13 results about "Change voice" patented technology

The invention discloses an external voice changing method and system, and the method comprises the steps: building a mapping relation between a voice changing scene and voice changing parameters, and enabling the voice changing scene to be used for representing an external environment where a vehicle is located; in response to the user operation, determining a target voice changing scene; obtaining a target voice changing parameter corresponding to the target voice changing scene based on the mapping relationship between the voice changing scene and the voice changing parameter; and performing voice changing processing on voice played by a loudspeaker outside the vehicle by adopting the target voice changing parameter. According to the method, the voice interaction mode of the vehicle and the external environment has scene perception and self-adaptive capabilities, and the voice outside the vehicle can be matched with the specific environment and is easier to accept.

A system S according to an exemplary embodiment of the present invention acquires head-related transfer functions (HRTFs) obtained by emitting sound toward the head of an individual P from multiple sound emission directions D in an anechoic chamber, averages the plurality of HRTFs, and calculates a target response curve (TRC) for the individual P, which is referred to as TPTRC, and which clarifies information related to sound timbre. The system S generates TPTRC(W) by multiplying the TPTRC by each of different multipliers W, presents sounds conforming to the respective TPTRC(W) to individual P, to prompt individual P to select from among the sounds a preferred sound, storing the TPTRC(W) selected by individual P as TPTRCadj. The system S generates a generic TPTRCadj by averaging TPTRCadj stored for each of a plurality of different individuals P1 to Pn. A sound data processing device according to the exemplary embodiment of the present invention superimposes the generic TPTRCadj on input sound data and outputs the processed sound data to a sound-emitting device such as earphones.

1. The name of this design product: Voice changer (with amplifier). 2. Purpose of this design product: used to change sound. 3. The key design point of this design product lies in the combination of shape and pattern. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The invention discloses a variable voice authentic identification and traceability method and system based on multi-task learning, and relates to the field of artificial intelligence and computer security. Obtaining an original voice sample; constructing a variable voice authentic identification and traceability model; inputting the original voice sample into a final variable voice authentic identification and traceability model to obtain a voice forgery probability and an original speaker; the variable voice authentic identification and traceability model integrates a feature extraction module, a shared encoder module, an authentic identification task branch module and a traceability task branch module; according to the invention, a joint learning framework capable of collaborative optimization and mutual promotion is constructed, multi-task learning is utilized to improve the authenticity identification accuracy and traceability of the voice-changing voice at the same time, and on the basis of high-precision discrimination of whether an original voice sample is forged or not, the original speaker voiceprint in the voice-changing voice is further reversely recovered, so that the voice-changing voice identification accuracy and traceability of the voice-changing voice are improved. And a high-performance defense technical scheme for variable voices is realized.

The utility model relates to a sound changing switch structure which comprises a base and a button which is sleeved on the base and can move up and down, and a reset spring is connected between the button and the base. The button comprises an upper button and a lower button which are connected together, the peripheral side of the lower button is provided with an enclosing wall structure, the outer side plane of the enclosing wall structure is slidably connected with a window in the top of the base in a sleeved mode, the middle of the lower button is provided with a guide column extending downwards, a groove is formed in the guide column, and the bottom of the guide column is of a closed structure. Magnets are embedded in the bottoms of the inner sides of the guide columns; the guide column and the base of the lower button are both made of plastic materials. The button adopts a split structure design, a magnet is arranged in a guide post of the lower button, and the guide post is slotted but not a through hole, but the bottom of the guide post is closed; when the button is pressed down, the bottom of the guide column is in contact with the middle contact point of the base in a plastic-to-plastic manner, so that the sound generated by collision of the guide column and the base is small, and meanwhile, the materials of the guide column and the base can be changed to adjust the key sound effect required by a user.

A speech processing system receives both text data and natural understanding data (e.g., domain, intent, and / or entity) related to a command represented in the text data. The system uses the natural understanding data to modify acoustic characteristics when determining spectrogram data corresponding to the text data based on the natural understanding data.

The utility model relates to a kind of integral switch of suspending and can change sound, including integral shell, button, suspension sleeve and return spring, recess is opened in the middle of suspension sleeve top, and suspension sleeve bottom is closed structure, magnet is embedded in recess inside bottom portion;The two opposite sides of the button are respectively provided with the guide groove passing through its top and bottom portion, and the two opposite sides of the integral shell are respectively provided with the guide rail with the corresponding side guide groove limit sliding cooperation;The other two opposite sides of the button are respectively provided with limit recess, and the other two opposite sides of the integral shell are respectively provided with the limit step with the corresponding side limit recess cooperation.The button and suspension sleeve in the utility model are split structure, when the contact point of pressing button drives suspension sleeve and integral shell bottom is contacted, both will impact to produce sound, since suspension sleeve and button are split, and there is buffering effect between both, the sound generated by button depression impact sound relative to integral handle is smaller.

