Preliminary Study on SSCF-derived Polar Coordinate for ASR

Sotheara Leang (1, 2) , Eric Castelli (2) , Dominique Vaufreydaz (2) , Sethserey Sam (1)

1 CADT - Cambodia Academy of Digital Technology
2 M-PSI - Multimodal Perception and Sociable Interaction

The transition angles are defined to describe the vowel-to-vowel transitions in the acoustic space of the Spectral Subband Centroids, and the findings show that they are similar among speakers and speaking rates. In this paper, we propose to investigate the usage of polar coordinates in favor of angles to describe a speech signal by characterizing its acoustic trajectory and using them in Automatic Speech Recognition. According to the experimental results evaluated on the BRAF100 dataset, the polar coordinates achieved significantly higher accuracy than the angles in the mixed and cross-gender speech recognitions, demonstrating that these representations are superior at defining the acoustic trajectory of the speech signal. Furthermore, the accuracy was significantly improved when they were utilized with their first and second-order derivatives (∆, ∆∆), especially in cross-female recognition. However, the results showed they were not much more gender-independent than the conventional Mel-frequency Cepstral Coefficients (MFCCs).

Mots clés: Automatic Speech Recognition; Spectral Subband Centroid Frequency; Speaker Normalization

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Traitement du signal et de l'image [eess.SP]

Sotheara Leang, Eric Castelli, Dominique Vaufreydaz, Sethserey Sam. Preliminary Study on SSCF-derived Polar Coordinate for ASR. ACET 2022, Dec 2022, Phnom Penh, Cambodia. ⟨hal-03871289⟩