Scott Instruments Corporation

Scott Instruments Company

Leland Stanford Junior University

Brian L Scott

Lee H Hardesty

J Mark Newell

Lloyd A Smith

John Mark Newell

William D Wagers, Jr

Wayne E Kirkwood

Bruce E Balentine

Clint L Miller

R Gary Goodman

Lisan S Lin

Voice activation of functions on a network such as the Internet are accomplished using a speech recognition system running synchronously with standard desktop-based Internet functions. This synchronous operation allows voice-based control to be exercised for all operations on the Internet. System functions are based on a unique combination of a local web browser, a remotely-located speech/web server, and control links between a web browser and a speech/web server. The control links provide a mechanism for controlling a speech server from a web page and a mechanism for driving both the local, as well as a remote, web browser.

Using speech recognition to access the internet, including access via a

Speech signals are analyzed by correlating a sequence of samples to derive a sliding average magnitude difference function (SAMDF) whereby histograms are formed which are compressed and normalized to form histogram sequences representing the speech signal for comparison and recognition.

Method and apparatus for extracting information-bearing portions of a

A method and apparatus for generating a signal transformation useful in signal processing. According to the preferred embodiment, a signal, e.g., a speech waveform, is first converted into a sequence of digital data samples, and a reference position along a first sub-part of the sequence is then selected. A 'weighted' histogram corresponding to the reference position is then generated according to a correlation function. Thereafter, a new reference position is selected, for example, at a sub-part of the sequence located a pitch period of the signal from the original reference position, and an additional histogram is generated for this sub-part. The plurality of histograms comprise the transformation of the signal, which retains a substantial part of the informational content of the original signal. Therefore, the transformation is then used as the signal itself in signal processing applications such as speech compression and synthesis.

Method and apparatus for generating a signal transformation and the use

A method and apparatus for processing a signal to extract selected information therefrom is provided. According to the method, an input signal is converted into a sequence of data samples, and these data samples are applied sequentially through a convolver having first and second sections, the output of the first section forming the input of the second section. A data sample in the second convolver section is then compared to each data sample in the first convolver section to produce an output signal of a plurality of data points, each of the data points representative of a midpoint position within the convolver between a pair of compared data samples. This comparison step is repeated for each data sample in the second convolver section and the output signals form a histogram from which the selected information is extracted. This method may be advantageously utilized in a speech recognition process for extracting various features from an input speech signal.

Method for signal processing

A real time cochlear implant processor (10) receives an audio input signal and extracts spectrum segments by operation of bandpass filters (18, 20). In each channel temporal circuitry detects the zero slope points of the filtered audio input signal and generates a control signal which operates a gate (66). Amplitude circuitry includes a reference voltage source for providing positive and negative polarity signals for a first mode of operation. The reference signals are routed through the gate (66) by the control signals. In a second mode of operation the audio input signal, after logarithmic amplification, is passed through the gate (66) by operation of the control signals. In a third mode of operation the audio input signal is squared through infinite clipping and the resulting signal is gated by the control signals through the gate (66). The outputs of the channels are combined in a summing circuit (78) and passed through a buffer (82) to produce a driver signal for an auditory implant electrode. The pulse outputs from the plurality of channels have different amplitudes where the higher frequency channels have lower amplitude pulses.

Real time cochlear implant processor

A method of human-machine interactive instruction with the aid of a digital computer is disclosed. The first step is providing the computer with a data base of a series of questions and answers which can be reproduced and thereafter individualized by student use by (i) providing the digital computer with a keyboarded typed question, (ii) providing the computer with a keyboarded typed answer, (iii) speaking the correct answer a plurality of times to generate relational signals for master template of the correct answer in digital form, and (iv) correlating the master template with the corresponding keyboarded typed answer. The second step is providing a human machine voice display interactive tutorial process, by for each question and answer in the data base of questions and answers, sequentially (i) displaying a typed question, (ii) displaying the corresponding correct typed answer, (iii) initiating the articulation of the correct answer by a user, (iv) processing the so-spoken answer by converting it from an audio signal into relational signals in digital form, (v) determining whether the processed spoken answer in digital form corresponds to the master template for that answer, and (vi) adjusting the master template to individualize it for the speaker if the processed spoken answer in digital form does not correspond to the master template.

