Abstract: A training device changes feedback formant frequencies which are formant frequencies of a picked-up speech signal, applies a lowpass filter, converts the picked-up speech signal, adds high-pass noise to the converted speech signal, feeds back the converted speech signal with the high-pass noise added to a subject, calculates a compensatory response vector by using pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted with change of the feedback formant frequencies to the subject, and pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted without change of the feedback formant frequencies to the subject, and determines an evaluation based on the compensatory response vector and a correct compensatory response vector.

Abstract: A method and system for rehabilitation of a patient having a physical impairment by providing music therapy, the method being implemented on a computer system having one or more physical processors configured by machine-readable instructions which, when executed perform the method, includes receiving biomechanical data from the patient regarding repetitive movements of the patient and determining a baseline condition; determining a baseline beat tempo having a constant frequency based on the baseline condition; providing music to the patient, the music having beat signals at the baseline beat tempo; providing a cue to the patient to perform each repetitive movement in time with an associated beat signal; receiving time-stamped biomechanical data of the patient relating to the repetitive movements performed by the patient in time with the baseline beat signals; analyzing the biomechanical data to identify an onset time of one or more cycles of the repetitive movement; determining an entrainment parameter based

Abstract: A computer implemented method, system and computer program product are provided that implement a neural network (NN) audio filter. The method, system and computer program product obtain an electronic audio signal comprising a speech impaired message and apply the audio signal to the NN audio filter to modify the speech impaired message to form an unimpaired message. The method, system and computer program product output the unimpaired message.

Abstract: An evaluation device applies a lowpass filter with a cutoff frequency being a first predetermined value or a second predetermined value greater than the first predetermined value with or without change of feedback formant frequencies which are formant frequencies of a picked-up speech signal, converts the picked-up speech signal, feeds back the converted speech signal to a subject, and includes an evaluation unit that calculates a compensatory response vector by using pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted with change of the feedback formant frequencies to the subject, and pickup formant frequencies which are formant frequencies of a speech signal acquired by picking up an utterance made by the subject while feeding back a speech signal that has been converted without change of the feedback formant frequencies to the subject, and determines an evaluation based

Abstract: A method includes: prompting a user to recite a story associated with a first target emotion; recording the user reciting the story and recording a first timeseries of biosignal data via a set of sensors integrated into a wearable device worn by the user; accessing a first timeseries of emotion markers extracted from the voice recording; labeling the first timeseries of biosignal data according to the first timeseries of emotion markers; generating an emotion model linking biosignals to emotion markers for the user based on the first emotion-labeled timeseries of biosignal data; detecting a second instance of the first target emotion exhibited by the user based on a second timeseries of biosignal data and the emotion model; and notifying the user of the second instance of the first target emotion.

Abstract: A method operates a hearing device in present surroundings such that noise cancellation of the hearing device is activated, so that ambient sounds are reduced for a user of the hearing device. A desired value for the voice volume of the user is determined for the present surroundings. An actual value for the voice volume of the user is measured. If the actual value is lower than the desired value, the hearing device takes a measure to prompt the user to speak more loudly. Additionally, a hearing device is configured to implement the method.

Abstract: An automated training method enhances conversational effectiveness of a system participant interacting with a virtual client. The method operates on received speech input to produce text. A speech effectiveness analysis processor receives both the speech and text and produces quantified metrics measuring speech effectiveness based on the input parameters. Personalized feedback is generated based on the quantified metrics and is transmitted to the system participant. A virtual client dialog is generated using a dynamic simulation processor. The virtual client dialog is based on the quantified metrics, such that the virtual client responds to the speech input using the generated dialog.

Abstract: A method and apparatus for generating a caption are provided. The method of generating a caption according to one embodiment comprises: generating caption text which corresponds to a voice of a speaker included in broadcast data; generating reference voice information using a part of the voice of the speaker included in the broadcast data; and generating caption style information for the caption text based on the voice of the speaker and the reference voice information.

Abstract: The present disclosure relates to a fluency aid comprising: a pacing signal generator operable to output a signal for generating, at regular time intervals, an audible sound; and a controller operable, in response to a voice being detected by a voice detector, to control the pacing signal generator such that the output signal causes the audible sound to continue, stop or fade.

