Wav2Nas: An Exploratory Approach to Nasalance Estimation in Speech

Nasalance, defined as the ratio of nasal energy to total acoustic energy during speech, is an important metric in speech science and clinical phonetics. Measurement of nasalance, how-ever, requires specialized equipment, which has severely limited its widespread applications. In this study, we explored methods of predicting nasalance from speech waveforms. We designed an oral-nasal separation mask with thermal flow sensors to record the airflows from the mouth and nose separately during speech production, alongside a microphone recording speech sounds. Nasalance was calculated from the oral and nasal airflows, and multilayer perceptron (MLP) models were trained to predict nasalance from speech waveforms. We compared Mel-spectrogram, Mel Frequency Cepstral Coefficients (MFCC), and Wav2vec 2.0 features as inputs to MLPs. The results demonstrated that the Wav2vec 2.0-based features have the highest Pearson Product Moment Correlation Coefficient (PPMC) of 0.7459, outperforming both the Mel-spectrogram and MFCC baselines. These findings emphasize the potential of leveraging pre-trained deep learning models such as Wav2vec 2.0 to predict nasalance directly from raw audio data, reducing reliance on expensive instruments and improving diagnostic capabilities in speech pathology. Moreover, this paper under-scores the promise of deep learning methods in advancing clinical assessment and opens up new avenues for applying compu-tational techniques to better understand and treat speech disorders.