With the availability of large data, ASRs perform well on native English but poorly for non-native English data.
Training nonnative ASRs or adapting a native English ASR is often limited by the availability of data, particularly for low resource scenarios. A typical HMM-DNN based ASR decoding requires pseudo-likelihood of states given an acoustic observation, which changes significantly from native to non-native speech due to accent variation.
In order to improve the performance of a native English ASR on non-native English data, we, in this work, propose a DNN-based pseudo-likelihood correction (PLC) technique, in which a non-native pseudo-likelihood vector is mapped to match its native counterpart. Instead of correcting all elements of a non-native pseudo-likelihood vector, a loss function is proposed to correct only top few of them.
Experiments with one native and multiple Indian English corpora show an improvement of WER by ∼12% and ∼5% using the proposed PLC technique over unadapted and adapted native English ASR respectively, when recognition is performed on an Indian English corpus different from that used for both PLC and adaptation. Experiments with upto 2 hours of parallel native and non-native English data reveal that, PLC performs better than adaptation for all unseen cases considered.