939 results about "Sound recognition" patented technology

Disclosed is a remote control device that interacts with a set-top box to provide selective programming and / or enhanced content based upon the identity of the user of the remote control. The present invention utilizes preference and profile data corresponding to the current user to control the video output and / or enhanced content of the display. The present invention can also select or exclude video or enhanced content based upon tags that describe video content and the identity of the user based upon the use of a personalized remote control. The present invention can employ recognition techniques, such as word recognition, image recognition and sound recognition to restrict or select video content based upon the identity of the user of a personalized remote control device.

A sound control system and method applicable to an electronic device having a timing unit. A setting module is provided to set predetermined conditions and corresponding sound volume parameters. A time session control module retrieves the sound volume parameter corresponding to a present condition obtained by the timing unit. Then, a corresponding sound output signal to be outputted by a speaker unit connected to the sound control system is set via a sound effects module according to the sound volume parameter and a sound signal around the electronic device that is received and recognized by a sound recognition module. By such arrangement, the sound control system and method allow the electronic device to provide the user with optimal sound effects depending on the environment and the user's preferences.

Targeted sound detection methods and apparatus are disclosed. A microphone array has two or more microphones M0 . . . MM. Each microphone is coupled to a plurality of filters. The filters are configured to filter input signals corresponding to sounds detected by the microphones thereby generating a filtered output. One or more sets of filter parameters for the plurality of filters are pre-calibrated to determine one or more corresponding pre-calibrated listening zones. Each set of filter parameters is selected to detect portions of the input signals corresponding to sounds originating within a given listening zone and filter out sounds originating outside the given listening zone. A particular pre-calibrated listening zone is selected at a runtime by applying to the plurality of filters a set of filter coefficients corresponding to the particular pre-calibrated listening zone. As a result, the microphone array may detect sounds originating within the particular listening sector and filter out sounds originating outside the particular listening zone. Sounds are detected with the microphone array. A particular listening zone containing a source of the sound is identified. The sound or the source of the sound is characterized and the sound is emphasized or filtered out depending on how the sound is characterized.

A neural network is provided for recognition and enhancement of multi-channel sound signals received by multiple microphones, which need not be aligned in a linear array in a given environment. Directions and distances of sound sources may also be detected by the neural network without the need for a beamformer connected to the microphones. The neural network may be trained by knowledge gained from free-field array impulse responses obtained in an anechoic chamber, array impulse responses that model simulated environments of different reverberation times, and array impulse responses obtained in actual environments.

The invention provides a crime monitoring method based on the face recognition technology and behavior and sound recognition, which includes the following steps: Step 1, recoding a video through a camera, reducing dimensions of the video to form a picture message ensemble; Step 2, performing the recognition comparison to the picture message ensemble as per an intelligent behavior pattern, and issuing an early warning and storing the video if the comparison is successful; and Step 3, verifying the crime situation by a police on duty, confirming the position of the camera through a GPS for positioning and tracking and confirming the police strength nearby, and sending crime situation to polices nearby by the police on duty, and if no police is on duty, confirming the position of the camera automatically through the GPS for positioning and tracking and confirming the police strength nearby, and sending crime situation to polices nearby and staff on duty. According to the invention, different intelligent behavior patterns are set as per the monitoring requirements of different situations, targeted monitoring is introduced, early warning prevention in advance is realized, the case is prevented from further worsening, the time in solving a criminal case is shortened, and the detection rate is improved.

The invention discloses an online learning system which comprises a courseware database module, a management module, and a student learning situation monitoring module. The student learning situation monitoring module comprises a face recognition module, a facial expression analysis module, a video scene analysis module, a sound recognition module, a monitoring video storage module, and a video acquisition module, and the like. The learning situation monitoring module can be applied to monitor the student learning and exam situations in real time, thereby preventing other people from taking learning and tests for someone, and improving the learning efficiency of students.

A low power sound recognition sensor is configured to receive an analog signal that may contain a signature sound. Sparse sound parameter information is extracted from the analog signal. The extracted sparse sound parameter information is processed using a sound signature database stored in the sound recognition sensor to identify sounds or speech contained in the analog signal, wherein the sound signature database comprises a plurality of sound signatures each representing an entire word or multiword phrase.

