221 results about "Voice source" patented technology

A speech separating apparatus includes: a PARCOR calculating unit (102) that extracts vocal tract information from an input speech signal; a filter smoothing unit (103) that smoothes, in a first time constant, the vocal tract information extracted by the PARCOR calculating unit (102); an inverse filtering unit (104) that calculates a filter coefficient of a filter having a frequency amplitude response characteristic inverse to the vocal tract information smoothed by the filter smoothing unit (103), so as to filter the input speech signal using the filter having the calculated filter coefficient; and a voicing source modeling unit (105) that cuts out, from the input speech signal filtered by the inverse filtering unit (104), a waveform included in a second time constant shorter than the first time constant, so as to calculate, for each waveform that is taken, voicing source information from the each waveform.

A data processing method includes acquiring voice data collected by at least two collecting devices from a voice source, acquiring a recognition result of the voice data that corresponds to a voice generated by the voice source, and executing a corresponding command in response to the recognition result.

The invention provides a method for enhancing microphone array voice based on combined inhibition. The method comprises the following steps of: structuring a microphone array for receiving external signals; analyzing the signals and obtaining time delays of different array signals relative to benchmark array signals in the microphone arrays opposite to a target voice source; respectively performing time delay compensation on digital signals corresponding to the two microphones, obtaining the compensated signals; respectively performing subband decomposition on the compensated array signals, and then forming fixed beams on each subband; meanwhile, respectively using blocking matrixes on each subband to obtain noise reference signals on each subband; and then respectively removing the noiseirrelative to the target voice form the fixed beam forming device on corresponding subband through an adaptive filtering processing algorithm, and then merging the subbands, thereby forming an initial gain signal; and meanwhile, making use of the previously compensated any two array signals to obtain a filter for inhibiting the noise signal related to the target voice through a recursive mutual power spectral density, thereby obtaining the final target voice signal through combining the initial gain signal.

The invention provides a multidimensional user identity identification method. The multidimensional user identity identification method comprises the steps of: detecting a human body in a photographic range by means of a camera, extracting facial features of the human body, comparing the facial features with user pictures prestored in a sample library, calculating a face matching coefficient, and preliminarily judging whether a user with permission exists in the photographic range; receiving user voice by using a microphone, converting an audio analog signal into a digital sequence, comparing the digital sequence with user voiceprints prestored in the sample library, calculating a voiceprint matching coefficient, and calculating the face matching coefficient and the voiceprint matching coefficient again to obtain a matching degree, so as to judge whether the user have the permission; and establishing a model for the user when judging that the user has the permission, carrying out human body dynamic tracking on the user, matching a voice source position with a position calculated through carrying out human body tracking on the user, judging that a command is issued by the user with permission and the command is valid when a voice position matches with an image position, and executing the command.

The invention provides a method for encoding and decoding lattice vector quantization audio. The method comprises the following steps: dividing a frequency domain coefficient of an audio signal which is subjected to modified discrete cosine transform (MDCT) conversion into a plurality of encoding sub-bands, and quantizing and encoding amplitude enveloping value of each encoding sub-band to acquire encoding bit of amplitude envelope; performing bit distribution on each encoding sub-band, normalizing, quantizing and encoding vectors in low-bit encoding sub-bands and high-bit encoding sub-bands by using a tower lattice vector quantizing method and a spherical lattice vector quantizing method to acquire encoding bit of the frequency domain coefficient respectively; and complexly packaging theencoding bit of the amplitude envelope and the encoding bit of the frequency domain coefficient of each encoding sub-band, and transmitting the package to a decoding end. The method and the system for encoding and decoding the lattice vector quantizing audio can acquire better voice source encoding effect.

