77 results about "Speech patterns" patented technology

A method and apparatus for providing personalized information content over telephones is described. The creation of a voice portal is supported by the invention. Embodiments of the invention use telephone identifying information such as the calling party's number to identify, or create, user profiles for customization. The personalized content is specific to that user based on her / his telephone identifying information and may be further customized based on the current time, current date, the calling party's locales, and / or the calling party's dialect and speech patterns. Also, the telephone identifying information may support targeted advertising, content, and purchasing recommendations specific to that user. The system may use a voice password and / or touch-tone login system when appropriate to distinguish the caller or verify the caller's identity for specific activities. Typically, embodiments of the invention will immediately present a caller personalized content based on her / his profile using the appropriate dialect as well as the caller's preferred content. Profiles can be constructed as the caller uses embodiments of the invention as well as through explicit designation of preferences. For example, as the user selects topics, as well as particular content, a record of actions can be maintained. This record of actions can be used to provide suggestions and direct the personalization of the system for the user.

Apparatus for providing biofeedback sports training are described to improve training in a convenient form. Aspects include a sparring device that converts impact and training rates into audio streams following human speech patterns. A device is described for coaching swings such as in golf. Another aspect of the invention is a strength training device utiling a multicylinder piston device.

A platform is provided to respond to data inquiries from callers or users that are directed to one of a plurality of clients or subscribers. A user is guided to a selected client's area on the platform using voice menus and prompts together with speech recognition and database search techniques. The voice prompts are adaptively generated according to the client's policies and the kind of content it offers, and the platform's experience with the user's speech patterns. The content is returned to the caller using a transmission method that is selected in response to voice prompts.

A method and apparatus improve the synchronization and presentation of an exchange of messages between two or more users during an on-line Internet messaging session. This method and apparatus discriminate which messages from a sender correspond to replies from a recipient and presents these messages in an orderly, time-sequenced fashion using color schemes or separate presentation windows which improves the overall readability and efficiency of the communication. Additionally, the method and apparatus provide a level of identity security. As a user enters messages, the typing style, speech patterns, or biometrics of all the users are monitored and will issue warnings whenever a change is detected, possibly indicating someone other then the original user is now sending messages. Alternatively, or in addition, a user may be asked a series of random questions and another user will evaluate answers provided to those questions to determine whether a user's identity is false.

An electronic device (10, 16) analyzes a voice communication for actionable speech using speech recognition. When actionable speech is detected, the electronic device may carry out a corresponding function, including storing information in a log or presenting one or more programs, services and / or control functions to the user. The actionable speech may be predetermined commands and / or speech patterns that are detected using an expert system as potential command or data input to a program.

An audible medical information system for a patient or other lay user that is loaded with content by a company or the health care practitioner and can be played at will by the patient and a means for recording information in the audio file. In one embodiment, the system records information in a physical card that the user can have with them without the need for any electronic devices such as a computer or smart phone. Other embodiments may include electronic audio or video files delivered to a computer or smart phone. The audio file can contain up to several minutes of audible information, some of which may be patient specific and some of which may be disease or medication specific. The information may include pre- or post-surgical instructions, information about medications or basic use instructions for medical devices.The file(s), which can play when a card is opened (note card format) or a button is pressed (credit card or digital format), will repeat the information as the user desires. The audio is in the form of a computer generated and / or pre-recorded human voice, which may be customized for the patient's language of choice and speech patterns, and will be clear and understandable. The voice characteristics may be optimized for persuasive characteristics so this tool can help motivate patient adherence to medical instructions. This system has particular utility for patients who do not speak the same language as the health care practitioner or who do not have the ability to understand the written instructions provided, although the system will be available in convenient form factors for all patients and for those who help with their medical care. Easy access to this information will contribute to improved patient satisfaction and compliance with medical instructions which is expected to improve health outcomes.

Disclosed is a noise suppression system including a unit for calculating a noise mean spectrum from an input signal, a unit for deriving the provisional estimate speech from the input signal and the noise mean spectrum, a reference speech pattern, and a unit for correcting the provisional estimate speech using the reference pattern.

In one embodiment, the present invention is directed to reconfiguration of a communication device or other network node based on a determination that a user has a target (altered) physical condition.

Systems, methods and articles of manufacture for controlling electronic devices in an interactive gaming environment. Embodiments detect a first interactive game is playing within the physical environment using one or more electronic devices. User movement is monitored using at least one sensor device within the physical environment and user speech is monitored using one or more microphone sensor devices within the physical environment. Upon determining that the user movement matches a predefined series of user actions and that the user speech matches a corresponding predefined speech pattern, embodiments determine a gameplay action corresponding to both the predefined series of user actions and the predefined speech pattern and transmit an instruction, to at least one of the one or more electronic devices within the physical environment, instructing the electronic device to perform the determined gameplay action.

