System and method for adapting automatic speech recognition pronunciation by acoustic model restructuring

摘要

Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for recognizing speech by adapting automatic speech recognition pronunciation by acoustic model restructuring. The method identifies an acoustic model and a matching pronouncing dictionary trained on typical native speech in a target dialect. The method collects speech from a new speaker resulting in collected speech and transcribes the collected speech to generate a lattice of plausible phonemes. Then the method creates a custom speech model for representing each phoneme used in the pronouncing dictionary by a weighted sum of acoustic models for all the plausible phonemes, wherein the pronouncing dictionary does not change, but the model of the acoustic space for each phoneme in the dictionary becomes a weighted sum of the acoustic models of phonemes of the typical native speech. Finally the method includes recognizing via a processor additional speech from the target speaker using the custom speech model.

主权项

1. A method comprising:
obtaining, by a system comprising a processor, information associated with an acoustic model, wherein the acoustic model is trained on native speech in a target dialect; and updating, by the system, the information associated with the acoustic model to replace a first phoneme in the acoustic model with a second phoneme, wherein the second phoneme comprises a sum of values associated with plausible phonemes in a lattice of plausible phonemes associated with a type of speaker.