no code implementations • 13 Jul 2019 • Nooshin Maghsoodi, Hossein Sameti, Hossein Zeinali, Themos~Stafylakis
By making use of the natural partition of input features into digits, we train digit-specific i-vector extractors on top of each HMM and we extract well-localized i-vectors, each modelling merely the phonetic content corresponding to a single digit.