46 results about "Speech Processor" patented technology

The invention discloses a system (100) for generating conversational content using a generative artificial intelligence (AI), said system (100) comprising: a user (101), an administrator (102), an application programming interface (API) server (103), a generative artificial intelligence (AI) server (104), a plurality of databases (105), a generative artificial intelligence (AI) processor (106), an audio generate processor (107), a text-to-speech processor / service provider (108), a video generation service (109), a video generation processor (110), and a memory communicatively coupled to the processor, wherein the memory stores processors instructions, which, on execution, causes the processor to generate at least one of conversational script, audio, video, or combination thereof. The system (100) allows users to create and customize various aspects of conversational content, including characters / personas / speakers, groups (of personas / characters / speakers), tones, content types, topics, conversation formats, and tone.

The application discloses a cochlear implant multi-channel stimulation pulse half-wave detection system and method, and relates to the technical field of cochlear implants, in particular to a cochlear implant multi-channel stimulation pulse half-wave detection system and method. The system comprises a test board, a head piece and a speech processor, and further comprises a half-wave detection unit and a multi-channel collector. The test board comprises a receiving coil, a stimulator, a stimulation electrode and a test electrode terminal. The speech processor receives and processes sound signals and encodes the sound signals. The encoded signals are transmitted to the receiving coil through the head piece. After decoding processing by the stimulator, pulse signals with corresponding frequencies and current intensities are generated and transmitted to each stimulation electrode. The stimulation electrode is connected to the test electrode terminal. The test electrode terminal is connected to the multi-channel collector. The multi-channel collector is connected to the half-wave detection unit. The multi-channel collector combines n stimulation electrodes to transmit signals to the half-wave detection unit for half-wave detection. The application utilizes the multi-channel collector and the half-wave detection unit to realize automatic half-wave detection, reduce labor costs, and improve the efficiency and success rate of half-wave detection.

The invention relates to the technical field of virtual simulation, in particular to a clinical nurse emergency simulation training system and method and a medium, and the system comprises AR glasses which are used for presenting a virtual scene; the brain-computer interface is worn on the head of a nurse and used for collecting electroencephalogram signals of the nurse; the physiological data acquisition device is used for acquiring physiological data of nurses; the dummy serves as an entity operated by a nurse, and a sensor is arranged at a preset part and used for collecting operation data of the nurse; the camera is used for collecting first-aid measure images and voice executed by nurses; the processor is connected with the brain-computer interface, the physiological data acquisition device, the AR glasses, the dummy and the camera, and is used for generating an instruction signal based on the electroencephalogram signal and the physiological data and adjusting or improving a virtual scene based on the instruction signal; and based on the first-aid measure image, the voice and the operation data, the accuracy of the first-aid measure of the nurse is judged, and the first-aid training effect on the clinical nurse is effectively improved through the virtual environment.

1. Name of the product in this design: Behind-the-ear speech processor for cochlear implants. 2. Purpose of this design: to receive and process sound signals and convert them into electrical signals that can stimulate the auditory nerve, enabling hearing-impaired patients to regain hearing. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

The invention discloses a sound control household appliance system, intelligent household equipment and a method. The sound-controlled household appliance system comprises a cloud end used for sending a corpus data packet to a smart home device, so that the smart home device receives the corpus data packet through a communication module in a voice integrated module, and configures and stores the corpus data packet through a voice processor; the voice processor is used for performing recognition through the corpus data packet according to the voice received by the audio circuit to obtain a first control instruction corresponding to the voice; the communication module is used for sending the first control instruction to the MCU; the MCU is used for executing a corresponding function according to the first control instruction; and the mobile terminal is used for determining whether to trigger an upgrading instruction according to the version number of the pre-acquired corpus data packet, or sending a second control instruction to the smart home equipment through the cloud, so that the smart home equipment executes a corresponding function according to the second control instruction. According to the invention, the technical effect of improving the configuration flexibility of the smart home equipment can be improved.

A system of fatigue detection includes an image sensor, a voice sensor, a memory and a processor. The image sensor is configured to capture at least one facial image of a driver. The voice sensor is configured to collect a voice of the driver. The memory is configured to store the at least one facial image and the voice. The processor is configured to extract at least one micro-expression feature from the at least one facial image, and establish a fatigue detection model based on the at least one micro-expression feature, and utilize the fatigue detection model to obtain a fatigue detection result. The processor is further configured to utilize a voice detection algorithm to recognize the voice to obtain a voice recognition result. The processor is further configured to determine a mental state of the driver based on the fatigue detection result and the voice recognition result.

