95 results about "Normal speech" patented technology

A method for adaptively training a subject, using auditory processing of phonemes within command sentences, to improve the subject's listening comprehension, grammatical parsing, and serial memory is provided. The method utilizes a number of training installments, each designed for testing a particular aspect of the subject's language skills, all tied together by a common story. More specifically, installments are provided that narrate a story, test the subject's listening comprehension to the narrated story, test the subject's ability to grammatically parse increasingly difficult sentence structures, and test the subject's ability to select and manipulate graphical objects in response to auditory commands. Speech processing is used for the narration, as well as for commands within each test to allow the subject to more easily distinguish between similar sounding phonemes. As the subject improves his/her ability to correctly respond to the tests, the amount of processing applied to the commands is reduced, ultimately to the level of normal speech.

A two piece dual mode earplug including an integrally molded elongated member having a nose end and an open rear end and a channel extending through the elongated member. An integrally molded insert member is formed with a base portion and a rod portion and with the rod portion seated within the open rear end of the elongated member. The insert member additionally includes an attenuation filter integrally molded as part of the rod portion and includes first and second openings located on each side of a chamber and with the size and length of the openings together with the chamber providing attenuation of impulse noise while allowing the passage of normal speech through the channel. The insert member also includes the base portion integrally molded to have a third opening larger than the first and second openings in the rod portion and with the first, second and third openings together forming a passageway through the insert member to the channel extending through the elongated member. The insert member further includes an integrally molded cap member and with the cap member having a plug portion of a size complementary to the third opening of the base member. The insertion of the plug portion into the third opening of the base portion seals off the third opening. The positioning of the cap member provides for the earplug being in a first mode of operation where the passageway is open and a second mode of operation where the passageway is closed.

A method and system for fitting a multichannel cochlear implant system to a patient increases the percentage of patients for which stapedial reflexes can be obtained, and increases the accuracy of predicting the “live speech” comfort levels of the patient's fitting programs from the stapedial reflex. Electrical stimuli are applied on multiple electrodes at “live speech” pulse rates. The neural excitation patterns elicited from such stimulation more closely resemble that which occurs when the system is subjected to normal speech patterns. By progressively setting threshold levels in bands, e.g., groups of electrodes, either overlapping or non-overlapping, as well as with a final check by globally adjusting the band obtained contour to the stapedial reflex, such values more closely resemble actual “live speech” program levels than those obtained with traditional methods. Further, broader excitation patterns produced by the activation of multiple electrodes increases the probability of obtaining reflex measurements where single electrode stimulation fails due to sparse neural survival.

The invention discloses a method and system for detecting abnormal use of voice input equipment. A characteristic extracting mode which is more comprehensive to remote voice signal characteristics and closer to human perception is adopted in the invention so as to roughly judge background voice, normal voice and remote voice. On the basis of classification of audio signals, by adopting the combined method of a modern signal processing technology and a statistical machine learning theory, the problem of multiple limits on front-end voice input by a traditional method is overcome so that signal-level quality scoring is closer to human scoring. According to the invention, the difference problem of front-end input voice quality due to artificial use errors of the equipment in large-scale tests of spoken language is solved.

Provided is a soft flexible oral appliance having protuberances that mimic naturally occurring dental Tori. An upper, palatial appliance and a lower, mandibular appliance may be used in conjunction or separately to alleviate a variety of disorders, improve facial tone, and increase physical performance. The appliances are lightweight, thin, and do not prohibit normal speech patterns when in use. Small protuberances are strategically molded along key surfaces of each appliance to stimulate nerves in the tongue and affect forward protrusion. Forward positioning of the tongue dilates the airways of the throat improving breathing while the use is sleeping, playing sports, or talking. It also reduces bruxing, or grinding of the teeth. A method is further provided, for adding protuberances to other types of oral appliances, thereby conferring some of the benefits listed above on appliances originally intended for other dental uses.

