Speech recognition thesis 2012

speech recognition system

This thesis addresses both of these limitations. Moreno, P. CS Dept. However, these combination methods can be computationally expensive, as data is processed by multiple systems. This limits the allowed forms of diversities that the ensemble can have.

Liu, F. The proposed method maps the state cluster posteriors from the teachers' sets of state clusters to that of the student. When performing recognition, these ensembles can be combined at the hypothesis and frame levels.

The proposals in this thesis are assessed on four ASR tasks. Balakrishnan Abstract: The goal of the proposed study is robust speech feature prediction using mel-LPC to improve the performance of speech recognition in adverse conditions and compares the performance with those standard LPC and MFCC through English dictation system with 14, isolated words and 9, connected words.

Gerazov, B. However, many of these have computational costs that scale linearly with the ensemble size. Cirilus and Methodius, Skopje.

Speech recognition algorithm

The combined ensemble performance depends on both the accuracy of the individual members of the ensemble, as well as the diversity between their behaviours. This thesis addresses both of these limitations. The experiments suggest that significant combination gains can be obtained by combining systems with different acoustic models, sets of state clusters, and sets of sub-word units. The experiments suggest that by using these sequence-level methods, a student can learn to emulate the ensemble better. Ensembles of these systems can exhibit highly diverse behaviours, because the systems are not biased toward any cross-entropy forced alignments. In standard teacher-student learning, information about the per-frame state cluster posteriors is propagated from the teacher ensemble to the student, to train the student to emulate the ensemble. Computer Speech and Language Google Scholar Carnegie Mellon University Google Scholar

One method to address this is teacher-student learning, which compresses the ensemble into a single student.

Rated 6/10 based on 51 review
Research on Speech Recognition Technology and Its Application