Exploring Dynamic Parameters for Vietnamese Gender-Independent ASR
This work addresses gender bias in Vietnamese ASR, but it is incremental as it builds on existing feature extraction methods.
The authors tackled the problem of improving Vietnamese automatic speech recognition by introducing dynamic parameters based on spectral subband centroid frequencies to capture speech transitions and tonal information, which reduced word error rates and enhanced gender independence compared to standard MFCCs.
The dynamic characteristics of speech signal provides temporal information and play an important role in enhancing Automatic Speech Recognition (ASR). In this work, we characterized the acoustic transitions in a ratio plane of Spectral Subband Centroid Frequencies (SSCFs) using polar parameters to capture the dynamic characteristics of the speech and minimize spectral variation. These dynamic parameters were combined with Mel-Frequency Cepstral Coefficients (MFCCs) in Vietnamese ASR to capture more detailed spectral information. The SSCF0 was used as a pseudo-feature for the fundamental frequency (F0) to describe the tonal information robustly. The findings showed that the proposed parameters significantly reduce word error rates and exhibit greater gender independence than the baseline MFCCs.