Method and system for generating electromyographic or sub-audible signals (“SAWPs”) and for transmitting and recognizing the SAWPs that represent the original words and/or phrases. The SAWPs may be generated in an environment that interferes excessively with normal speech or that requires stealth communications, and may be transmitted using encoded, enciphered or otherwise transformed signals that are less subject to signal distortion or degradation in the ambient environment.

A method on a computing device is provided for enhancing the memory and cognitive ability of an older adult by requiring the adult to differentiate between rapidly presented stimuli. The method utilizes a sequence of phonemes from a confusable pair which are systematically manipulated to make discrimination between the phonemes less difficult or more difficult based on the success of the adult. The manipulation includes processing of the consonant and vowel portions of the phonemes by emphasizing the portions, and/or by stretching the portions. Further processing includes separating the consonant and vowel portions by time intervals. As the adult improves in their auditory processing, the discriminations are made progressively more difficult by reducing the amount of processing to that of normal speech.

The invention provides a speech recognition-based unlocking method. According to the speech recognition-based unlocking method, a user (keymaker) read a custom password and a random password at normal speech speed in the front of a door lock, secondary matching verifying is adopted, speed information of the user (keymaker) is collected by the intelligent door lock, speech characteristic extraction is carried out, the speech characteristics are compared with that of the user (keymaker) stored in a cloud server or speech characteristic local database, and cloud terminal can also be used for updating of the speech characteristic local database. The safety and convenience of intelligent door lock unlocking are improved greatly.

The invention discloses a method of converting whispered voice into normal voice based on a radial group neutral network, which comprises two steps of training and converting: respectively extracting line spectrum pair parameters of the whispered voice and the normal voice when in training; seizing mapping relation of spectrum envelope of the whispered voice and the normal voice by using the radial group neutral network; preprocessing the whispered voice when in conversion and extracting the line spectrum pair parameters, converting the line spectrum pair parameters of the whispered voice by the trained radial group neutral network, at last generating a driving source of the voice by using basic frequency mean value of the voice as basic voice frequency, and converting into the normal voice by a line spectrum pair synthesizer. The whispered voice converted by the invention achieves better effect on the respects of intelligibility threshold and tone quality.

The invention relates to the technical field of neural engineering and speech audiometry field and particularly relates to a speech audiometry method based on auditory steady state response. The method comprises steps of generating modulating frequency on an electroencephalogram gamma section, which has audibility first voice stimulation and inaudibility second voice stimulation; simulating a testee by using the first voice stimulation and the second voice stimulation respectively, and recording electroencephalogram signals of the testee during the simulation; and according to electroencephalogram signals, analyzing the strength of the auditory steady state response, and determining whether the testee has the normal speech identification ability. By the aid of the method, the subject factor effect is avoided, the audiometry result can be obtained accurately and objectively, the method is quick and noninvasive, and the speech identification ability determination of the testee, differential diagnosis of deafness and treatment of deaf persons are facilitated.

The invention provides a speech processing method, device and terminal. The method includes in a preset noise filtering mode, collecting speech information; determining whether the collected speech information contains the part matching with the preset speech information or not; if so, synchronizing the preset speech information with the collected speech information, and eliminating the spectrum of the preset speech information to perform noise reduction on the collected speech information. By the aid of the technical scheme, the background noise caused by the preset speech information can be eliminated only, the problem that normal speech except for noise produced by dual microphone noise reduction is eliminated is avoided, the noise eliminating accuracy and communication quality are improved, and the user's experience is improved.

The invention provides a high-frequency cracks processing method which comprises that: the first step: a receiving terminal has a short-time energy analysis on received speech data; the short-time energy of the achieved speech data is compared with an energy threshold value; if the short-time energy of the speech data is greater than the energy threshold value, the speech data is a sonant signal, otherwise, the speech data is a surd signal; the second step: the sonant signal is processed by basetone frequency analysis and the basetone frequency of the received sonant signal is compared with a basetone frequency threshold value; if the basetone frequency of the sonant signal is greater than the basetone frequency threshold value, the sonant signal is a high-frequency cracks signal, otherwise, the sonant signal is a normal sonant signal; the third step: the judged high-frequency cracks signal is analyzed and processed. The invention also provides a high-frequency cracks analytical method. Through the high-frequency cracks processing method and the analytical method provided by the invention, the high-frequency cracks in the normal speech signal can be judged and data source is recorded, further the cause for producing the high-frequency cracks is analyzed, thereby solving the produced problems.