Embodiments of the present application provide an audio processing method and a computer device for generating a synthesized accompaniment with a target object's changed voice. The method of the embodiments of the present application comprises obtaining a to-be-synthesized changed voice, the to-be-synthesized changed voice being an audio obtained by performing a changed-pitch unchanged-speed processing on an original dry voice corresponding to a target song according to a pitch of a target object; obtaining a duet sentence group period template of the target song; decomposing the to-be-synthesized changed voice into a target object sentence group and a user sentence group according to the duet sentence group period template; retaining the target object sentence group in the to-be-synthesized changed voice and performing a mute processing on the user sentence group in the to-be-synthesized changed voice; mixing the retained target object sentence group with an accompaniment of the target song according to a preset energy ratio, so that a loudness of a volume of the mixed accompaniment is the same as an original loudness of the accompaniment of the target song and is not lower than a preset loudness standard; and outputting the mixed accompaniment with the target object's changed voice.

The present invention is applicable to the field of audio processing, and discloses a method for voice conversion of real-time speech, a terminal device, and a storage medium. The method for voice conversion of real-time speech includes: generating original speech data according to real-time conversation audio, and determining a conditional feature, a diversity feature, and a padding data mask according to the original speech data; determining a first tensor information according to the conditional feature, the diversity feature, and the padding data mask, and determining a speaker embedding vector according to the original speech data; determining a second tensor information according to the first tensor information, the speaker embedding vector, and the padding data mask; generating a target timbre audio according to the second tensor information, the speaker embedding vector, and the pitch frequency of the original speech data. The present invention significantly improves the reconstruction accuracy of the original timbre features in the voice conversion process, enables the generated speech to reach the level of a real person in perception dimensions such as timbre similarity and intonation naturalness, and improves the authenticity of voice conversion of real-time speech.

The utility model relates to the technical field of glasses, and discloses a glasses frame and intelligent glasses, the glasses frame comprises a glasses frame and glasses legs, the glasses legs are connected with the glasses frame, each glasses leg comprises a loudspeaker module, a shell and a sliding module, the shell is provided with a cavity, a sound leakage hole and a sound outlet hole, and the sound leakage hole and the sound outlet hole are communicated with the cavity. The loudspeaker module is arranged in the cavity, the sound leakage hole is located at the top of the loudspeaker module, and the sound outlet hole is located at the bottom of the loudspeaker module; the sliding module is in sliding connection with the shell, and the sliding module can move in the direction close to or away from the sound leakage hole under the action of external force so as to shield or open the sound leakage hole. According to the utility model, the sound leakage hole is shielded or opened through the sliding module, so that the area of the sound leakage hole is adjusted, and the sound quality effect of sound is changed.

A system (S) according to one embodiment of the present invention acquires head transfer functions (HRTF) when sounds are emitted in a plurality of sound emission directions (D) toward the head of a person (P) in an anechoic chamber, averages the plurality of HRTFs, and calculates, as TPTRC, a TRC for the person (P) in which tone information of the sounds is clarified. The system (S) generates TPTRC (W) by multiplying the multiplier (W) by TPTRC with respect to each of the different multipliers (W), allows an individual (P) to listen to sounds following the TPTRC (W), selects a favorite sound from among the sounds, and stores the TPTRC (W) selected by the individual (P) as TPTRCadj. A system (S) averages TPTRCadj stored for each of a plurality of different persons (P1-Pn), and generates a general-purpose TPTRCadj. A sound data processing device according to one embodiment of the present invention superimposes general-purpose TPTRCadj on input sound data and outputs the same to a sound generating device such as an in-ear headphone.

A sound playback device includes: a sensor, output of which changes in accordance with a position or movement of an object including a first area and a second area; a detection part configured to detect a position of the object based on output of the sensor; a sound control part configured to control playback of sound; and a determination part configured to determine whether a first condition is satisfied based on detection results. The sound control part changes a sound playback manner when a second condition, including a position of an object detected in the first area being detected in the second area, becomes satisfied, and changes a sound playback manner based on satisfaction of a third condition including a position of an object detected in the first area becoming not detected in the detection area and the first condition being determined not to be satisfied.