Abstract: A multipart handle for coupling to a magnifying lens is provided. In a preferred embodiment, the multipart handle comprises a head member comprising a first end coupleable to the lens and a second end having a cavity formed therein; a body section having a channel for receiving a material member, wherein the body section comprises a first body member having a first end and a second end and a second body member having a first end and a second end; wherein the first end of the first body member is securable within the cavity of the head member and the first end of the second body member is securable within the cavity of the head member; wherein the second end of the first body member is press-fitted to the second end of the second body member; wherein the securing together of the respective second ends of the body members maintains the material member in the channel. In a particular embodiment, a combination magnifying lens and a personalizable handle for coupling to the magnifying lens is also provided.

Abstract: A digital phosphor spectrum analyzer (DPSA) uses a fast rasterization and decay process to emulate the look and feel of an analog phosphor display while improving the ratio of waveform acquisition to non-acquisition time. Multiple acquisitions of complex digital data for an input signal being analyzed across a frequency span are accumulated in a raster memory at a waveform update rate to produce a composite waveform. A decay function is applied to the composite waveform to produce a display waveform. The display waveform is viewed on a display device at a display update rate, resulting in the ability to see otherwise unobservable frequency characteristics of the input signal.

Abstract: A digital speech enabled middleware module is disclosed that facilitates interaction between a large number of client devices and network-based automatic speech recognition (ASR) resources. The module buffers feature vectors associated with speech received from the client devices when the number of client devices is greater than the available ASR resources. When an ASR decoder becomes available, the module transmits the feature vectors to the ASR decoder and a recognition result is returned.

Abstract: The invention provides devices and methods to decompose the noise-corrupted speech into an estimate for the clean speech component and an estimate for a noise component in a domain wherein the two components additively interact. In one implementation, the noise-corrupted speech signal is transformed into the cepstrum domain and combined with a cepstrum of a nonlinear gain function representing noise to obtain an estimate of the clean speech component in the cepstrum domain. In another implementation, the clean speech component is decomposed from the background noise component and channel distortion in the noisy speech cepstrum domain.

Abstract: Frequency warping approaches to speaker normalization have been proposed and evaluated on various speech recognition tasks. In all cases, frequency warping was found to significantly improve recognition performance by reducing the mismatch between test utterances presented to the recognizer and the speaker independent HMM model. This invention relates to a procedure which compensates utterances by simultaneously scaling the frequency axis and reshaping the spectral energy contour. This procedure is shown to reduce the error rate in a telephone based connected digit recognition task by 30%.

Abstract: Devices and methods for speech recognition enable simultaneous word hypothesis detection and verification in a one-pass procedure that provides for different segmentations of the speech input. A confidence measure of a target hypothesis for a known word is determined according to a recursion formula that operates on parameters of a target models and alternate models of known words, a language model and a lexicon, and feature vectors of the speech input in a likelihood ratio decoder. The confidence measure is processed to determine an accept/reject signal for the target hypothesis that is output with a target hypothesis signal. The recursion formula is based on hidden Markov models with a single optimum state sequence and may take the form of a modified Viterbi algorithm.

Abstract: Systems, methods and articles of manufacture are provided for adjusting the parameters of ones of a plurality of recognition models. The recognition models collectively represent a vocabulary. The recognition models are utilized to identify a known word represented within a received input signal. The received input signal may include within vocabulary and out of vocabulary words. An output signal representing a confidence measure corresponding to the relative accuracy of the identity of the known word is generated. Particular ones of the plurality of recognition models are adjusted as a function of the output signal to improve the confidence measure. The systems, methods and articles of manufacture are preferably implemented in accordance with discriminative techniques, and the adjustment process is used during either a preferred training or a recognition mode.