Impact of pronunciation variation in speech recognition

Mapping the acoustic sequence to lexical units is an issue in speech recognition. To address this, multiple pronunciations are included in the pronunciation dictionary. However, the number of lexical variants required for improved recognition is not clear as pronunciation varies significantly across dialects. This can lead to poor recognition sometimes. In this paper, a systematic study is carried out to observe the effect of pronunciation variation on recognition accuracy. In particular, a data-driven approach is employed to observe pronunciation variation at syllable level. The acoustic cue about the syllable boundaries are obtained from Group Delay (GD) segmentation. The preliminary experiments carried out for TIMIT corpus reveal that the use of prominent pronunciation variants for each dialect leads to an improved recognition performance.