A concept, method and apparatus for detecting and correcting an accent by means of sound morphing is provided. The input audio signal is analyzed for finding pre-specified unwanted speech patterns, i.e. phonemes or groups of phonemes that are to be corrected, for instance because they represent a foreign accent. These unwanted sounds are then modified or completely replaced by the pre-stored replacement audio patterns, adjusted to the current pitch and voice timbre of the user. The degree of speech modification, i.e. the set of phonemes to be modified, can be set at a desired level. The system works in two modes: first, learning, i.e. storing the unwanted and the replacement phoneme patterns, and second, the correction mode which performs phoneme modification based on the stored information. The implementation is both in software and hardware. The hardware apparatus is based on parallel signal processing and therefore allows for real-time accent correcting of variable complexity, up to multiple-user multiple-accent super-complex systems based on mesh architecture of multiple chips and boards, possibly as a part of a telephone or another networking system.

Fraudulent callers that masquerade as legitimate callers in order to discover details of bank accounts or other accounts are an increasing problem. In order to detect possible fraudsters and preventing them from obtaining such details a method and system is proposed that transform the recorded speech of a batch of incoming calls to strings of phonemes or text. Thereafter similar speech patterns, such as distinct similar phrases or wording, in the recorded speech are determined and calls having similar speech patterns, and preferably also similar acoustic properties, are grouped together and identified as being from the same fraudulent caller. Transactions initiated by the fraudulent caller can as a result be stopped and preferably a voiceprint of the fraudulent caller's speech is generated and stored in a database for further use.

In one embodiment, the present invention is directed to a communication device that analyzes received utterances and detects when the speaker has a target physical condition.

A method, system, and computer program product is disclosed for customizing a synthesized voice based upon audible input voice data. The input voice data is typically in the form of one or more predetermined paragraphs being read into a voice recorder. The input voice data is then analyzed for adjustable voice characteristics to determine basic voice qualities (e.g., pitch, breathiness, tone, speed; variability of any of these qualities, etc.) and to identify any “specialized speech patterns”. Based upon this analysis, the characteristics of the voice utilized to read text appearing on the screen are modified to resemble the input voice data. This allows a user of the system to easily and automatically create a voice that is familiar to the user.

Systems, devices, methods, and computer readable media are provided in various embodiments having regard to authentication using secure tokens, in accordance with various embodiments. An individual's personal information is encapsulated into transformed digitally signed tokens, which can then be stored in a secure data storage (e.g., a “personal information bank”). The digitally signed tokens can include blended characteristics of the individual (e.g., 2D / 3D facial representation, speech patterns) that are combined with digital signatures obtained from cryptographic keys (e.g., private keys) associated with corroborating trusted entities (e.g., a government, a bank) or organizations of which the individual purports to be a member of (e.g., a dog-walking service).

A method and an apparatus for providing automated speech-to-text encoding and decoding for hearing-impaired persons. A broadband subscriber terminal interfaces to: (a) a network to convey speech packets thereover, (b) a telephone to convey speech information, and (c) a display device to display textual information of spoken words. A speech buffer in the subscriber terminal receives speech data and a processor decodes and displays textual representations of speech on the display device. A database stores voice and / or speech patterns that are used by a speech analyzer to recognize an incoming caller and to associate a name or characteristic (e.g., male or female) with the incoming call. A tonal and inflection analyzer analyzes speech to add punctuation to the displayed text. A detector, such as a DTMF detector, responds to subscriber inputs to activate / deactivate speech recognition or other functions.

A device and method for translating language is disclosed. In one embodiment, for example, a method for providing a translated output signal derived from a speech input signal, comprises receiving a speech input signal in a first language, converting the speech input signal into a digital format, comprising a voice model component representing a speech pattern of the speech input signal and a content component representing a content of the speech input signal, translating the content component from the first language into a second language to provide a translated content component; and generating an audible output signal comprising the translated content in an approximation of the speech pattern of the speech input signal.

The embodiment of the invention discloses a method for automatically switching speech patterns. The method comprises the following steps: detecting and obtaining the moving direction and the putting direction of a mobile terminal of the current call; judging whether the moving direction and the putting direction of the mobile terminal of the current call meet the conditions of speech pattern switching, wherein the conditions of speech pattern switching include the moving direction and the putting direction of the mobile terminal; and if so, the speech pattern of the mobile terminal is switchedto a speech pattern corresponding to the switching conditions met by the mobile terminal. The invention also discloses a system and the mobile terminal for automatically switching speech patterns; and according to the moving direction and the putting direction of the mobile terminal of the current call, the speech mode of the mobile terminal is automatically switched, thus being more convenient and more humanized in use.

