Language identification and accent variation detection in spoken language recordings

We develop a model for identifying languages and accents in audio recordings. Our Hierarchical-Sequential Nodule Model (HSNM) incorporates both short-distance features (which capture simple linguistic distinctions, e.g. phoneme inventories) and longdistance features (which detect long-distance suprasegmental patterns, e.g. tone and prosody) which help a… CONTINUE READING