Abstract: The present disclosure provides a fluency aid comprising: a masking signal generator; a switch operable to switch the masking signal generator between an ON state and an OFF state, wherein, when in the ON state, the masking signal generator is operable to generate a masking signal; a sound generator operable to receive the masking signal from the masking signal generator and generate a masking sound for output to a user of the fluency aid; and a voice detector operable to detect a voice of the user, wherein the masking signal generator is operable to generate the masking signal at least until the voice of the user is detected by the voice detector.

Abstract: A method for providing feedback of an own voice loudness of a user of a hearing device comprises: extracting an own voice signal of the user from an audio signal acquired with a microphone of the hearing device; determining a sound level of the own voice signal from the audio signal; determining an acoustic situation of the user; determining at least one of a minimal threshold and a maximal threshold for the sound level of the own voice signal from the acoustic situation of the user; and notifying the user, when the sound level is at least one of lower than the minimal threshold and higher than the maximal threshold.

Abstract: Facial image data of an individual is collected of the individual to provide mental state data using a first web-enabled computing device. The mental state data is analyzed to produce mental state information using a second web-enabled computing device. The mental state information is shared across a social network using a third web-enabled computing device. The mental state data is also collected from the individual through capture of sensor information. The mental state data is also collected from the individual through capture of audio data. The individual elects to share the mental state information across the social network. The mental state data may be collected over a period of time and analyzed to determine a mood of the individual. The mental state information is translated into a representative icon for sharing, which may include an emoji. An image of the individual is shared along with the mental state information.

Abstract: An electronic device for providing health information or assistance includes an input configured to receive at least one type of signal selected from sound signals, verbal signals, non-verbal signals, and combinations thereof, a communication module configured to send information related to the at least one user and his/her environment to a remote device, including the sound signals, non-verbal signals, and verbal signals, the remote device being configured to analyze a condition of the at least one user and communicate condition signals to the electronic device, a processing module configured to receive the condition signals and to cause the electronic device to engage in a passive monitoring mode or an active engagement and monitoring mode, the active engagement and monitoring mode including, but not limited to, verbal communication with the at least one user, and an output configured to engage the at least one user in verbal communication.

Abstract: The present invention relates to a device for focusing a user's attention for an individual who loses focus during an activity. This is accomplished by randomizing (which includes pseudo randomizing) each reminder prompts as well as the time interval within a selected time frame.

Abstract: A method for speech enhancement, the method may include receiving or generating sound samples that represent sound signals that were received during a given time period by an array of microphones; frequency transforming the sound samples to provide frequency-transformed samples; clustering the frequency-transformed samples to speakers to provide speaker related clusters, wherein the clustering is based on (i) spatial cues related to the received sound signals and (ii) acoustic cues related to the speakers; determining a relative transfer function for each speaker of the speakers to provide speakers related relative transfer functions; applying a multiple input multiple output (MIMO) beamforming operation on the speakers related relative transfer functions to provide beamformed signals; and inverse-frequency transforming the beamformed signals to provide speech signals.

Abstract: An audio analysis system that may analyze participant audio input in an online game environment. The audio analysis system may receive audio input for participants (players or spectators) in a current game session of a game executing within an online game system. The audio analysis system may analyze the audio input to generate audio analysis information for the current game session, and provide the audio analysis information to the online game system. The audio analysis information may be applied within the online game system in various ways. For example, the information may be displayed to the players and/or spectators via a user interface provided by game clients executing on respective client devices. The audio analysis system may provide an application programming interface (API) to receive audio input and provide audio analysis information to one or more game systems.

Abstract: A hybrid method is provided for modulating upper airway function in a subject. The method includes applying first and second therapy signals to the subject to modulate at least one extrinsic laryngeal muscle and at least one intrinsic laryngeal muscle to synergistically control laryngeal motion and vocal fold movement, respectively.

Abstract: An individual can exhibit one or more mental states when reacting to a stimulus. A camera or other monitoring device can be used to collect, on an intermittent basis, mental state data including facial data. The mental state data can be interpolated between the intermittent collecting. The facial data can be obtained from a series of images of the individual where the images are captured intermittently. A second face can be identified, and the first face and the second face can be tracked.