The present invention discloses an automatic load detection and audio input source switching circuit, which includes a current detection unit, a switching unit, an audio amplifier, and a voltage converter. Among them, the switching unit is respectively connected to the current detection unit, the audio amplifier, and the voltage converter. The voltage converter outputs different voltages to supply power to the switching unit, the current detection unit, and the input source. The switching unit and the audio amplifier are also respectively connected to the DSP chip of the cochlear implant speech processor. The present invention can automatically detect the input source connected to the external device of the cochlear implant, and can automatically identify the FM receiver or the external direct audio input, without manual intervention, which greatly facilitates the users of cochlear implants. At the same time, low-power devices are adopted in the whole circuit, and only part of the circuit works when the whole circuit is in standby operation. After testing, the static power consumption of the whole circuit is less than 3 μA, which can extend the battery usage time.

The utility model discloses a voice processor, and relates to the technical field of voice processing. The device comprises a protective shell, a voice processing module, an opening and closing assembly and a side baffle, the voice processing module is placed in the protective shell, the opening and closing assembly is installed on the protective shell, and the opening and closing assembly comprises a main opening and closing plate and an auxiliary opening and closing plate. The main opening and closing plate and the auxiliary opening and closing plate are rotationally arranged on the upper side of the protective shell, the main opening and closing plate can drive the auxiliary opening and closing plate to be opened and closed on the protective shell, the side baffles are arranged on the two sides of the protective shell, the dustproof boxes are installed on the side baffles, plug wire interfaces are formed in the dustproof boxes, and the plug wire interfaces are connected with the protective shell. And the plug wire interface is connected with the voice processing module. The voice processor has the advantages that miniaturization is achieved, the voice processor can be compatible with various kinds of hardware, the use cost of the control simulator is reduced, the applicability of the voice processor is improved, and the voice processor is quite convenient to maintain and overhaul.

The invention relates to a hearing device comprising a first microphone for providing a first microphone input signal and a second microphone for providing a second microphone input signal; a voice detector module for processing the first microphone input signal and the second microphone input signal, the voice detector module being configured to detect own voice of a user; a processor for providing an electrical output signal; and a receiver for providing an audio output signal, wherein the voice detector module is configured to determine a direction parameter indicative of a direction of a sound source based on the first and / or the second microphone input signal; to determine whether a direction criterion based on the direction parameter is fulfilled; to determine a first distance parameter indicative of a distance to the sound source; to determine whether a distance criterion based on the first distance parameter is fulfilled; and to provide a voice detector output.

The utility model provides a sound control electric ceramic cooker. The sound control electric ceramic cooker comprises a cooker body assembly, a power supply assembly and a remote control assembly, a heating piece is arranged in the furnace body assembly; the power supply assembly comprises a power supply part, a voice processor and a controller, the voice processor is integrated in the controller, and the power supply part is electrically connected with the controller and the heating part; the controller is electrically connected with the heating piece; the remote control assembly is in signal connection with the controller. Voice control can be achieved, the two hands of a user can be liberated, the control mode of the electric ceramic cooker is more diversified, the cooking efficiency and the user experience are improved, meanwhile, the voice processor and the controller are both arranged on the power source assembly and are far away from the heating piece, operation of the voice processor and the controller cannot be affected when the heating piece conducts heating for cooking, and the user experience is improved. The voice processor and the controller are prevented from being damaged by a high-temperature environment, and the service life of the product is prolonged.

A captioned telephone service (CTS) system provides a transcription service and a speech-to-text and text-to-speech converting service for the deaf or hard-of-hearing user with a speech disorder during a phone call between the user and the peer. The CTS system transcribes the peer's voice into text to be displayed on the user's device. The CTS system transcribes the user's voice into text based on the database storing user's spoken audios and corresponding texts, and converts the text into a clear and articulate speech to be sent to the peer's device instead of the user's voice in order to help the peer better understand what the user said. The CTS system includes a speech-to-text handler and a text-to-speech handler. The speech-to-text handler transcribes user's voice into text using the database, and the text-to-speech handler converts the text into a clear and articulate speech.

