Research Using CMUSphinx

CMU Sphinx Toolkit is actively used in speech recognition research. To note some, here is the list of publications it’s worth to mention

Ph.D Theses

MS Reports

Papers and Talks

2009

2008

2007

2006

2005

2004

2003

2002

2001

2000

1999

1998

1997

1996

1995

1994

1993

1992

1991

1990

“Classic” robust papers (pre-1990)

Original description of extended maximum a posteriori probability (EMAP) speaker adaptation:

  • R. M. Stern and M. J. Lasry, “ Dynamic Speaker Adaptation for Feature-Based Isolated Letter Recognition ,” IEEE Trans. on Acoustics, Speech, and Signal Processing 35: 751-763, 1987.

  • M. J. Lasry and R. M. Stern, “A Posteriori Estimation of Correlated Jointly Gaussian Mean Vectors,” IEEE Trans. on Pattern Anal. and Mach. Intel. 6: 530-535, 1984.

  • M. J. Lasry and R. M. Stern, “Unsupervised Adaptation to New Speakers in Feature-Based Letter Recognition,” Proc. IEEE Conf. on Acoustics, Speech, and Sig. Proc., San Diego, California, May, 1984.

  • R. M. Stern and M. J. Lasry (1983). “Dynamic Speaker Adaptation for Isolated Letter Recognition Using MAP Estimation,” Proc. IEEE Conf. on Acoustics, Speech, and Sig. Proc., Boston, Massachusetts, May, 1983.

External publications