Abstract: A multi-party conversation analyzer and logger uses a variety of techniques including spectrographic voice analysis, absolute loudness measurements, directional microphones, and telephonic directional separation to determine the number of parties who take part in a conversation, and segment the conversation by speaking party. In one aspect, the invention monitors telephone conversations in real time to detect conditions of interest (for instance, calls to non-allowed parties or calls of a prohibited nature from prison inmates). In another aspect, automated prosody measurement algorithms are used in conjunction with speaker segmentation to extract emotional content of the speech of participants within a particular conversation, and speaker interactions and emotions are displayed in graphical form.

Abstract: Multi-user portable electronic devices for improving reading ability and/or comprehension for a plurality of subjects are provided. The multi-user portable electronic devices may include a pitch shifter circuit configured to generate frequency altered auditory speech feedback (FAF) signals corresponding to respective auditory speech signals received from respective active microphones, and to transmit the respective FAF signals to the plurality of subjects while one or more of the plurality of subjects are respectively reading aloud, to improve the plurality of subjects' reading ability and/or comprehension. The multi-user portable electronic devices may also include a switch configured to activate the microphones selectively, serially. Related methods and systems are also described.

Abstract: The present invention relates to a system and a method for inspecting an emotion recognition capability using multisensory information, and a system and a method for training emotion recognition using multisensory information.

Abstract: The application relates to a hearing assistance device (HAD) comprising (a) an input transducer system comprising (a1) an audio input transducer (AIT), and (a2) a first supplementary input transducer (SIT1), (b) an output transducer (OT) for converting a processed output signal to a stimulus perceivable by said user as sound, and (c) a signal processing unit (SPU) operationally connected to said audio input transducer (AIT), to said first supplementary input transducer (SIT1), and to said output transducer (OT), said signal processing unit (SPU) being configured for processing said electric audio input signal, and said first supplementary electric input signal, and for providing said processed output signal. The audio input transducer (AIT) is adapted for being located in an ear of the user. In a NORMAL mode of operation, electric audio input signal is processed in the signal processing unit and the supplementary electric input signal(s) are used to control the processing.

Abstract: A hybrid method is provided for modulating upper airway function in a subject. The method includes applying first and second therapy signals to the subject to modulate at least one extrinsic laryngeal muscle and at least one intrinsic laryngeal muscle to synergistically control laryngeal motion and vocal fold movement, respectively.

Abstract: The invention describes a computer-based system that asks (101) a patient to pronounce a word displayed on a monitor, automatically assesses (104, 105) the speech quality, and uses suitable means to feed back (106) any improvement or deterioration of speech quality.

Abstract: Audio sounds are captured from a subject's body, e.g., using a smartphone or a worn array of microphones. Plural features are derived from the captured audio, and serve as fingerprint information. One such feature may be a time interval over which a threshold part of spectral energy in the audio is expressed. Another may be a frequency bandwidth within which a second threshold part of the spectral energy is expressed. Such fingerprint information is provided to a knowledge base that contains reference fingerprint data and associated metadata. The knowledge base matches the fingerprint with reference fingerprint data, and provides associated metadata in return—which can comprise diagnostic information related to the captured sounds. In some arrangements, an audio signal or pressure waveform stimulates the body at one location, and is sensed at another, to discern information about the intervening transmission medium. A great variety of other features and arrangements are also detailed.

Abstract: One example embodiment of the present disclosure includes method and system to improve communication comprising an assembly fixedly positioned during use in close proximity to a user's ear. The assembly includes an accelerometer to detect the initiation and duration of the user's speech and an output presentation system. The output presentation system comprises a non-occlusive ear fitting that presents unintelligible noise that is unrelated to the sound-frequency or intonation of the user's current speech. The unintelligible noise is presented to the patient at a level less than 85 dB. The system further comprises a control arrangement to maintain presentation of the noise substantially throughout the detected duration of the user's speech, but substantially not at other times.

Abstract: A plurality of individual toys, at least a first one of which generates acoustic signals and at least a second one of which receives acoustic signals. When the second toy receives acoustic signals from the first toy, it responds, for example, by generating a sound and/or controlling its motion. In a preferred embodiment of the invention, the toys flock and/or form a procession of toys which follow a leader toy, for example a mother goose and a plurality of following and preferably quacking goslings.

Abstract: A method and device is disclosed for reducing and controlling stuttering. The method involves tactile feedback of the stutterer's own speech to reducing stuttering. In one embodiment, the device may detect speech by audible or mechanical means, and the feedback may be produced by vibration mechanisms.