Process of human-machine interactive educational instruction using voice

Recognition of human speech is carried out by storing a template for each unit of speech to produce a dictionary of stored words and phrases. A given speech signal is converted to produce a template which is compared to the stored template to find the closest comparison. The word or phrase corresponding to the identified template is produced and displayed to complete the recognition of the speech signal. The speech signal is processed to produce two separate frequency components. The frequency components are processed to produce a DC signal proportional to the frequency of the frequency component. The frequency components are also rectified to produce amplitude signals corresponding to the envelope of the frequency components. The products [F.sub.1 ][F.sub.2 ] and [A.sub.1 ][A.sub.2 ] and ratios F.sub.1 /F.sub.2 and A.sub.1 /A.sub.2 of the pairs of frequency and amplitude signals are produced to generate a plurality of relational signals which comprise the templates corresponding to each speech signal. In building the dictionary each speech sample is submitted a number of times to produce an average template value together with the variants for each data point.

Method and apparatus for speech recognition

The present invention comprises a frequency responsive tactile stimulator. Selected mid-frequency and high frequency components are extracted from an input audio signal by a bandpass filter (18) and a high-pass filter (20). The outputs of these filters are transmitted through precision rectifiers (22, 24) and provided to modulate power drivers (26, 28). A random noise signal is generated by a noise generator (30) and limited to fixed length randomly distributed pulsed by a one-shot circuit (36). The random pulses are provided as the input to the power drivers (26, 28). The lower frequency power driver (26) drives a plurality of vibrators (42-48) which are spatially arranged on a transducer to cover a distinct area. The high frequency signal component modulates power driver (28) which drives two vibrators (50, 52) which are contiguously located to produce a punctate vibration. The use of the stimulator in accordance with the present invention together with an audio amplifier hearing aid provides the user with the ability to distinguish various high frequency signal components despite the loss of hearing for high frequency signals.

Vibratory aid for presbycusis

Voice pitch is detected by passing a speech signal from a microphone 10 through a filter array 20 to a summing amplifier 22. The summing amplifier 22 provides a composite signal of the acoustic components of the speech signal and this composite signal is input to a multiplier 26 and from the multiplier 26 to a multiplier 36 having an output connected to a comparator 42. The comparator 42 compares the output of the multiplier 36 with a hysteresis signal, then provides an output to a phase locked loop 46. The phase locked loop 46 provides a first voltage output in analog form to a bar graph display 50 and provides a square wave output that is applied to a frequency-to-voltage converter 52 for driving a digital display 54.

Voice pitch detector and display

A speech signal is input to a microphone (10) and applied through a signal compressor (14) to a filter array (18) consisting of a high pass channel (20), a midfrequency channel (22) and a low pass channel (24). The outputs of the filter array (18) are precision rectified in rectifiers (28), (36) and (46). The rectified signals are applied to voltage controlled power drivers (54) and (56), where the output of the midfrequency channel (22) and the low frequency channel (24) are applied to the power driver (54) and the output of the high frequency channel (20) and the low frequency channel (24) are applied to the power driver (56). The power driver (54) drives vibrators (58) and (60) and the output of the power driver (56) drives a vibrator (62). To drive the vibrators (58) and (60), a random frequency signal at the output of a one shot multivibrator (38) is amplitude modulated by the output of the midfrequency channel (22). To drive the vibrator (62) the same random frequency signal is amplitude modulated by the output of the high pass channel (20).

Growing community of inventors

Denton, TX, United States of America

Brian L Scott