The invention relates to a method for realizing monolingual input to multilingual voice playing, which is characterized by comprising the following steps of: acquiring audio by a microphone; the audio is subjected to spectral analysis and feature extraction, is subjected to voice recognition and then is sent to the voice processor; the voice processor is compared with the keyword list and outputs a voice identification number to the MCU main control chip; the MCU main control chip converts the output voice identification number and the selected language into a broadcast language identification number, and compares the broadcast language identification number with a voice file library to take out a compressed voice file; the compressed voice file is decoded and played through the sound-light alarm platform; the voice file is decoded by software, a decoding chip is not needed, the cost is reduced, and the flexibility is improved; keywords and multilingual voice files can be configured.

We provide the system. [Solution] It is a device equipped with an imaging means, and a means for recording images of a dirty area, A means for processing the aforementioned video data and using a machine learning model to identify the type and degree of dirt, A means for determining a method for suggesting the optimal cleaning means and tools based on the identified dirt, A means comprising a voice processor that converts the aforementioned presentation into audio and provides guidance to the user, A means equipped in cleaning equipment that has a patrol function that detects dirt by going around to different locations in the home, A communication means that sends a notification to a smartphone based on the information detected by the aforementioned patrol function, A system that includes this.

A vehicle capable of outputting a sensible response voice to a user's speech command includes: a voice processor that converts the user's speech command into text information and recognizes a domain and an entity name corresponding to the speech command based on the text information; a database that stores a response text corresponding to the domain and the entity name; a speaker; and a control unit that receives information corresponding to the domain and the entity name, modifies the response text stored in the database based on the information corresponding to the domain and the entity name, and controls the speaker to output the modified response text.

A health management system by voice comprises a user interface (10), adapted to interact with an input voice receiver (12), in a user desired language The input voice receiver (12) is provided to receive and convey the input to an audio processor (13). The audio processor (13) is provided to filter audio signals and convey the same to a voice to text processor (14) provided to convert voice instruction into text instructions and convey the same to a disease analysing processor (15). The disease / knowledge analysing processor (15) is provided to process received text instructions and analyse the same in order to diagnose the disease, based on the pre-feed information stored in a server (16) and convey the diagnosis / answers to questions about the disease to a text to voice processor (17) provided to convert the text into voice and convey the same to the user interface (10) into a desired language. An emergency button (18) is provided to activate emergency alarms including sending calls to the emergency contacts and healthcare staff, as well.

A cochlear implant binaural control system, comprising a remote control device and two speech processors, wherein the remote control device is separately connected to the two speech processors by means of BLE and is configured to send control signals to the two speech processors; when one of the speech processors is connected to an audio source, an audio signal from the audio source is transmitted to the speech processor, and the speech processor establishes an radio frequency connection with the other speech processor and transmits the audio signal to the other speech processor. The one remote control device of the cochlear implant binaural control system can simultaneously control the two speech processors on both sides. This not only reduces costs but also facilitates the implantee to control both processors simultaneously, avoiding the need to carry or operate two remote control devices. The implantee's bilateral processors can receive audio from a unified audio source, thereby enabling stereophonic hearing and providing a better listening experience.

The application provides a voice interaction device, system, method, cloud server and medium, wherein the voice interaction device comprises a voice processor, a first communication module, at least one microphone and a voice interaction system, the voice interaction system comprises a second communication module; a first input end of the voice processor is connected with the microphone, a first output end of the voice processor is connected with the first communication module, the voice processor is used for determining that the microphone acquires a first voice signal, and sending the first voice signal acquired by the microphone to a cloud server through a connection established with the cloud server by the first communication module; the voice interaction system is connected with the cloud server through the second communication module, and the voice interaction system is used for receiving a first response signal sent by the cloud server for voice interaction. The application can meet the real-time performance of voice interaction, reduce the power consumption of an electronic device, and thus prolong the endurance time of the electronic device.

