186 results about "Speech acquisition" patented technology

To enable determining the correlation between customer satisfaction and employee satisfaction, a speech acquisition unit 102 acquires conversations between employees and customers; an emotion recognition unit 155 recognizes employee and customer emotions based on employee and customer speech in the conversation; a satisfaction calculator 156, 157 calculates employee satisfaction and customer satisfaction based on the emotion recognition output from the emotion recognition unit 155; and a customer service data recording unit 159 relates and records employee satisfaction data denoting employee satisfaction and customer satisfaction data denoting customer satisfaction as customer service data in a management server database DB.

A method and a wearable communication system for personal face-to-face and wireless communications in high noise environments are provided. A noise cancellation device (NCD) operably coupled to a wireless coupling device (WCD) includes a speech acquisition unit, an audio signal processing unit, one or more loudspeakers, and a communication module. The NCD receives voice vibrations from user speech via a contact microphone and a second microphone and converts the voice vibrations into an audio signal. The NCD processes the audio signal to remove noise signals and enhance a speech signal contained in the audio signal. A loudspeaker emits the speech signal during face-to-face communication. The NCD transmits the speech signal to a communication device via the WCD and receives an external speech signal from the communication device during wireless communication. With the NCD, the signal intelligibility and signal-to-noise ratio can be improved, for example, from −10 dB to 20 dB.

The present invention provides an electric appliance speech control method and device and a speech control air-conditioner, wherein the method comprises the steps of receiving an awakening instruction, and awakening an electric appliance of a standby state according to the awakening instruction; after the electric appliance is awakened, obtaining the speech information from a speech acquisition device; matching the speech information with the instruction information in a speech instruction list; according to a matching result, determining a control instruction corresponding to the instruction information, and controlling the electric appliance according to the control instruction. According to the scheme provided by the present invention, the energy consumption of the electric appliance can be reduced while the electric appliance speech control is realized.

The present invention provides a speech control method and a home appliance control system. The home appliance system includes a plurality of electric devices each of which is in data connection witha cloud controller; at least a part of the plurality of electric devices are configured with speech acquisition devices which are adopted as speech interaction devices. The speech control method of the home appliance system includes the following steps that: a plurality of speech interaction devices acquire surrounding speech signals by using the respective acquisition collection devices; the acquired speech signals are identified, the signal parameters of the speech signals are extracted, and whether the speech signals are matched with preset wake-up signals is judged; and speech interactiondevices which receive the speech signals matched with preset wake-up signals send the signal parameters of the received speech signals, so that the cloud controller can select a speech response devicefrom the speech interaction devices according to the parameters of the speech signals; and the cloud controller issues a control instruction for enabling the speech response device to enter a speechresponse state to the speech response device.

This invention presents a noise cancellation device for improved personal face-to-face and radio communications in high noise environments. The device comprises speech acquisition components, an audio signal processing module, a loudspeaker, and a radio interface. With the noise cancellation device, the signal-to-noise ratio can be improved by as much as 30 dB.

A conference system including a microphone array unit having a plurality of microphone capsules arranged in or on a board mountable on or in a ceiling of a conference room. The microphone array unit has a steerable beam and a maximum detection angle range. The conference system further includes a processing unit which is configured to receive the output signals of the microphone capsules and to steer the beam based on the received output signal of the microphone array unit. The processing unit is configured to control the microphone array to limit the detection angle range to exclude at least one predetermined exclusion sector in which a noise source is located.

A terminal includes a speech acquisition unit that acquires first speech information, a first speech processor that removes noise contained in the first speech information using a first removal method and outputs the noise-removed speech information as second speech information, a first speech recognition unit that performs speech recognition on the second speech information and outputs the speech recognition result as first speech recognition result information, a communication unit that receives a speech recognition result as second speech recognition result information from a server, the speech recognition result being a result obtained by performing speech recognition on third speech information, the third speech information being obtained by removing noise contained in the first speech information using a second removal method that removes a larger amount of noise than the amount of noise removed from the first speech information using the first removal method, and a determination unit that makes a selection as to which of the first speech recognition result information and the second speech recognition result information should be outputted.