A drive recorder 1 comprises a volatile memory 15, a nonvolatile memory 16, an image collection unit 111 that stores in real-time image data into the volatile memory 15, an acceleration collection unit 112, a sound collection unit 113 that stores in real-time sound data into the volatile memory 15, an acceleration comparison unit 114 that determines in real-time whether the acceleration exceeds a threshold value, a sound recognition unit 115 that determines if the sound data includes an accident sound which is a distinctive sound that is generated at an accident, by performing sound recognition on sound data when the acceleration exceeds the threshold value, and a data transcribe unit 116 that transcribes image data stored in the volatile memory 15 into the nonvolatile memory 16 when it is determined that the accident sound is included in the sound data.

A system and method related to a new approach to speech recognition that reacts to concepts conveyed through speech. In its fullest implementation, the system and method shifts the balance of power in speech recognition from straight sound recognition and statistical models to a more powerful and complete approach determining and addressing conveyed concepts. This is done by using a probabilistically unbiased multi-phoneme recognition process, followed by a phoneme stream analysis process that builds the list of candidate words derived from recognized phonemes, followed by a permutation analysis process that produces sequences of candidate words with high potential of being syntactically valid, and finally, by processing targeted syntactic sequences in a conceptual analysis process to generate the utterance's conceptual representation that can be used to produce an adequate response. The invention can be employed for a myriad of applications, such as improving accuracy or automatically generating punctuation for transcription and dictation, word or concept spotting in audio streams, concept spotting in electronic text, customer support, call routing and other command / response scenarios.

A home appliance diagnostic system and method are disclosed. A home appliance outputs product information in the form of a sound signal, which is transmitted to a service center at a remote site over a communication network so that the service center can readily check the state of the home appliance. The home appliance performs a sound signal re-output operation in such a manner that it re-outputs the same product information in the form of a different sound signal. Therefore, it is possible to improve a sound recognition rate, so as to improve fault diagnosis accuracy.

A speech recognition control device has a plurality of microphones placed at different positions, a speech transmission control unit, and a speech recognition execution control unit. The speech transmission control unit stores data based on the speeches which are input from the microphones and time data related to ranks among the microphones, assigns ranks to the plurality of microphones using the time data based on a preset condition, and transmits a speech data signal corresponding to the microphone to the speech recognition execution control unit in the order of the ranks. The speech recognition execution control unit executes the speech recognition process according to the order of the speech data signals transmitted from the speech transmission control unit.

The present invention relates to a method for identifying a sound event, and problems of low accuracy of sound identification and poor robustness under a strong interference condition in the prior artare mainly solved. The method comprises a step of collecting and processing sound under different interference environments and forming a sound digital signal, a step of carrying out sub-band filtering on the sound digital signal by a filter group and obtaining a cochlear spectrum of an audio signal, a step of training a part of the cochlear spectrum into a convolution neural network model and establishing a sound recognition template, and a step of substituting the other part of the cochlear spectrum into the convolution neural network model and detecting the accuracy of sound recognition. According to the above method, the problem is solved, and the method can be used for identifying the sound event in a traffic environment.

A simplified TV viewer response system coupled to a telephone system enables a viewer / subscriber to respond to television displays by dialing a special code less than six digits. The code is routed to an enhanced services server. The server captures the dial string including the caller ID, checks the caller ID against a subscriber / viewer profile and maps the caller ID to the cable company providing service to the viewer / subscriber. The server delivers the response to the cable television company which processes the response according to the selected items or choices in the TV screen. Several special dialing codes of limited digits expedite viewer / subscriber selections. Each code includes a special character to route the dialing string to the server. The system provides sound recognition of viewer / subscriber selections.

The invention relates to a pan and tilt camera with a sound identification and positioning function, which comprises a camera, a pan and tilt servo module and a pan and tilt control module, and the pan and tilt control module is respectively connected with the camera and the pan and tilt servo module. The pan and tilt camera has the following main technical characteristics that: the input end of the pan and tilt control module is connected with a sound identification and positioning module, and the input end of the sound identification and positioning module is connected with a highly directional sound pickup fixed on the pan and tilt camera. The design of the pan and tilt camera is reasonable, and the pan and tilt camera can identify and position the sound of a monitored site; when abnormal sound occurs, the pan and tilt camera can be controlled to aim at the direction of the sound source and shoot in order to timely acquire the video of an abnormal incident, and can send alarm information on the abnormal sound and the like to a monitoring center; the sound pickup distance is increased, the sound pickup effect are improved, the efficiency of capturing sound and other abnormal incidents is increased, and thereby the working efficiency of monitoring personnel can be increased.