Abstract: A speech analysis system and method for analyzing speech. The system includes: a voice recognition system for converting inputted speech to text; an analytics system for generating feedback information by analyzing the inputted speech and text; and a feedback system for outputting the feedback information.

Abstract: A device for supplementing a voice includes: a sensing unit sensing a bio-signal corresponding to a first vibration of vocalization and generating a first signal corresponding to the bio-signal; a vibration unit generating a second vibration using the first signal; and a power unit supplying a power to the sensing unit and the vibration unit.

Abstract: A stimulation system and method for treating to a human subject having spasmodic dysphonia includes a sensing electrode configured to detect voice activity of a vocalizing muscle of the subject and to generate a first signal, and a processor configured to receive the first signal from the sensing electrode and to generate at least one stimulation parameter based on the first signal. The system further includes a mechanical actuator configured to receive the stimulation parameter from the processor and to activate a glottic closure reflex of the subject in response to the stimulation parameter and a stimulating electrode configured to receive the stimulation parameter from the processor and stimulate the recurrent laryngeal nerve or the vagus nerve of the subject based on the stimulation parameter.

Abstract: Methods and devices treat non-stuttering pathologies having impaired or decreased communication skills by administering a frequency altered auditory feedback signal to a subject having a non-stuttering pathology while the subject is speaking or talking to thereby improve the subject's communication skills.

Abstract: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

Abstract: A device for stuttering alleviation is disclosed, comprising a speech sensor, configured to output signals indicative of speech, a processing unit configured to detect stuttering, log stuttering and/or produce stimulation indication based on stimulation rules Said device may further comprise a remote server and a server user interface, configured to allow the speech therapist access to the processing unit. Further provided is a method for accelerating the learning procedure for obtaining a permanent fluent speech, comprising receiving and analyzing speech parameters, determining whether a negative reinforcement is required and executing the negative reinforcement.

Abstract: One example embodiment of the present disclosure includes method and system to improve communication comprising an assembly fixedly positioned during use in close proximity to a user's ear. The assembly includes an accelerometer to detect the initiation and duration of the user's speech and an output presentation system. The output presentation system comprises a non-occlusive ear fitting that presents unintelligible noise that is unrelated to the sound-frequency or intonation of the user's current speech. The unintelligible noise is presented to the patient at a level less than 85 dB. The system further comprises a control arrangement to maintain presentation of the noise substantially throughout the detected duration of the user's speech, but substantially not at other times.

Abstract: One example embodiment of the present disclosure includes method and system to improve communication comprising an assembly fixedly positioned during use in close proximity to a user's ear. The assembly includes an accelerometer to detect the initiation and duration of the user's speech and an output presentation system. The output presentation system comprises a non-occlusive ear fitting that presents unintelligible noise that is unrelated to the sound-frequency or intonation of the user's current speech. The unintelligible noise is presented to the patient at a level less than 85 dB. The system further comprises a control arrangement to maintain presentation of the noise substantially throughout the detected duration of the user's speech, but substantially not at other times.

Abstract: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

Abstract: A device for volitional swallowing with a substitute sensory system comprises a band 101 wrapped around the neck with a vibrator 102 positioned over the larynx. Upon activation by a button 103 on a spoon 104 held by an operator, such as the subject 105, the vibrator 102 moves and vibrates the larynx. The patient 105 initiates the sensory stimulation immediately prior to the patient's own initiation of a swallow by viewing on a display screen 106 a movement feedback signal 107, possibly from a piezo-electric sensor 108 also contained in the band 101 which will also be displayed on the display screen 106. The signal 109 from the switch device initiating sensory stimulation will be presented on the same display screen 106 for the patient 105 and trainer to observe when the button or switch 103 is activated for sensory stimulation in relation to the onset of the swallow.

Abstract: A method and device is disclosed for reducing and controlling stuttering. The method involves tactile feedback of the stutterer's own speech to reducing stuttering. In one embodiment, the device may detect speech by audible or mechanical means, and the feedback may be produced by vibration mechanisms.

Abstract: One example embodiment of the present disclosure includes method and system to improve communication comprising an assembly fixedly positioned during use in close proximity to a user's ear. The assembly includes an accelerometer to detect the initiation and duration of the user's speech and an output presentation system. The output presentation system comprises a non-occlusive ear fitting that presents unintelligible noise that is unrelated to the sound-frequency or intonation of the user's current speech. The unintelligible noise is presented to the patient at a level less than 85 dB. The system further comprises a control arrangement to maintain presentation of the noise substantially throughout the detected duration of the user's speech, but substantially not at other times.