The invention discloses an evaluation method for a student reading assignment for oral practice. The method includes that a first text model L1 which a specified text corresponds to is established by a language model, the first text model L1 is designed to be a second text model L2 with competitive capacity according to a confused vocabulary list and a confused pronunciation list which the specified text corresponds to, a speech file read by a user is acquired through a speech acquisition device, a sound track is revaluated to obtain a revaluated speech file, a speech recognizer is guided by the model L2 to recognize the revaluated file to obtain a recognized text, and comparison and judgment with confidence degree weighing are performed for the recognized text and the specified text. By means of the evaluation method for the student reading assignment for the oral practice, acquired speech file can be accurately and efficiently recognized and judged.

The invention relates to a smart home control system and method. The system includes a speech acquisition unit which acquires speech information and sends the speech information to a network-to-network connector, the network-to-network connector used for connecting a plurality of terminals and includes a speech recognition unit used for analyzing the speech information to generate control instructions, and the terminals which are used for receiving the control instructions to execute corresponding operation. With the technical schemes of the invention adopted, a speech recognition function can be realized through a gateway, speech recognition work can be completed through the operational capability of a gateway processor, a corpus can be further subdivided through a face recognition unit, and therefore, the speed of speech recognition can be improved; the matching time of speech in the corpus is recorded, and the division of the speech in the corpus in the time dimension can be further realized according to user' behaviors, and therefore, the speech information can be analyzed more accurately, so that the control instructions can be obtained.

A conference system including a microphone array unit having a plurality of microphone capsules arranged in or on a board mountable on or in a ceiling of a conference room. The microphone array unit has a steerable beam and a maximum detection angle range. The conference system further includes a processing unit which is configured to receive the output signals of the microphone capsules and to steer the beam based on the received output signal of the microphone array unit. The processing unit is configured to control the microphone array to limit the detection angle range to exclude at least one predetermined exclusion sector in which a noise source is located.

A 2.3 kb / s speech coding technique with harmonic excitation and linear prediction is disclosed. The speech signals are acquired by speech acquisition system and then inputted to the processor of computer. The fundational tone detecting method and voiced sound analysis method are used to split the LPC exciting signal into lower band associated with voised sound and higher band relative to voiceless sound. A united harmonic model with a fixed phase spectrum of voiced sound of man speech is used to express the harmonic component and pseudo-noise component. An interpolation method is used to reduce noise. A short-lag filter is used for high quality of synthetic speech.

The invention relates to an intelligent household system based on speech recognition. The system is characterized in that: the system comprises: a plurality of speech acquisition units possessing wireless data transmission functions and a host; the host comprises: a microprocessor, a speech pretreatment module which connected with the microprocessor, a 485 communication module and a storage module; the 485 communication module is connected with a household appliance entrance guard controller; the speech acquisition units transmits collected speech data to the speech pretreatment module through a wireless communication mode so as to carry out amplification, denoising and framing processing; then, a processed speech signal is compared with the speech model data stored in the storage module; the microprocessor controls the household appliance entrance guard controller through the 485 communication module according to a comparative value. The system of the invention can perform speech intelligence control to the entrance guard and the household appliance through the speech recognition. A user does not need to run to a switch position of the corresponding household appliance or the entrance guard to carry out controlling. The user can remotely control the household appliance through a telephone or a mobile phone. A user experience of the intelligent household can be increased.

The invention provides a depression automatic evaluation system and method based on phonetic features and machine learning. On the basis of speech processing, feature extracting and machine learning technologies, the system and method search for the relations between phonetic features and depression, and provide objective references for clinical diagnosis of depression. The system includes 1, a speech acquisition recording module for recording speech information of testees at different emotional and communication stimulation; 2, a speech feature calculating module for calculating acoustic features of the speech, 3, a speech database module containing relative data for speech feature efficiency analysis, classifier training optimization and a system classification rate; 4, a machine learning module for determining an extracting mode of effective features and training a classifier for automatic evaluation; 5; an automatic evaluation module. The system and method conduct depression degree classification on the effective speech features of the testees according to the extracting mode of the effective features and a classification mode of the trained classifier.