The invention discloses a method for sensing and notifying voice. The method comprises the following steps of: receiving a voice signal sensed by a microphone, and calculating energy of the voice signal; when the energy of the voice signal is greater than the preset value, judging the direction of the voice source according to the energy of the voice signal; determining the type of the voice signal according to the characteristic parameters of the voice identification and different types of voice models which are stored in a voice model database; and sending early warning information according to the type of the voice and notifying a user of the direction of the voice source. By the method, voice of the surrounding environment can be sensed in real time, and early warning information can be sent to the user when the abnormal condition occurs.

The invention relates to a signal processing method for enhancing target voice signal pickup in a sound environment. The method includes the steps that (1), parameters of an ESN are acquired through experiments, and a corresponding sound source model is established; (2), the model is used for two occasions, namely, when output of the model is certain expected target voice signals and input of the model is a mixture of sound environment reflected sound signals of a target voice source and the target voice signals, the model can be used for echo cancellation of field amplified sound; when the output of the model is the expected target voice signals and the input of the model is a mixture of sound environment reflected sound signals of another specific voice source and the target voice signals, the model can be used for echo cancellation of voice communication between two specific persons; (3), when the model is used by a target voice person in the actual sound environment and the pickup position changes, reflected signals of sound source signals pointed by training can be suppressed as well, and then corresponding enhanced target voice signals are output. By the adoption of the signal processing method, the influence of the change of the pickup position on quality of the voice signals is overcome.

The invention discloses a voice processing method and apparatus, a terminal device and a storage medium. The method comprises the steps of: obtaining noise-containing audio data, wherein the noise-containing audio data comprise a voice source signal; preprocessing the noise-containing audio data, extracting the noise-containing audio features from the noise-containing audio data, and inputting thenoise-containing audio features into a pre-trained voice processing network model to obtain de-noised audio features, wherein the pre-trained voice processing network model comprises multiple cause and effect convolutional layers and at least one recurrent neural network layer, the multiple cause and effect convolutional layers are configured to output texture features of the corresponding voicesource signal according to the noise-containing audio features, and the at least one recurrent neural network layer is configured to output the de-noised audio features according to the texture features; and obtaining an estimated value of the voice source signal according to the de-noised audio features, and outputting the estimated value as de-noised noise-containing audio data. According to thevoice processing method and apparatus disclosed by the invention, real-time noise reduction of the noise-containing audio data is realized by the cause and effect convolutional layers and the recurrent neural network layer, and the voice noise reduction effect is improved.

Disclosed is a recognition and location test method for noise sources. The method includes: (1) setting measurement parameters and analysis parameters on a main control computer (MCC); (2) performing sound wave scan collection of the noise sources through turning a microphone array, converting the obtained acoustical signals into electric signals, and obtaining real-time images of sound sources by using an optical camera fixed on the microphone array; (3) obtaining the electric signals in the step (2) through a data collector, and transmitting the signals to the MCC; and (4) the MCC performing data analysis on the electric signals, combining with images obtained by the optical camera to form and display a sonogram of the noise sources. Fast recognition and location for the noise sources can be achieved through the method, the testing accuracy can be improved remarkably compared with the existing noise source recognition technology, and noise testing of complex vibrational structural bodies can be finished rapidly and accurately.

The present invention relates to technologies of implementing voice source tracking by using a microphone array. A method and an apparatus for a mobile terminal to implement voice source tracking. The method comprises: collecting outside voice information by using a microphone array (101); analyzing the outside voice information to determine target voice source information (102); and collecting a delay time of the target voice source information according to the microphone array to calculate a position of a target voice source (103). The apparatus comprises: a voice source information collection module (20), configured to collect outside voice information by using the microphone array; and a voice source information calculation processing module (30), configured to analyze the outside voice information, to determine target voice source information; and collect a delay time of the target voice source information according to the microphone array, to calculate a position of a target voice source.

