, AVRAHAM FAIZAKOF
Estimating the term…
A system and method of automatically discovering unigrams in a speech data element may include receiving a language model that includes a plurality of n-grams, where each n-gram includes one or more unigrams; applying an acoustic machine-learning (ML) model on one or more speech data elements to obtain a character distribution function; applying a greedy decoder on the character distribution function, to predict an initial corpus of unigrams; filtering out one or more unigrams of the initial corpus to obtain a corpus of candidate unigrams, where the candidate unigrams are not included in the language model; analyzing the one or more first speech data elements, to extract at least one n-gram that comprises a candidate unigram; and updating the language model to include the extracted at least one n-gram.
A method of automatically discovering unigrams in a speech data element, by at least one processor, the method comprising:
A system for automatically discovering unigrams in a speech data element, the system comprising:
Dependencies are inferred from the claim text.