The invention relates to a speech processing method, a router and an intelligent speech control system. The speech processing method comprises the steps that: the router receives a plurality of speech signals sent by a plurality of sets of speech acquisition equipment, the router determines a first speech signal with the maximum signal intensity from the plurality of speech signals, analyzes and processes the first speech signal, and determines equipment to be controlled and an operation instruction corresponding to the first speech signal; and the router transmits the operation instruction to the equipment to be controlled, so that the equipment to be controlled executes corresponding operation according to the operation instruction. The speech processing method, the router and the intelligent speech control system provided by the invention enable intelligent speech control to be free of distance limitation, and can achieve speech control over intelligent equipment regardless of the distance between a user and the intelligent equipment.

The embodiment of the invention provides a multi-tone area speech recognition method and device, and a computer-readable storage medium. The multi-tone area speech recognition method comprises the steps: collecting speech in a speech acquisition environment using a microphone module, wherein a target tone area is set for each microphone in the microphone module in advance, the target tone area being one of a plurality of independent tone areas in the speech acquisition environment set in advance; Judging whether the speech is from a target sound region; Suppressing speech from a sound region other than the target sound region; the suppressed speech is recognized. As the embodiment of the invention use a microphone module to isolate different sound regions, the voice use by all the staff inthe voice acquisition environment is realized by isolating a plurality of sound regions, and the isolation degree of each sound region can reach 15-20dB, the ideal isolation effect is achieved.

A chatting robot system based on a fuzzy neural network comprises a speech acquisition terminal, a characteristic extracting module, a matching searching module, a fuzzy neural network analysis module, a speech postprocessing module and a speech broadcasting module, wherein the characteristic extracting module is connected with the speech acquisition terminal, the matching searching module is provided with a sound model data base and connected with the characteristic extracting module, the fuzzy neural network analysis module is connected with the matching searching module, the speech broadcasting module is connected with the matching searching module, the speech broadcasting module is connected with the speech postprocessing module, and the fuzzy neural network analysis module is provided with a fuzzy neural network training data base and a knowledge data base. According to the chatting robot system based on the fuzzy neural network and a chatting method, the technologies of fuzzy recognition, pattern matching searching, a artificial neural network and the like are utilized, the fuzzy reasoning process of thinking and speeches of the human brain is simulated, a reply can be made according to contexts and emotion characteristics, and the system has the self-learning ability in different scenarios.

The invention discloses a speech control device, a speech control system and a speech control method. The device comprises a speech acquisition module for receiving speech signals; a speech recognition module for generating speech characteristics according to the speech signals, carrying out judgment on the speech characteristics according to a current working mode of the speech control device, and generating a speech command when judging that the speech characteristics are matched with speech samples corresponding to the current working mode; a first communication module for wireless communication with an intelligent terminal; and a control module for generating a control instruction according to the speech command and sending the control instruction to the intelligent terminal through the first wireless communication module to enable the intelligent terminal to work according to the control instruction. Therefore, the speech control device, system and method can work in a working mode meeting user speech situations according to user selection and improve speech recognition accuracy, can also meet different requirements of different users for speech control and can carry out speech control on the intelligent terminal, such as voice waking.

A parking lot system includes a camera that photographs an image including a number plate of a vehicle, and generates a first image; an image analysis section that performs a number analysis processing to analyze the first image and acquire number information described on the number plate of the vehicle; a storage section that stores the number information and parked position information of the vehicle associated with one another; a speech acquisition section to acquire the voice of the user; a speech recognition section that performs a speech recognition processing on the voice; and an output section that performs an output processing to retrieve the number information from the storage section based on the result of the speech recognition processing and notifies the user of the parked position information.

The invention provides a speech pickup device and a multimedia device. The device comprises an image acquisition unit which is used for acquiring an image, a face recognition unit which is electrically connected with the image acquisition unit to carry out face recognition on the acquired image, a speech acquisition unit which is used for acquiring a speech signal, a steering adjusting unit which is connected with the speech acquisition unit to adjust the orientation of the speech acquisition unit, and a processing control unit which is electrically connected with the image acquisition unit, the face recognition unit, the speech acquisition unit and the steering adjusting unit. The processing control unit controls the steering adjusting unit to align the speech acquisition unit with the orientation of a face when the face recognition unit recognizes that the face is in the acquired image and controls the speech acquisition unit to acquire the speech signal of the orientation of the face. The device is capable of automatically steering to carry out oriented speech pickup on the speech signal sent by a user according to the face position of the user to reduce external noise interference.

