Joint discriminative training of multiple speech recognizers

摘要

Adjusting model parameters is described for a speech recognition system that combines recognition outputs from multiple speech recognition processes. Discriminative adjustments are made to model parameters of at least one acoustic model based on a joint discriminative criterion over multiple complementary acoustic models to lower recognition word error rate in the system.

主权项

1. A method of adjusting model parameters in a speech recognition system comprising:
in a speech recognition system executed by computer system that combines recognition outputs from a plurality of parallel speech recognition processes that operate on a given speech input word sequence and produce different competing recognition outputs which are then combined to determine a final recognition output;
wherein the speech recognition processes are complementary so as to produce different recognition errors on a given same speech input; performing a discriminative adjustment process including:
i. selecting at least one acoustic model of the system, andii. adjusting a plurality of model parameters of the selected acoustic model based on a joint discriminative criterion over a plurality of complementary acoustic models to lower combined recognition WER in the system over only independently discriminatively trained recognition systems.