Beth A. Carlson

Learn More
Speech recognizers trained with quiet wide-band speech degrade dramatically with high-pass, low-pass, and notch filtering, with noise, and with interruptions of the speech input. A new and simple approach to compensate for these degradations is presented which uses mel-filter-bank (MFB) magnitudes as input features and missing feature theory to dynamically(More)
Classical speaker and language recognition techniques can be applied to the classiication of unknown utterances by computing the likelihoods of the utterances given a set of well trained target models. This paper addresses the problem of grouping unknown utterances when no information is available regarding the speaker or language classes or even the total(More)
As the need for neonatal intensive care units (NICU) continues to increase, a growing body of evidence on the developmentally appropriate healing environment for neonates suggests that changes are needed in NICU design. The private room NICU model is emerging as an alternative to large multi-bed wards; however, some have suggested that such a radical design(More)
Benign soft tissue lesions of the mouth can be removed using the CO2 laser. This type of laser surgery is faster and offers less postoperative complication as compared with conventional surgery and electrosurgery. Presently, the CO2 laser can be used for intraoral biopsy of benign masses, gingivectomies, and frenectomies.
Speech recognizers trained with quiet wide-band speech degrade dramatically with high-pass, low-pass, and notch filtering, with noise, and with interruptions of the speech input. A new and simple approach to compensate for these degradations is presented which uses mel-filter-bank (MFB) magnitudes as input features and missing feature theory to dynamically(More)
35 T     operates worldwide in a variety of international environments that require language translation. Translators who can interpret military terminology are a scarce commodity in countries such as the Republic of Korea (R.O.K.), and U.S. military leaders there support the development of bilingual machine translation. Although U.S.(More)