The present invention discloses an abnormal emotion speech recognition-based wearable intelligent safety device and a control method. The intelligent device comprises a main control module, a speech acquisition module, an analog-to-digital conversion module, a communication module and a positioning module. The control method is characterized by acquiring and processing the speech signals, extracting the speech characteristics, inputting the extracted characteristic parameters to a trained Gaussian mixture model for mode matching, and when the abnormal emotion speech is detected, starting a positioning early warning function, and comprises the concrete flows of S1 speech signal acquisition; S2 speech signal pre-processing; S3 speech end point detection; S4 speech signal characteristic extraction; S5 an abnormal emotion speech recognition stage; S6 a positioning early warning stage. The wearable intelligent safety device of the present invention triggers the early warning automatically via the abnormal emotion speech of sufferers, such as the cry, the scream, the call for help, etc., when an emergency situation occurs, thereby guaranteeing the personal safety of the wearers.

The invention discloses a mobile terminal based on biological recognition. The mobile terminal comprises a display module, a master chip, a biological recognition chip, a fingerprint acquisition module, a vein acquisition module, a facial image acquisition module, an iris image acquisition module, a speech acquisition module, a document reading module and a wireless communication module, wherein a comparison threshold adjustment unit and a storage unit used for storing a biological recognition algorithm are arranged inside the biological recognition chip, and the comparison threshold adjustment unit can adjust a biological recognition comparison threshold according to successfully recognized biological characteristics. By adopting the technical scheme of the invention, the safety, reliability and working efficiency of biological identity recognition and verification can be improved.

The invention discloses a voiceprint recognition method based on 3D convolution neural network, which comprises the following steps: step 1, preprocessing the speech signal. In the process of speech acquisition, there will be more channel noise, which will bring great difficulty to the recognition task, therefore, firstly, the input speech data is denoised by spectral subtraction, that is, noise spectrum estimation is subtracted from the noise speech estimation, so as to obtain the spectrum of pure speech. Here, the channel noise is eliminated, and the channel noise is the noise caused by therecording equipment; all the information about the speaker is completely preserved while the channel noise is removed. Compared with other methods, the spectral subtraction method introduces the leastconstraint conditions, the most direct physical meaning and the small calculation amount, so that the accuracy of recognition can be effectively improved.

The invention discloses an intelligent speech interaction system based on a cloud end. The intelligent speech interaction system comprises a speech acquisition system, a semantic comprehension system, and a speech response playing system. An MIC audio acquisition device is used to transmit an acquired question audio signal to an audio acquisition module. The audio acquisition module is used to convert an audio input signal into a digital signal, which can be processed by a processor, by adopting an AD conversion way, and the audio digital signal is transmitted to a cloud end data processing module by a wireless network. The cloud end data processing module is used for the data processing and parsing of the acquired audio digital signal by a core control module, and is used for realizing specific function codes. An answer audio signal after being processed and parsed is converted into a playable answer audio signal by an audio playing module, and the answer audio signal is played by an audio playing device.

The invention discloses a speech recognition method of vehicle equipment. The vehicle equipment includes a speech acquisition module and stores a local command recognition word library. The speech recognition method includes the steps as follows: receiving a speech signal which is collected by the speech acquisition; recognizing a controlled module corresponding to the speech signal according to the local command recognition word library; detecting the current internet connection status of the controlled module; when the current internet connection status of the controlled module conforms to presupposition condition, the speech signal is recognized by a cloud speech recognition method, and the controlled module works according to the feedback result of speech recognition. The invention also discloses the vehicle equipment and a computer readable storage medium. The technical scheme of the vehicle equipment, the speech recognition and the readable storage medium aims at solving the disadvantage of low efficiency of the speech recognition.