The invention provides a voice evaluation method and device. The voice evaluation method comprises the steps that voice data to be tested are received; voice recognition is conducted on the voice data to be tested to obtain voice recognition data; the voice recognition data are analyzed to defect whether the voice recognition data are abnormal voice data or not, and an evaluation result of the voice data to be tested is generated according to a detection result. The voice evaluation method can detect and recognize abnormal voice, so that abnormal voice is deleted from the voice to be tested, the abnormal voice can not join evaluation of normal voice, influence of the abnormal voice on the evaluation result is greatly reduced, the accuracy of the evaluation result is improved, the evaluation requirement of a user is met, and user experience is improved.

A method on a computing device for enhancing the memory and cognitive ability of an older adult by requiring the adult to differentiate between rapidly presented stimuli. The method utilizes a sequence of phonemes from a confusable pair which are systematically manipulated to make discrimination between the phonemes less difficult or more difficult based on the success of the adult, such as processing the consonant and vowel portions of the phonemes by emphasizing the portions, stretching the portions, and/or separating the consonant and vowel portions by time intervals. As the adult improves in auditory processing, the discriminations are made progressively more difficult by reducing the amount of processing to that of normal speech. Introductory phonemes may each include a blend of a formant-synthesized phoneme and an acoustically naturalistic phoneme that substantially replicates the spectro-temporal aspects of a naturally produced phoneme, with the blends progressing from substantially natural-sounding to substantially formant-synthesized.

The embodiment of the invention discloses a speech data packet loss compensation method and device which are used for compensating for the lost speech data packet. The method comprises the following steps of: when the lost frame is detected, extracting the pitch period from the received speech data; calculating the backward phase of the received last frame of normal speech data; calculating the forward phase of the lost frame according to the backward phase; and capturing the last frame of data with the same phase as the forward phase from the received data as the compensation data.

The invention discloses an estimation method for the fundamental frequency of Chinese whispered speech. The estimation method concretely includes the steps that a whispered speech and normal speech database uniform in linguistic data is set up; LPCC parameters Lw of whispered speech, LPCC parameters Ln of normal speech and fundamental frequency parameters F0 are extracted, and DTW alignment is carried out according to Lw and Ln; F0 of the normal speech is divided within the range of 100-300 Hz at the interval of 5 Hz, and forty intervals are generated in total; aligned vectors are assigned to all the intervals according to F0 values of the normal speech, all whispered speech LPCC vectors in each interval are trained to be a GMM model, the combined vectors formed by all the whispered speech LPCC vectors and the F0 parameters of the normal speech in the corresponding interval are trained be to a GMM model to obtain an estimation function, and forty estimation functions are obtained in total; the LPCC parameters of the whispered speech are extracted and matched with all the GMM models to search for the optimum matching model, and then the F0 values of the whispered speech are estimated according to the estimation function of the model. The fundamental frequency of the whispered speech can be estimated, and the difficulty, caused by the loss of fundamental frequency information, of the Chinese whispered speech is effectively overcome.

The invention relates to the technical field of speech recognition, and provides a signal processing method and terminal equipment. The signal processing method comprises the following steps: extracting feature information from an input signal; determining whether the input signal is an abnormal speech signal or not according to the extracted feature information. In the signal processing method, through the processing process of determining whether the input signal is an abnormal speech signal or not according to the feature information extracted from the input signal, so that the effective recognition of the abnormal speech signal is realized, the accuracy of recognition is improved, and the safety of voice interaction of a user is guaranteed, and the user experience is improved.