A telephonic authentication system, method and program product. An authentication system is provided for authenticating a user of a telephonic device that includes a setup system for capturing and storing an authentic user speech pattern sample; a comparison system that compares the authentic user speech pattern sample with an inputted speech pattern sample and generates a comparison result; and a control system for controlling access to the telephonic device. The control system analyzes the comparison result for an initial inputted speech pattern sample received when a telephone call is initiated and periodically analyzes comparison results for ongoing inputted speech pattern samples received during the telephone call.

A GPS navigation code device has GPS features and easy address retrieval means built in, enabling a driver to retrieve and request directions to an address without taking his eyes off the road. The user pre-programs the GPS navigation code device with a plurality of addressees or points of interest and assigns unique navigation codes for each as keyboard entry and speech, all stored in local database within the GPS in three linked databases. While driving, the user presses a special address search mode key and inputs the unique navigation code by keyboard or speech pattern, views displayed address and accepts the same. When an unknown navigation code is entered the GPS accesses a remote database through the Internet to recover the associated company name and uses Internet based map service to locate closest list of specified business providing directions by map and speech on a turn-by-turn basis.

A method and a device for processing of speech information uses the input and / or storage and / or the acoustical reproduction and / or for the transmission of speed and data information to other devices for local storage and / or reproduction, as well as searching for one or several speech segments in the stored speech information. A recording and search / reproduction of speech information is ensured without manual designation and classification and without the requirement of a vocabulary. Spoken words and / or correlated sentences (memorandums) are digitally recorded as speech signals in a memory which, in a partial scope of at least one word, are again spoken for search purposes and are compared in a device with the recordings and subsequently evaluated, from which a score between the two speech patterns is determined and the memorandum with the smallest score is issued / reproduced acoustically.

A speech recognition apparatus, method and computer program product whereby noise is subtracted from an input speech signal by a plurality of spectral subtractions having differing rates of noise subtraction to produce plural noise-subtracted signals, at least one speech features is extracted from the noise-subtracted signals, and the extracted feature is compared with a standard speech pattern obtained beforehand to recognize the speech signal based on a result of the comparison. In addition, features can be extracted from at least one of the noise-subtracted signals and also the input speech signal for comparison with the standard speech pattern. Plural features can be combined into a single feature for the comparison.

A GPS navigation code device has GPS features and easy address retrieval means built in, enabling a driver to retrieve and request directions to an address without taking his eyes off the road. The user pre-programs the GPS navigation code device with a plurality of addressees or points of interest and assigns unique navigation codes for each as keyboard entry and speech, all stored in local database within the GPS in three linked databases. While driving, the user presses a special address search mode key and inputs the unique navigation code by keyboard or speech pattern, views displayed address and accepts the same. When an unknown navigation code is entered, the GPS accesses a remote database through the Internet to recover the associated company name and business GPS coordinates. The remote database computes travel distance based on vehicle and business GPS coordinates, creating an ordered list that is presented to the GPS user, together with directions by map and speech on a turn-by-turn basis.

Due to the large vocabulary to be recognized, it is presently not possible in many commercially available speech recognition systems to identify, with the desired good recognition results, commands in parallel to the list elements (mostly recorded as dynamic vocabulary). It is now proposed that the speech pattern supplied to the speech recognition system by the user is intermediate stored. Parallel thereto, the at least one element selected from the list by the speech recognizer is merged in a first recognition step with the system command to form a temporary recognizer vocabulary. After the production of this temporary recognizer vocabulary, subsequently the intermediate stored speech input is newly submitted to the recognizer, wherein this now forms the basis of this temporary recognizer vocabulary. Then, if thereby the speech pattern is recognized with higher probability as element of the system command than as the at least one selected element from the list, then it is accordingly interpreted by the speech recognition system as system command. On the other hand, when it is recognized with higher probability as list element, the speech pattern is interpreted as selection of this element by the user.

Systems, devices, methods for providing a speech pattern as a metric of well-being system for remotely monitoring the well-being of a patient are disclosed. In one exemplary embodiment, a system can include at least one wearable device that is configured to collect body sensor data and speech pattern data associated with a patient wearing the device and analyze the data to determine if the patient's emotional well-being is compromised. In some exemplary embodiments, the wearable device can be configured to send an alert to at least one caregiver device that indicates the patient's emotional well-being is compromised. The wearable device can also be configured to send recommendations on courses of action to alleviate the condition.