The invention provides a voice amplifying method and a mobile terminal, and solves the problem of a non-ideal voice amplification effect caused by changing a holding posture, as the holding posture is changeless, of existing voice amplification equipment. The voice amplifying method provided by the invention comprises the following steps: acquiring audio signals received by a plurality of microphones of the mobile terminal; determining the microphone, closest to a voice source, in the plurality of microphones as a primary microphone according to audio information of the audio signals received by each microphone; performing amplification process on the audio signals received by the primary microphone; and outputting amplified audio signals through a loudspeaker. According to embodiments of the invention, when the holding posture of the voice amplification equipment changes, amplification process is performed on the audio signals received by the primary microphone closest to the voice source, so that noise interference is reduced, outputted audio signals are clearer, and user experience of a user is improved.

The invention provides a vision display method and device for compensation voice information, storage medium and an electronic device and relates to the technical field of human-computer interaction.The method comprises the steps that an orientation scale plate is provided on a graphical user interface, wherein the orientation scale plate comprises an orientation identifier for indicating orientation; voice in a game scene in a preset range is detected, and orientation information of a voice source of the voice is obtained when the voice in the game scene in the preset range is detected; according to the orientation information, a graph identifier corresponding to the voice is generated at the position corresponding to the orientation scale plate. A user can distinguish the type of voiceand the distance and orientation of the voice source with respect to a virtual object in a noisy environment and user experience is better by adopting the method.

The invention provides an electronic larynx speech reconstructing method and a system thereof. The method comprises the following steps of: firstly, extracting model parameters form collected speech as a parameter library; secondly, collecting the face image of a sounder, and transmitting the face image to an image analysis and processing module to obtain the sounding start moment, the sounding stop moment and the sounding vowel category; thirdly, synthesizing a voice source wave form through a voice source synthesizing module; and finally, outputting the voice source wave form through an electronic larynx vibration output module. Wherein the voice source synthesizing module is used for firstly setting the model parameters of a glottis voice source to synthesize the glottis voice source wave form, then simulating the transmission of the sound in the vocal tract by using a waveguide model and selecting the form parameters of the vocal tract according to the sounding vowel category so as to synthesize the electronic larynx voice source wave form. The speech reconstructed by the method and the system is closer to the sound of the sounder per se.

The embodiment of the invention discloses a large-view angle camera control method and a user terminal. The method comprises steps: when a photographing function of the large-view angle camera is opened, voice signals in the current environment are firstly acquired, and a voice source region for the voice signals is determined; a straight line formed between a central point of the voice source region and a central point of an imaging region of the large-view angle camera is determined, and an included angle between the straight line and a vertical line of the imaging region of the large-view angle camera is determined; and finally, according to the included angle, a rotating angle of the large-view angle camera is determined, and according to the rotating angle, the large-view angle camera is controlled to rotate until the included angle is smaller than a preset angle threshold. In the embodiment of the invention, rotation of the large-view angle camera does not need to be manually controlled by a user, the user terminal only needs to control the large-view angle camera to rotate according to the determined rotating angle, and thus, the operation steps during the photographing process by using the large-view angle camera can be simplified.

The embodiment of the invention discloses a method, an apparatus and a device for achieving co-location of voices and images and a medium. The method comprises the steps of: performing image recognition and voice recognition for a current playing video to obtain image features and voice features corresponding to the current playing video; based on the feature images, determining whether the current playing video has a sound production source; if yes, obtaining position information of the sound production source of the current playing video at a current video display screen; based on the voicefeatures, determining whether the current playing video has a voice source matching with the sound production source or not; if yes, generating control signals according to the position information ofthe sound production source in the current video display screen to control the voice corresponding to the position information to restore element sound production, wherein a preset image feature database is constructed in advance according to the current playing video. Through the technical scheme, the play effect of the video can be improved to bring high sense of immediacy for watchers.

The invention provides a voice signal processing method and device. The method comprises the steps that the relative positional relation between a user and an electronic device is obtained; a first distance between a voice source of voice signals to be collected and the electronic device is determined according to the relative positional relation; adjusting signal intensity compensating parameters of the voice signals in the voice signals collected by a voice collecting unit according to the first distance. According to the voice signal processing method, the quality of the voice signals output by the electronic device can be improved.

