In order to promote the dissemination of research results and to help advance the general state of the art in speech recognition, a public domain library of plug-compatible subroutines, modules, and programs has been created. This paper describes the Carnegie-Mellon Portable Speech Library (CMPSL). CMPSL provides algorithms written in C that can be used to quickly prototype state-of-the-art speech recognition systems that are useful in their ability to perform the speech recognition task while also providing a basis from which to pursue further research. CMPSL's chief contributions are to make available recent advances in speech recognition at Carnegie-Mellon in the context of Lee's large-vocabulary, speaker-independent recognition system, SPHINX [K.-F. Lee and H.-W. Hon, Proc. IEEE ICASSP-88, 123–126 (1988)], and to suggest a framework within which speech researchers can make the results of their work available to other members of the automatic speech recognition community. The scope of CMPSL includes digital signal processing, training, recognition, and evaluation algorithms. [Work supported by DARPA.]