Effect of Modeling Glottal Activity Parameters on Zero-Shot Children's ASR

The primary objective of this study is to enhance the recognition performance of zero-shot children's automatic speech recognition (ASR) task. In such a setup, statistical models are trained on adults' speech while the test data is from child speakers. Due to the stark differences in the speech data from adult and children, poorer recognition performances are obtained. To mitigate the ill-effects of acoustic mismatch between the training and the test data, we have first resorted to data augmentation wherein the attributes of adults' training speech were modified in such way that those become acoustically similar to children's speech. Data augmentation helped us build a better baseline ASR system. In order to further enhance the recognition performance, we have studied the impact of concatenating glottal activity parameters with the Mel-frequency cepstral coefficients (MFCC). The explored glottal activity parameters are strength of excitation (SoE), normalized auto-correlation peak strength (NAPS), higher-order statistics (HOS), jitter and shimmer. However, shimmer was found to be unsuitable for the zero-shot children's ASR task. Therefore, only SoE, NAPS, HOS and jitter parameters were included into the training and this, in turn, yielded significantly improved recognition performance. A relative reduction in word error rate by <tex-math notation="LaTeX">$24.5%$</tex-math> over the baseline was obtained on including glottal activity parameters. Similarly, the relative reduction in character error rate was noted to be <tex-math notation="LaTeX">$30%$</tex-math> over the baseline. Finally, in order to further build confidence in the idea of modeling glottal activity parameters, we have extended the study to low-resource children's ASR task employing end-to-end architecture. Even in this case, significant reductions in error rates were noted.