The invention discloses a robot voice addressed rotation system and a method thereof. The robot voice addressed rotation system comprises a voice activity detection unit used for detecting a received voice signal and judging whether a user sends out a voice signal or not, a voice addressed unit used for calculating the addressing angle of the voice signal, and a voice addressed rotation unit used for driving a robot to turn to the direction of the voice source of the voice signal according to the addressing angle of the voice signal. In this way, the voice recognition accuracy can be improved. Meanwhile, the voice recognition accuracy and the signal-to-noise ratio are improved. Based on the robot voice addressed rotation method, the voice signal sent from the user can be accurately and effectively obtained. Therefore, the signal-to-noise ratio and the voice recognition accuracy are improved.

The invention provides a voice-tracking microphone and a control method of the voice-tracking microphone. The voice-tracking microphone is characterized by comprising a body, a voice sensor set, a control circuit and a drive device. The body comprises a movable shaft, a base and a microphone body. The voice sensor set is used for picking up a corresponding upper voice signal, a corresponding lower voice signal, a corresponding left voice signal and a corresponding right voice signal according to a voice source. The control circuit comprises an A / D converter, a comparison circuit and a drive circuit. The drive device comprises a height adjustment mechanism and a direction adjustment mechanism, wherein the height adjustment mechanism is used for adjusting the height of the microphone body, the direction adjustment mechanism is used for adjusting the direction of the microphone body, the microphone body is adjusted to be higher when an upper volume value is larger than a lower volume value, the microphone body is adjusted to be lower when the upper volume value is smaller than the lower volume value, the microphone body is rotated leftward when a left volume value is larger than a right volume value, and the microphone body is rotated rightward when the right volume value is larger than the left volume value. According to the voice-tracking microphone, the voice sensor set adjusts the height and the direction of the microphone body according the position of the voice source so that voice tracking can be realized, and great convenience is brought to a user.

A device includes: an input speech separation unit which separates an input speech into vocal tract information and voicing source information; a mouth opening degree calculation unit which calculates a mouth opening degree from the vocal tract information; a target vowel database storage unit which stores pieces of vowel information on a target speaker; an agreement degree calculation unit which calculates a degree of agreement between the calculated mouth opening degree and a mouth opening degree included in the vowel information; a target vowel selection unit which selects the vowel information from among the pieces of vowel information, based on the calculated agreement degree; a vowel transformation unit which transforms the vocal tract information on the input speech, using vocal tract information included in the selected vowel information; and a synthesis unit which generates a synthetic speech using the transformed vocal tract information and the voicing source information.

The invention discloses a voice message processing method and device. The voice message processing method comprises the following steps: acquiring voice information of a voice source and target position information; determining a target translation strategy according to the target position information; translating the voice information according to the target translation strategy to obtain translation information; and outputting the translation information. With the adoption of the voice information processing method, a user can perform translation without repeatedly selecting translation ways; the operation is simple, and the conversation efficiency is high.

The present invention provides an electronic terminal and a voice signal processing method. The electronic terminal comprises a microphone module which comprises three microphones, a positioning module which is used for determining the position of a target voice source according to the voice signals collected by the at least three microphones at the beginning of a call, a determining module for determining a sound recording range according to the position of the target voice source, and a processing module used for obtaining the voice signal in the sound recording range and transmitting according to the voice signal in the sound recording range. In the invention, the target voice source is positioned through the microphone module, the sound recording range is determined, only the voice signal in the sound recording range is obtained, thus the environment noise can be effectively filtered, and the conversation effect is improved.

The present invention to provide an earphone comprising a casing, a loudspeaker provided in the casing and adapted to amplify sound in response to receiving a voice source signal, a cap fixedly mounted onto the casing, a piezoelectric microphone provided in the cap and a sound barrier member provided between the piezoelectric microphone and the loudspeaker, wherein the sound barrier member has a diameter larger than that of the piezoelectric microphone but smaller than that of the loudspeaker such that sound amplified by the loudspeaker is adapted to transmit beyond the cap through the sound barrier member and sound vibrations transmitted to the piezoelectric microphone are substantially absorbed. Thus, sound amplified by the loudspeaker does not interfere with the external sound receiving capability of the piezoelectric microphone.

