The Speaker and Content Adaptation in Radiology Information System

Abstract:

After attempts on applying the speech recognition system to radiology information system (RIS), we focus on the implementation of introducing adaptation technology to the system. To be consistent with the practical application of RIS, we intend to solve the problems on how to adapt and add new content related to the RIS report to the old model. This paper describes an acoustic model-based speaker and content adaptation scheme using a synthetic method which introduces a simplified maximum likelihood linear regression (MLLR) module to the incremental maximum a posteriori (MAP) processing. We designed and tested a procedure using our own adaptation data collected from hospital diagnostic reports. Finally, the efficiency of this method is supported by experimental results.

• Periodical: Applied Mechanics and Materials (Volumes 195-196)
• Pages: 859-863
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.195-196.859
• Online since: August 2012
• Authors: Fei Ran Wu, Xin Xin Wang, Zhi Qian Ye
• Keywords: Acoustic Model Adaptation, Content Adaptation, Map, MLLR, Speaker Adaptation

References

[1] Xinxin Wang, Feiran Wu, Zhiqian Ye, The Application of Speech Recognition in Radiology Information System, Biomedical Engineering and Computer Science (ICBECS), pp.1-3, Apr. (2010).

[2] Douglas A. Reynolds, Thomas F. Quatieri, and Robert B. Dunn, Speaker Verification Using Adapted Gaussian Mixture Models, Digital Signal Processing, vol. 10, pp.19-41, (2000).

DOI: 10.1006/dspr.1999.0361

[3] P.C. Woodland, Speaker Adaptation for Continuous Density HMMs: A Review, ISCA Tutorial and Research Workshop (ITRW) on Adaptation Methods for Speech Recognition, pp.11-19, Aug. (2001).

[4] Jean-Luc Gauvain, Chin-Hui Lee, MAP Estimation of Continuous Density HMM: Theory and Applications, DARPA Sp. & Nat. Lang. Workshop, pp.185-190, Feb. (1992).

[5] Arindam Mandal, Mari Ostendorf, Andreas Stolcke, Improving Robustness of MLLR Adaptation with Speaker-Clustered Regression Class Trees, Computer Speech & Language, vol. 23, pp.176-199, Apr. (2009).

DOI: 10.1016/j.csl.2008.05.004

[6] C. J. Leggetter, P. C. Woodland, Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models, Computer Speech and Language, vol. 9, pp.171-185, (1995).

DOI: 10.1006/csla.1995.0010

[7] Brian Mak, Roger Hsiao, Kernel Eigenspace-based MLLR Adaptation, Audio, Speech, and Language Processing, pp.784-795, Mar. (2007).

DOI: 10.1109/tasl.2006.885941

[8] Hongcai Feng, Zhengding Lu, Integration Incremental Adaption Method Research Based on MAP & MLLR, Computer Engineering, vol. 31, No. 5, pp.4-7, Mar. (2005).

[9] R. Bakis, Continuous Speech Word Recognition via Centisecond Acoustic States, 91st Meeting of the Acoustical Society of America, Apr. (1976).

DOI: 10.1121/1.2003011