The invention provides a microphone speech enhancement method and a corresponding device. The method comprises the steps of acquiring first array speech signals which are acquired and inputted through multi-channel digital speech acquisition equipment; calculating optimal beam output signals synthesized by the first array speech signals by adopting the first array voice signals according to a minimum variance adaptive beam optimization model of the first array speech signals; and carrying out single-channel speech enhancement processing by adopting a power spectrum estimation value of the optimal beam output signals, wherein the minimum variance adaptive beam optimization model of the first array speech signals comprises a space guidance vector from a target sound source to the multi-channel digital speech acquisition equipment. The microphone speech enhancement method and the microphone speech enhancement device provided by the invention can process original speech of a speech acquisition equipment array with many array elements and large spacing.

The invention discloses an electronic card system which comprises a speech acquisition module, a speech analysis module, a speech characteristic extraction module, a keyword recognition module, an electronic card manager and an electronic card database, wherein the speech acquisition module is used for acquiring speech; the speech analysis module is used for transmitting an effective speech signal to the speech characteristic extraction module; the speech characteristic extraction module is used for extracting speech characteristics according to the received speech signal; the keyword recognition module is used for carrying out keyword recognition on the speech characteristics and outputting a keyword; the electronic card manager is used for establishing an electronic card in the electronic card database according to the keyword or browsing, retrieving, deleting and correcting the electronic card established in the electric card database; and the electronic card database stores the electronic card. The invention also discloses a speech recording method and a speech retrieval method of the electronic card, and also discloses an effective speech judgment method. According to the invention, contact information can be conveniently recorded and the electronic card is established, and multiple electronic cards can be rapidly retrieved.

The invention discloses an information processing method and system and an electronic device. The defects of speech amplitude truncation and reduced speech recognition rate, which are caused by the fact that fixed gain is carried out on a speech signal with high volume at the present, are overcome. The method is applied to the electronic device. The electronic device has a speech acquisition unit. The method comprises the steps that the speech signal is acquired through the speech acquisition unit; the speech signal is analyzed to acquire the environmental noise of the environment of the electronic device; based on the corresponding relationship among the environment noise, the preset level of the environment noise and a speech signal processing method, the speech signal processing method corresponding to the environment noise is determined; and first processing is carried out on the speech signal based on the speech signal processing method corresponding to the environment noise, so that the amplitude of the speech signal is maintained in a predetermined range. According to the embodiment of the invention, the signal-to-noise ratio can be maximized, and the speech accuracy and recognition rate are improved.

A conference system with transmitting and receiving sides. The transmitting side has a microphone array unit with microphone capsules, and a processing unit. The processing unit is configured to receive output signals of the microphone capsules and to execute audio beamforming based on the received output signals for acquiring sound coming from an audio source in a first direction. The processing unit has a direction-recognition unit that computes from the output signals of said microphone capsules a score for each of multiple search grid spatial positions and uses a search grid spatial position having a higher score to identify said first direction. The receiving side has an audio reproduction system that reproduces an audio signal detected by the microphone array with directional information of the first direction. The detected audio signal and the directional information regarding the first direction are transmitted from the transmitting side to the receiving side.

This invention presents a noise cancellation device for improved personal face-to-face and radio communications in high noise environments. The device comprises speech acquisition components, an audio signal processing module, a loudspeaker, and a radio interface. With the noise cancellation device, the signal-to-noise ratio can be improved by as much as 30 dB.

The invention discloses a wireless sensor network access control method and the system thereof for speech acquisition and transmission and belongs to the field of wireless sensor network. The method of the invention comprises the following procedures: a node captures a terminal-to-terminal path packet loss rate from the node to a convergent node, and compression ratio and redundancy rate are calculated according to the packet loss rate; a node i is required to calculate the rate of injection according to the compression ratio and the redundancy rate and sends out a participation request message containing the rate of injection to the convergent node simultaneously; the convergent node judges whether the current flow satisfies the bandwidth constraint according to the participation request message; if the current flow satisfies the bandwidth constraint and no message of objecting the node i to participate sent by other nodes is received, then the node i is allowed to participate; if objects, the node i is not allowed to participate. The system of the invention also comprises a microcontroller, a wireless transmit-receive module and a speech acquisition device. Compared with the present technique, the invention has the advantages of ensuring the terminal-to-terminal speech quality, raising network utilization rate and providing on-line and in-real evaluation of sensor network speech transmission.