Abstract: The computer document audio access and conversion system allows a user to access information originally formatted for audio/visual interfacing on a computer network via a simple telephone. Of course, files formatted specifically for audio interfacing can also be accessed by the system. A user can call a designated telephone number and request a file via dual-tone multi-frequency (DTMF) signalling or through voice commands. The system analyzes the request and accesses a predetermined document. The document may be in a standard document file format, such as hyper-text mark-up language (HTML) which is used on the World Wide Web. The document is analyzed by the system, and depending on the different types of formats used in the document, information is translated from an audio/visual format to an audio format and played to the user via the telephone interface. The document may contain links to other documents which can be invoked to access such other documents.

Abstract: A note facility which documents the progress of a student in producing human speech. The facility stores a set of notes in a note file in a computer memory. Each of the set of notes contains textual information generally descriptive of the human speech produced at a given time during the training. A set of speech samples is also stored and attached to selected ones of the set of notes. Each of the speech samples is a digitized version of the human speech produced. The facility analyzes the human speech produced at least one of the given times to produce speech statistics which are presented to the user interface. The speech statistics can be stored in a note and the statistics note attached to the set of notes containing the descriptive text. Navigation through the note file can review each of the notes for the subjective opinion of the student's progress, statistics of an objective acoustic analysis of the speech and listen to the speech file on which the opinion is based.

Abstract: A signal processing system for a strain-gauge pointing device has a reduced parts count and permits the use of relatively inexpensive low-tolerance components. The system can process signals from two or three or more strain gauges, permitting additional inputs by users without a linear increase in the number of signal processing components. The system employs an RC network to develop an offset for the signal to be provided to an analog-to-digital converter. The system performs each measurement twice, once with a particular excitation polarity and again with the opposite excitation polarity, which permits correction for drift and temperature instability.

Abstract: A speech recognition apparatus includes a sound pickup, a standard feature storage device, a comparing device, a display pattern storing device, and a display. The apparatus can display non-speech sounds either as a message or as an image, and is especially useful for hearing-impaired individuals. For example, if a fire engine siren is detected, the display can show a picture of a fire engine, or can display the message "siren is sounding".

Abstract: Selecting human speech samples for a speech model of human speech is preformed. The system presents a graphic representing a human speech sample on a computer display, e.g., an amplitude vs. time graph of the speech sample. Through user input, the system marks a segment of the graphic. The marked segment of the graphic represents a portion of the human speech sample. The system plays the portion of the human speech sample represented by the marked segment back to the user to allow the user to determine its acceptability for inclusion in the speech model. If so indicated by the user, the portion of the human speech sample represented by the marked segment is selected for inclusion in the speech model. The system also analyzes the portion of the human speech sample represented by the marked segment for acoustic properties. These properties are presented to the user in a graphic of the analyzed portion representative of the acoustic properties, e.g.

Abstract: A learning and assessment aid (10) for helping visually impaired individuals develop desirable ambulatory motion habits. The learning aid includes a housing (14) designed to be attached to an article of clothing worn by the individual. Internal to the housing is an inertial transducer (16) that monitors the rotation of the housing and the individual. The individual enters commands to the learning aid through a keypad (20) in response to audible instructions generated over a speaker (22). To foster desirable turning motions, the learning aid informs of the extent to which the individual turns. To foster straight-line walking, the learning aid generates a message over the speaker whenever the individual rotates more than a pre-set individual-entered maximum veer.

Abstract: A system for performing recognition having a telephone transmitter, a camera, a data channel and recognition processing logic, in which the camera is directly mounted to and positioned with respect to the telephone housing to obtain video information from a non-direct frontal view of the speaker corresponding to at least one facial feature for use in speechreading. The facial features that may be obtained include the position of the tongue, separation of the teeth and the rounding protrusion of the lips. Using this data, recognition processing logic performs speechreading recognition of the video information.

Abstract: Improved signal to noise ratio to help speech comprehension in a noisy environment is accomplished by selectively downwardly expanding a speech and noise composite signal when the speech signal is absent, thereby lowering signal components which represent noise. An expansion control signal is extracted from the composite input signal. Operation is based on the assumption that when noise alone is present, the input signal amplitude is less than some reference level and that when speech and noise are present together, the input signal amplitude is greater than the reference level. The response rates of gain changes are quite rapid, and do not introduce distortion or other audibly noticeable artifacts of the processing. The amount of downward expansion of the noise alone is small compared to noise gates to further reduce processing artifacts.

Abstract: A biofeedback system for speech disorders is provided which is adapted to detect disfluent speech, and to provide auditory feedback enabling immediate fluent speech, and to control the auditory feedback in accordance with the disfluent speech, to enable immediate and carryover fluency. The disfluent speech detector is preferably an electromyograph (EMG). The auditory feedback is preferably frequency-altered auditory feedback (FAF). The controller shifts the pitch of the user's voice in accordance with the user's disfluent speech. The biofeedback system may also be provided with delayed auditory feedback (DAF) which enables user control of speaking rate, with masking auditory feedback (MAP) which improves user awareness of the physical sensations of speech, and with a voice-operated switch (VOX) to switch the device off when the user stops talking. The biofeedback system may also include a timer on the DAF circuit to automatically vary the user's speaking rate at regular time intervals.

Abstract: Apparatuses, systems, and a method provide for a visual display of speech, such as the visual display of a received audio signal in telecommunications, especially useful for the hearing impaired. The preferred apparatus includes a network interface that is coupleable to a first communication channel to receive an audio signal; a radio frequency (RF) modulator to convert a baseband output video signal to a RF output video signal and to transmit the RF output video signal on a second communication channel for video display; and a processor coupled to the network interface and to the RF modulator for running a set of program instructions to convert the received audio signal to a text representation of speech, and to further convert the text to the baseband output video signal. The RF output video signal, when displayed on a video display, provides the visual display of speech. The preferred apparatus may also include a speech generation subsystem.

Abstract: A hand held hearing screening device includes a housing with a spacing element extending therefrom. Word generating circuitry is carried within the housing. A control switch on the housing cycles the generating circuitry to produce one or more output word or phrase sequences.