The present disclosure relates to sound and speech recognition devices and methods. A system is provided that utilizes a system of tonal and rhythmic visualization methods to recognize different sounds so as to accurately identify true security problems in a cost effective manner. The system can also be utilized to recognize different vocal characteristics so as to accurately identify individuals based on their speech.

The invention discloses an auditory perception and intelligent decision making system of an unmanned vehicle. The auditory perception and intelligent decision making system includes an auditory perception system and an intelligent decision making system; the auditory perception system includes a sound source positioning system and a sound identification system. The sound source positioning system positions the location and relative direction of a sound emitting source and transmits positioning results to the sound identification system and the intelligent decision making system; the sound identification system classifies and identifies sound source positioning information and transmits results to the intelligent decision making system; the information acquisition module of the intelligent decision making system receives sound information transmitted by the sound source positioning system and the sound identification system; an information processing and decision making module analyzes and processes the sound information and calculates lane changing and avoidance schemes of the unmanned vehicle; and a control execution module controls the behaviors of the unmanned vehicle and makes effective response.

The invention provides a listening assisting method and system based on a mobile device. The listening assisting method includes the steps of outputting testing voices at a plurality of frequencies to test listening thresholds of users at the multiple frequencies, and generating listening curve graphs according to the listening thresholds of the users under the multiple frequencies; judging the listening loss types of the users according to the listening curve graphs, and selecting corresponding prescription selecting formulas according to the listening loss types; determining fitting parameters of the users according to the prescription selecting formulas and the listening curve graphs; collecting voice signals, and conducting sound recognition rate improving processing on the voice signals according to the fitting parameters of the users for playing. By means of the listening assisting method and system, the listening loss conditions of the users can be tested through the mobile device, the listening curve graphs of the users can be automatically recorded, automatic fitting can be carried out according to the different listening curve graphs of the users, listening compensation is carried out in a target mode, and the audiometry function of an audiometer, the fitting function of hearing-aid fitting software and the function of a hearing-aid are integrated.

Security system for public places controlled remotely, manually and by a computer program, using cameras and various weapons. Using amongst other methods of crisis identification; facial recognition, behavior recognition and sound recognition. Methods to neutralize the danger of suspect attackers. Useable in public buildings, at public gatherings, on public transport and the like.

A low power sound recognition sensor is configured to receive an analog signal that may contain a signature sound. The received analog signal is evaluated using a detection portion of the analog section to determine when background noise on the analog signal is exceeded. A feature extraction portion of the analog section is triggered to extract sparse sound parameter information from the analog signal when the background noise is exceeded. An initial truncated portion of the sound parameter information is compared to a truncated sound parameter database stored locally with the sound recognition sensor to detect when there is a likelihood that the expected sound is being received in the analog signal. A trigger signal is generated to trigger classification logic when the likelihood that the expected sound is being received exceeds a threshold value.

An apparatus and method for merging acoustic object information to provide an Augmented Reality (AR) service in which real images are merged with sounds. The acoustic object information merging apparatus includes an acoustic objectization unit, an acoustic object information creator and a merging unit. The method classifies sounds received in a microphone array to identify an object corresponding to the received sound. If there is a failure to identify an object for each sound, then a band-pass filter is applied to secondarily classify the received sounds. Acoustic object information is created and merged with a captured image or recorded sound. The acoustic object information may include additional information about the object identified as corresponding to the received sound.

An ambient sound retrieving device includes a sound input unit receiving a sound signal, a sound recognition unit performing a speech recognition process on the sound signal and generating an onomatopoeic word, a sound data storage unit storing an ambient sound and an onomatopoeic word corresponding to the ambient sound, a correlation information storage unit storing correlation information in which a first onomatopoeic word, a second onomatopoeic word, and a frequency of selecting the second onomatopoeic word are correlated with each other, a conversion unit converting the first onomatopoeic word into the second onomatopoeic word corresponding to the first onomatopoeic word using the correlation information, and a retrieval and extraction unit extracting the ambient sound corresponding to the second onomatopoeic word from the sound data storage unit and ranking and presenting a plurality of candidates of the extracted ambient sound.

The present disclosure relates to sound recognition devices and methods. A system is provided that utilizes a system of tonal and rhythmic visualization methods to recognize different environmental sounds so as to accurately identify certain species of wildlife and other elements of nature.

