Title :
Phonetic subspace adaptation for automatic speech recognition
Author :
Ghalehjegh, Sina Hamidi ; Rose, Richard C.
Author_Institution :
Electr. & Comput. Eng. Dept., McGill Univ., Montreal, QC, Canada
Abstract :
An approach is proposed for adapting subspace projection vectors in the subspace Gaussian mixturemodel (SGMM) [1]. Subword models in the SGMM are composed of states, each of which are parametrized using a small number of subspace projection vectors. It is shown here that these projection vectors provide a compact and well-behaved characterization of phonetic information in speech. A regression based subspace vector adaptation approach is proposed for adapting these parameters. The performance of this approach is evaluated for unsupervised speaker adaptation on two large vocabulary speech corpora.
Keywords :
Gaussian processes; speech recognition; vectors; SGMM; automatic speech recognition; phonetic information; phonetic subspace adaptation; regression based subspace vector adaptation approach; subspace Gaussian mixture model; subspace projection vectors; subword models; unsupervised speaker adaptation; vocabulary speech corpora; Acoustics; Adaptation models; Hidden Markov models; Speech; Speech recognition; Training; Vectors; Phonetic Subspace; Speaker Adaptation;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
DOI :
10.1109/ICASSP.2013.6639210
