1993 benchmark tests for the ARPA spoken language program
HLT '94 Proceedings of the workshop on Human Language Technology
A new paradigm for speaker-independent training
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Speaker normalization on conversational telephone speech
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
A parametric approach to vocal tract length normalization
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
A study of speech recognition for children and the elderly
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Speaker normalization using efficient frequency warping procedures
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Improved methods for vocal tract normalization
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Acoustic variability and automatic recognition of children's speech
Speech Communication
Towards age-independent acoustic modeling
Speech Communication
A review of ASR technologies for children's speech
Proceedings of the 2nd Workshop on Child, Computer and Interaction
An automatic transcription system of hearings in Italian courtrooms
Proceedings of the 2nd ACM workshop on Multimedia in forensics, security and intelligence
EURASIP Journal on Audio, Speech, and Music Processing - Special issue on atypical speech
Hi-index | 0.00 |
In this paper, speaker adaptive acoustic modeling is investigated by using a novel method for speaker normalization and a well known vocal tract length normalization method. With the novel normalization method, acoustic observations of training and testing speakers are mapped into a normalized acoustic space through speaker-specific transformations with the aim of reducing inter-speaker acoustic variability. For each speaker, an affine transformation is estimated with the goal of reducing the mismatch between the acoustic data of the speaker and a set of target hidden Markov models. This transformation is estimated through constrained maximum likelihood linear regression and then applied to map the acoustic observations of the speaker into the normalized acoustic space. Recognition experiments made use of two corpora, the first one consisting of adults' speech, the second one consisting of children's speech. Performing training and recognition with normalized data resulted in a consistent reduction of the word error rate with respect to the baseline systems trained on unnormalized data. In addition, the novel method always performed better than the reference vocal tract length normalization method adopted in this work. When unsupervised static speaker adaptation was applied in combination with each of the two speaker normalization methods, a different behavior was observed on the two corpora: in one case performance became very similar while in the other case the difference remained significant.