The present invention discloses a method and system for a cochlear implant to perform sound scene recognition with the aid of a mobile device, which mainly includes the following steps: after a central processing unit receives a scene recognition abnormality signal, a DSP module transmits the received voice signal to the central processing unit via low-power Bluetooth technology; the central processing unit starts to perform sound scene recognition depth calculation according to the voice signal, and after calculating several frames of sound signals, the central processing unit obtains new scene recognition information and sends it to the DSP module; the DSP module compares the new scene recognition information with the current scene recognition information stored in a register, and if the scene is judged to be different, the sound signal processing strategy corresponding to the new scene is changed, and the characteristic value calculation is restored. The present invention utilizes the low-power wireless voice transmission technology of the speech processor and the stronger computing power of the mobile device to improve the reliability of sound scene recognition, and reduces the device resource usage time and power consumption through distributed computing.

A captioned telephone service system is provided for assisting users with speech disorders in communicating with peers. The system comprises a CTS server, a user device, and a user application configured with a sentence refinement unit and a text-to-speech handler. The user inputs one or more words, which are processed by the sentence refinement unit to correct errors, insert missing grammar, and generate grammatically complete sentences. A contextual adaptation module analyzes conversation and peer information to select the most relevant sentence. The user confirms, regenerates, or edits the sentence, which is then converted to natural speech by the text-to-speech handler and transmitted to the peer's device. The system further employs user and peer databases to learn from prior interactions, thereby improving accuracy and facilitating effective communication for speech-impaired individuals.

An apparatus for speech processing comprises an input (101) arranged to receive an audio signal comprising a speech audio component. A determiner (105) generates a breathing waveform signal from the audio signal, where the breathing waveform signal is indicative of a lung air volume of the speaker as a function of time. A speech processor (103) performs speech processing on the audio signal, where the speech processing depends on the breathing waveform signal. The speech processor (103) may determine one or more respiratory parameters, such as respiratory rate, respiratory volume, timing of inspiratory interval, etc., and may adjust speech processing in response to such respiratory parameters. The speech processing may typically be speech enhancement or speech recognition processing.

The invention relates to the technical field of artificial cochlea, in particular to a titanium alloy artificial cochlea which comprises a shell, the shell comprises a circular ring, a reinforcing block is arranged in the circular ring, a supporting column is arranged at the center of the top of the reinforcing block, and the top of the supporting column is connected with a shell through a circular truncated cone. And a voice processor, a master control system and a simulation system are arranged in the shell. According to the invention, the durability and safety of the device are improved, the device has excellent corrosion resistance and biocompatibility, the service life of the device can be effectively prolonged, the damage caused by the external environment is reduced, the titanium alloy is mild in reaction to the human body, allergy or rejection reaction is not easy to cause, the comfort and safety after implantation are ensured, and the device is suitable for popularization and application. Therefore, the titanium alloy artificial cochlea can provide more stable and reliable performance during long-term wearing, and the overall use experience of a patient is improved.

A cochlear implant system for processing polyphonic pitch includes an electrode array for implanting in a cochlea of a patient. The electrode array includes a first set of electrodes, where each electrode of the first set is for implanting on a first region of the cochlea. The electrode array also includes a second set of electrodes, where each electrode of the second set is for implanting on a second region of the cochlea. The system also includes a sound processor configured to capture a sound signal having polyphonic pitch. For each electrode of the first set and second set, the speech processor generates at least two different modulated frequency signals from the sound signal, such that each of the modulated frequency signals corresponds to a different pitch in the sound signal. The speech processor stimulates the electrode by simultaneously applying the at least two different modulated frequency signals.

An external speech processor of a cochlear implant based on a clock image method-based cochlear implant data transmission protocol according to an embodiment defines an NP2 interface and an NP2 protocol to stably capture NP2 data transmitted using an NP2 clock internally restored at a period inferred by a conversion chip from data transmitted by a speech processing chip even in a situation where a clock period of the speech processing chip and a clock period of the conversion chip are not related to each other at all. In addition, the external speech processor of a cochlear implant based on a clock image method-based cochlear implant data transmission protocol according to the embodiment stores the amount of data period variation during 12 bits in a buffer through a clock image, which is a snap-shot for a predetermined section, and repeatedly uses same. In the embodiment, all count values are stored as one data set and the stored data set is used. That is, in the embodiment, it is assumed that the sum of period changes of each bit during 12 bits and the sum of period changes of each bit during next 12 bits will have the same amount of variation, and each bit during the next 12 bits is captured at different time points according to the period of each bit stored in the buffer.