A voice recognition apparatus includes: a voice recognition module that performs a voice recognition for an audio signal during a voice period; a distance measurement module that measures a current distance between the user and an voice input module; a calculation module that calculates a recommended distance range, in which being estimated that an S / N ratio exceeds a first threshold, based on the voice characteristic; and a display module that displays the recommended distance range and the current distance.

An apparatus and method for controlling a user interface using sound recognition are provided. The apparatus and method may detect a position of a hand of a user from an image of the user, and may determine a point in time for starting and terminating the sound recognition, thereby precisely classifying the point in time for starting the sound recognition and the point in time for terminating the sound recognition without a separate device. Also, the user may control the user interface intuitively and conveniently.

The invention discloses an automobile theft prevention monitoring system based on a voice recognition technology. By the system, a user can accurately detect whether automobile glass is broken into pieces, and a thief enters the automobile for theft, an active theft prevention technology is adopted, a third-generation mobile communication (3G) technology is fully utilized, and multiple alarm methods are adopted. An embedded computer is respectively connected with a key, a microphone, a display, a camera, a storage, a global position system (GPS) positioner, a theft prevention door lock, a theft prevention engine lock, a passive infrared detector, a transaction detector, a frequency analyzer and a 3G wireless signal transceiver, wherein the transaction detector is connected with a vibrating sensor; a filter is respectively connected with the frequency analyzer and a glass breaking detector; the 3G wireless signal transceiver is respectively in wireless connection with a 3G mobile phone and a 110 alarm console; and the 3G mobile phone is in wireless connection with the 110 alarm console. The system is mainly applied to automobile theft prevention system, and can be applied to the financial field of banks and the like.

The invention discloses an intelligent range hood which comprises an enclosure, a fan device and an intelligent control system, and the intelligent range hood is characterized in that the intelligent control system comprises a sound acquisition unit, a sound identification unit, a starting control unit, a cooking sound output control unit and a power control unit. Compared with the prior art, the intelligent range hood disclosed by the invention has the advantages that various environment sounds in a kitchen are detected by analyzing the sounds in the kitchen, so that the range hood can judge whether the sounds are made in a cooking process and determine the level of the lampblack quantity corresponding to the cooking sounds; start or stop of the range hood is set and the rotating speed of a fan is adjusted according to the level of the lampblack quantity, so that the aim of intelligently controlling the range hood is fulfilled; control on the range hood is realized by a sound identification technology, so that the execution cost is relatively low; the phenomenon that detection equipment fails in working or the sensitivity of the detection equipment is reduced because of the influence and the pollution of smoke is unlikely to occur; reliable work of the range hood can be guaranteed, and the service life of the range hood is prolonged.

A low power sound recognition sensor is configured to receive an analog signal that may contain a signature sound. Sparse sound parameter information is extracted from the analog signal and compared to a sound parameter reference stored locally with the sound recognition sensor to detect when the signature sound is received in the analog signal. A portion of the sparse sound parameter information is differential zero crossing (ZC) counts. Differential ZC rate may be determined by measuring a number of times the analog signal crosses a threshold value during each of a sequence of time frames to form a sequence of ZC counts and taking a difference between selected pairs of ZC counts to form a sequence of differential ZC counts.

The invention provides a monitoring method based on sound recognition and a monitoring device and system thereof. The method comprises the following steps that S1: multiple types of specific sound is acquired in advance to perform sound model training so as to obtain trained sound models; S2: onsite sound is acquired, and feature extraction corresponding to multiple types of specific sound is performed on the acquired sound; S3: the extracted features and the sound models are matched and classified so as to obtain the classification result of the onsite sound; and S4: the requirement of alarm is judged according to the classification result. The insufficiency of conventional video monitoring can be compensated, and the sound and the video are cooperated so as to better monitor the complex environment in real time. Besides, the efficiency of preventing and combating criminal activities can be enhanced, and initiative and timeliness of the monitoring system for unsafe event monitoring can be ensured.

When having obtained sound singles transmitted / received among plural terminal apparatuses, a sound recognition unit of a conference server performs a sound recognition processing on the obtained sound signals and then generates text information. A language analyzing unit of the conference server performs a language analysis processing on the text information generated by the sound recognition unit and then disassembles the text information into words. A deciding unit of the conference server compares the disassembled words and a keyword database, and decides whether or not any keyword stored in the keyword database is contained in each sentence of speech contents of respective speakers. A totalizing unit calculates a cumulative score based on the decision result of the deciding unit which represents a state of a discussion, and then it is decided in accordance with the calculated cumulative score whether or not the discussion matches to the subject.