Proceedings ArticleDOI
PCA-PMC: a novel use of a priori knowledge for fast parallel model combination
Ruhi Sarikaya,John H. L. Hansen +1 more
- Vol. 2, pp 1113-1116
Reads0
Chats0
TLDR
The novel approach here is to encode the clean models using principal component analysis (PCA) and pre-compute the prototype vectors and matrices for the means and covariances in the linear spectral-domain using rectangular DCT and inverse DCT matrices.Abstract:
This paper describes an algorithm to reduce computational complexity of the parallel model combination (PMC) method for robust speech recognition while retaining the same level of performance. Although, PMC is effective in composing a noise corrupted acoustic model from clean speech and noise models, the intense computational complexity limits its use in real-time use. The novel approach here is to encode the clean models using principal component analysis (PCA) and pre-compute the prototype vectors and matrices for the means and covariances in the linear spectral-domain using rectangular DCT and inverse DCT matrices. Therefore, transformation into the linear spectral domain is reduced to finding the projection of each vector in the eigen space of means and covariances followed by a linear combination of vectors and matrices obtained from the projections. Furthermore, the eigen space allows a better trade-off for reducing computational complexity versus accuracy. The computational savings are demonstrated both analytically and through experimental evaluations. Experiments using context independent phone recognition with TIMIT data shows that the new PMC framework can outperforms the baseline method by a factor of 1.9 with the same level of accuracy.read more
Citations
More filters
Journal ArticleDOI
Cepstrum-domain acoustic feature compensation based on decomposition of speech and noise for ASR in noisy environments
Hong Kook Kim,Richard Rose +1 more
TL;DR: In this paper, a set of acoustic feature pre-processing techniques that are applied to improving automatic speech recognition (ASR) performance on noisy speech recognition tasks are presented. But the main contribution of this paper is an approach for cepstrum-domain feature compensation in ASR which is motivated by techniques for decomposing speech and noise that were originally developed for noisy speech enhancement.
Proceedings Article
Using observation uncertainty in HMM decoding.
Jon A. Arrowood,Mark A. Clements +1 more
TL;DR: An approach that reformulates the model combination technique to update the each observation instead of the model, which compares favorably with PMC in unchanging noise environments, but has significant benefits in changing noise.
Proceedings ArticleDOI
University of Colorado dialog systems for travel and navigation
Bryan L. Pellom,Wayne H. Ward,John H. L. Hansen,Ronald A. Cole,Kadri Hacioglu,Jianping Zhang,X. Yu,Sameer Pradhan +7 more
TL;DR: Recent improvements in the development of the University of Colorado "CU Communicator" and "CU-Move" spoken dialog systems are presented.
Patent
Model weighting, selection and hypotheses combination for automatic speech recognition and machine translation
Suleyman S. Kozat,Ruhi Sarikaya +1 more
TL;DR: A model combiner is configured to assign probabilities to each model output and assign weights to the outputs of the plurality of models based on the probabilities to provide a best performing model for the context of the utterance as mentioned in this paper.
Proceedings Article
High performance digit recognition in real car environments.
TL;DR: This paper considers the problem of robust digit recognition in real car environments using newlycollected CU-Move database and uses array processing, enhancement and noise adaptation techniques as an integrated solution.
References
More filters
Book
Principal Component Analysis
TL;DR: In this article, the authors present a graphical representation of data using Principal Component Analysis (PCA) for time series and other non-independent data, as well as a generalization and adaptation of principal component analysis.
Journal ArticleDOI
Constrained iterative speech enhancement with application to speech recognition
TL;DR: The algorithms are evaluated with respect to improving automatic recognition of speech in the presence of additive noise and shown to outperform other enhancement methods in this application.
Journal ArticleDOI
Cepstral parameter compensation for HMM recognition in noise
Mark J. F. Gales,Steve Young +1 more
TL;DR: The PMC technique is based on parallel model combination in which the parameters of corresponding pairs of speech and noise states are combined to yield a set of compensated parameters, which improves on earlier cepstral mean compensation methods in that it also adapts the variances and as a result can deal with much lower SNRs.
Journal ArticleDOI
The short-time modified coherence representation and noisy speech recognition
D. Mansour,Biing-Hwang Juang +1 more
TL;DR: Initial implementation of the SMC in a speaker-dependent isolated word recognizer shows an improvement in recognition accuracy equivalent to an increase in input SNR of approximately 13 dB, as compared to the LPC recognizer.
Proceedings ArticleDOI
A fast and flexible implementation of parallel model combination
Mark J. F. Gales,Steve Young +1 more
TL;DR: This paper introduces an alternative method that can compensate all the parameters of the recognition system, whilst reducing the computational load of this task, and offers an additional degree of flexibility, as it allows the number of components to be chosen and optimised using standard iterative techniques.