An apparatus for speech processing comprises an input (101) arranged to receive an audio signal comprising a speech audio component. A sectionalizer (105) generates segments of the audio signal, wherein a time interval between consecutive segments has an inter-segment duration less than the segment duration. A first generator (107) generates a segment of the respiratory waveform signal for each segment of the audio signal, and a second generator (109) generates the respiratory waveform signal by combining the segments of the respiratory waveform signal by applying a weighted combination to samples of different segments for the same moment in time, where the weight is determined according to a segment window function. A speech processor (103) performs speech processing of the audio signal, where the speech processing depends on the breathing waveform signal. The speech processor (103) may determine one or more breathing parameters, such as breathing rate, breathing volume, timing of inspiratory interval, and the like, and may adapt speech processing in response to such breathing parameters.

A vehicle-mounted device operation system, includes: an operating part that is located in a vehicle cabin, and configured to be subjected to operation for manually operating a vehicle-mounted device; a sound collector that is located in the vehicle cabin, and configured to collect speech of an occupant; and a processor configured to determine whether a command to the vehicle-mounted device is included in a content of the speech of the occupant collected by the sound collector, activate the vehicle-mounted device according to the command, when the processor determines that the command to the vehicle-mounted device is included in the content of the speech of the occupant, and highlight the operating part for the vehicle-mounted device activated by the processor.

The invention discloses an artificial cochlea speech processor with an external microphone, which comprises a speech processor body and further comprises an external microphone module arranged outside the speech processor body, and the speech processor body is further provided with a terminal capable of being connected with the external microphone module; the speech processor body comprises an audio amplification circuit, and the wiring terminal is connected to the audio amplification circuit; the external microphone module comprises an electret microphone; the electret microphone is connected with the audio amplification circuit through the wiring terminal; or, the external microphone module comprises an electret microphone and an audio amplification circuit, the electret microphone is connected with the audio amplification circuit, and the audio amplification circuit is connected with the speech processor body through the wiring terminal; according to the artificial cochlea speech processor with the external microphone, the external wired microphone is added, so that when the internal microphone of the speech processor works abnormally, the external wired microphone can be adopted for an implanter to hear sound.

The invention relates to the technical field of intelligent equipment, in particular to a barrier-free reply system. According to the barrier-free reply system provided by the invention, the technical problem that the content output by the deaf-mute cannot be played in a sound mode when the deaf-mute has a conversation in the prior art is solved. A barrier-free reply system comprises a recognizer; a voice processor, wherein the voice processor is in communication with the recognizer; reply content data are stored in the reply content storage device; a reply content selector for selecting reply content data stored in the reply content memory; according to the application scene and the context, several replies are preset for the question of the user to be selected by the deaf-mute, after the deaf-mute selects one reply, the reply is converted into voice, and the voice is played to the other party in the form of sound through the reply content output device worn by the deaf-mute, so that the deaf-mute can effectively communicate with others.

The present invention provides a sound processing device (1), which is portable and according to which a speaker uses an auxiliary device and so that a hearing-impaired person can easily listen to sound without using an auxiliary device. The sound processing device (1) comprises: a sound processor (10) for performing sound processing to make sound clear for a sound signal supplied from a microphone (21); a speaker (22) that converts the sound signal having been subjected to the sound processing into sound; and a housing that houses the sound processor (10).

The utility model relates to the technical field of water valve timers, in particular to a water valve timer with voice recognition, which comprises an MCU (Microprogrammed Control Unit), a Bluetooth module connected with the MCU, a power supply module, a timer, a voice processor connected with the Bluetooth module, and a microphone and an AI (Artificial Intelligence) cloud which are connected with the voice processor, the power supply module is used for providing a driving power supply for the MCU; the MCU is used for receiving a voice command fed back by the Bluetooth module and outputting an execution command to the PLC for control; the microphone is used for collecting voice of a user; the AI cloud is used for recognizing voice and converting the voice into a corresponding voice instruction; the voice processor is used for distinguishing and recognizing the collected voice and judging whether the collected voice is matched with the execution voice or not. On the basis of the water valve timer, the voice control function is expanded, the defects of a traditional water valve timer are overcome, and a user can select a traditional operation mode or a voice control mode according to own preferences.