An embodiment of the invention provides a voice noise reduction method, equipment and a storage medium, wherein the method comprises the steps of acquiring a voice signal which is acquired by a microphone; according to the voice signal and a transfer function between a voice source and a microphone, determining a source signal emitted from the voice source; and if a target standard voice signal which matches the source signal exists in at least one standard voice signal, performing filtering on the voice signal which is acquired by the microphone in reference to the target standard voice signal. In the voice noise reduction method, multiple types of voice signals in the voice signal which is acquired by the microphone can be filtered, and a useful signal acquired after noise reduction is same with a standard voice signal, thereby effectively preventing interference of the noise signal to voice processing.

The invention relates to a pharyngeal cavity electronic larynx synthesis and communicated system which can be automatically regulated and a method thereof, wherein a device based on a software platform and external hardware of a computer comprises a camera, a microphone and an electronic larynx oscillator; the automatic control to the working state of the electric larynx and the voice source synthesis of the pharyngeal cavity is realized through extracting visual phonetic feature information of movement images of the face and the neck of a user, thereby the electronic larynx can be used without holding by hands, which is simpler and more convenient, and the problems that the synthesis voice source is not consistent with the electronic larynx applying part and the voice of the electronic larynx is mechanical and unnatural are solved; and meanwhile, the dynamic de-noising enhancement treatment is implemented for the voice rebuilding of the pharyngeal cavity electronic larynx, thereby the quality and the intelligibility of the rebuilt voice are improved; and the remote real-time communication of the voice of the electronic larynx is realized through the network transmission technique, the application range of the electronic larynx is further expanded, and the life quality of a patient after laryngectomy is improved.

The invention relates to a voice acquisition method and device, computer equipment and a storage medium. The voice acquisition method comprises the steps that an audio stream is received and divided into a plurality of voice segments; the voiceprint characteristics of the voice segments are extracted; and the voiceprint characteristics of the voice segments are compared in a paired mode to obtaina fraction matrix corresponding to the audio stream, and the fraction matrix is used for expressing the corresponding fractions of the similarity of paired voice fragments; the voiceprint characteristics are clustered according to the fraction matrix, and the voice fragment numbers corresponding to multiple voice sources are obtained; and the corresponding voice segment is extracted according to the voice source with the largest voice fragment number. Through the voice acquisition method, the phenomenon that later manual operation is increased due to the voice quality problem can be avoided, and the voice acquisition efficiency is improved.

The invention discloses a voice-to-character conversion method and device. The voice-to-character conversion method comprises steps of using more than two microphones to collect voice information of more than one users, performing analysis processing on voice information collected by the microphone to obtain a voice source characteristic parameter of each user, classifying the collected voice information according to the voice source characteristic parameter of each user to obtain voice information corresponding to each user, and converting voice information corresponding to each user to corresponding character information.

Disclosed is a phase difference measurement-based microphone array direction finding method. The phase difference measurement-based microphone array direction finding method comprises the steps of obtaining the sampling data of a microphone array; performing fast Fourier transform on the sampling data of the microphone array according to channel sequence numbers to obtain the frequency domain data of the microphone array; selecting available frequency units; according to the available frequency units, computing corresponding array distance difference vectors; utilizing the array distance difference vectors of all the available frequency units to compose the high-dimensional linear system of equations of voice signal direction vectors, cooperatively solving the direction vector estimated values of voice source signals; according to the direction vector estimated values of the voice source signals, computing the azimuth angle estimated values and the pitch angle estimated values of the voice source signals. The phase difference measurement-based microphone array direction finding method has the advantages of being high in direction finding speed and precision, and particularly through the phase difference information of multiple available frequency units of the voice signals, obtains high azimuth angle and pitch angle estimating performance.