Abstract: A speech aid for persons with hypokinetic dysarthria, a speech disorder associated with Parkinson's disease. The speech aid alters the pitch at which the user hears his or her voice and/or provides multitalker babble noise to the speaker's ears. The speech aid induces increased speech motor activity and improves the intelligibility of the user's speech. The speech aid may be used with a variety of microphones, headphones, in one or both ears, with a voice amplifier, or connected to telephones.

Abstract: Methods and devices treat treating non-stuttering pathologies having impaired or decreased communication skills by administering a frequency altered auditory feedback signal to a subject having a non-stuttering pathology while the subject is speaking or talking to thereby improve the subject's communication skills.

Abstract: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

Abstract: A small, compact voice volume monitor has been developed that provides feedback to the speaker/user regarding the volume of the user's speech. The monitor is based on a sensing sound vibrations in the ear bone during speech and converting these vibrations into an electrical signal reflecting the speech volume. Electronic circuitry is then used to compare the intensity of this signal with pre-set reference levels. When the intensity of the signal is outside the reference levels for a set amount of time, feedback is provided to the user, for example, from a small vibratory motor.

Abstract: A device and method for improving speech. One embodiment comprises an apparatus and method for treating stuttering by providing biofeedback to monitor aspects of the user's voice and also providing altered audio feedback (AAF) to induce fluent speech. Biofeedback features include monitoring phonated intervals. AAF features include delayed auditory feedback (DAF), frequency-altered auditory feedback (FAF), and switching the user's voice between his or her left and right ears multiple times per second. The biofeedback controls AAF parameters including volume, which changes smoothly. Bluetooth is also included to connect to wireless microphones and earphones. Another embodiment comprises an apparatus and method for use by persons without speech disabilities for the purpose of improving public speaking by providing their voice back to their ears altered to appear to be in a different emotional state, thus inducing this preferred emotional state in the person speaking.

Abstract: Methods and devices treat treating non-stuttering pathologies having impaired or decreased communication skills by administering a frequency altered auditory feedback signal to a subject having a non-stuttering pathology while the subject is speaking or talking to thereby improve the subject's communication skills.

Abstract: A device for treating and reducing stuttering by utilizing auditory feedback. A bone conducting hearing aid apparatus is arranged to be attached to the skull bone of a user with a stuttering problem so that his ear canal is left free. A tactile component in the form of a vibrator mechanically transmits sound information to the inner ears of the user via the skull bone so that both cochleas are stimulated. The cochlea on the opposite side of the skull receives a signal that is further delayed and also has another frequency characteristics compared to the digital received by the nearest cochlea.

Abstract: Methods and devices treat treating non-stuttering pathologies having impaired or decreased communication skills by administering a frequency altered auditory feedback signal to a subject having a non-stuttering pathology while the subject is speaking or talking to thereby improve the subject's communication skills.

Abstract: Stuttering-treatment techniques using neural stimulation and/or drug delivery. One or more electrodes and/or a catheter are implanted adjacent to sites in the brain. A signal generator and the electrode deliver stimulation to a first site. A pump and the catheter deliver one or more therapeutic drugs to a second site. The first and second sites could be: the supplementary motor area, the centromedian circuit, the dorsomedial nuclei, the lateral prefrontal circuit, or other paramedian thalamic and midbrain nuclei. The stuttering treatment could be performed via periodic transcranial magnetic stimulation. A sensor, located near the patient's vocal folds, can be used for generating a signal responsive to activity of the patient's speech-producing muscles. A controller adjusts one or more stimulation parameters in response to the signal from the sensor.

Abstract: The invention relates to a portable listening system comprising a microphone device for picking up a person's voice and a listening device comprising a receiver. The invention further relates to the use of such system. The object of the present invention is to provide a portable device for treatment of stuttering. The problem is solved in that the system being adapted to pick up the voice of a person wearing the portable system by the microphone device, converting the voice to an own voice electrical signal, to transmit the own voice electrical signal to the listening device, to receive the own voice electrical signal in the listening device and to play it for the person by the receiver with a delay. An advantage of the invention is that it provides a flexible body worn system suitable for treatment of stuttering. The invention may e.g. be used for applications involving listening devices to be worn by a person to be treated for stuttering.