CN114554381A - Automatic human voice restoration system and method - Google Patents
Automatic human voice restoration system and method Download PDFInfo
- Publication number
- CN114554381A CN114554381A CN202210174208.XA CN202210174208A CN114554381A CN 114554381 A CN114554381 A CN 114554381A CN 202210174208 A CN202210174208 A CN 202210174208A CN 114554381 A CN114554381 A CN 114554381A
- Authority
- CN
- China
- Prior art keywords
- resistor
- capacitor
- voice
- signal
- comparator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000005236 sound signal Effects 0.000 claims abstract description 100
- 230000009467 reduction Effects 0.000 claims abstract description 8
- 239000003990 capacitor Substances 0.000 claims description 182
- 238000001514 detection method Methods 0.000 claims description 12
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 17
- 230000003321 amplification Effects 0.000 abstract description 14
- 238000003199 nucleic acid amplification method Methods 0.000 abstract description 14
- 230000003044 adaptive effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000004044 response Effects 0.000 description 4
- 230000001755 vocal effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000008602 contraction Effects 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 210000001260 vocal cord Anatomy 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R27/00—Public address systems
- H04R27/04—Electric megaphones
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/003—Changing voice quality, e.g. pitch or formants
- G10L21/007—Changing voice quality, e.g. pitch or formants characterised by the process used
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2430/00—Signal processing covered by H04R, not provided for in its groups
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Circuit For Audible Band Transducer (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a human voice automatic reduction system and a human voice automatic reduction method, wherein the system comprises a voice acquisition module, a human voice recognition module and a signal processing module, the voice acquisition module is used for acquiring human voice audio signals and sending the human voice audio signals to the human voice recognition module and the signal processing module, the human voice recognition module is used for recognizing the human voice audio signals and sending a voice base judgment signal to the signal processing module, and the signal processing module selects adaptive preset EQ parameters according to the voice base judgment signal to adjust the human voice audio signals. According to the invention, the human voice identification module identifies the human voice audio signal to obtain the voice base judgment signal corresponding to the voice gender attribute, and then the human voice audio signal is sent to the signal processing module, and the signal processing module adjusts the human voice audio signal through the preset EQ parameter according to the voice base judgment signal to improve the sound amplification tone quality and restore the sound effect of male voice or female voice with higher quality.
Description
Technical Field
The invention relates to the technical field of human voice signal processing, in particular to a human voice automatic restoration system and a human voice automatic restoration method.
Background
Most of existing used sound amplification equipment has an unobvious sound amplification fidelity effect, and does not have a function of identifying the voices of men and women, so that the sound amplification difference is obvious when the voices of men and women are amplified, the effect of a conference or a speaker is influenced in the mode, and the experience feeling is poor.
Therefore, a human voice automatic recovery system is needed to solve the above-mentioned problems.
Disclosure of Invention
In view of the above, there is a need to provide a system and a method for automatically restoring human voice, which can restore the sound effect of male voice or female voice with high quality when a male or a female speaks for public address.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
the invention provides a human voice automatic reduction system which comprises a voice acquisition module, a human voice recognition module and a signal processing module, wherein the voice acquisition module is respectively connected with the human voice recognition module and the signal processing module, the human voice recognition module is connected with the signal processing module, the voice acquisition module is used for acquiring a human voice audio signal and sending the human voice audio signal to the human voice recognition module and the signal processing module, the human voice recognition module is used for recognizing the human voice audio signal and sending a sound base judgment signal to the signal processing module, and the signal processing module selects an adaptive preset EQ parameter according to the sound base judgment signal to adjust the human voice audio signal.
In one embodiment, the signal processing module comprises an MCU module and an audio processing module, wherein the input end of the MCU module is connected with the human voice recognition module, the output end of the MCU module is connected with the audio processing module, and the audio processing module is connected with the sound acquisition module.
In one embodiment, the MCU module stores preset EQ parameters, and selects an appropriate preset EQ parameter based on the audio-based determination signal and sends the selected preset EQ parameter to the audio processing module.
In one embodiment, the voice recognition module includes a male voice base determination unit and a female voice base determination unit, the male voice base determination unit and the female voice base determination unit are arranged in parallel, the voice base determination signal includes a male voice base determination signal and a female voice base determination signal, and the male voice base determination unit is configured to receive a voice audio signal and send the male voice base determination signal to the signal processing module; the female voice base judgment unit is used for receiving the voice audio signal of the person and sending the acquired female voice base judgment signal to the signal processing module.
In one embodiment, the sound collection module includes a first comparator U3B, a resistor R29, R30, R31, R32, R33, R34, R35, R36, a capacitor C17, C18, C19, C20, C21, C22, C23 and an ESD tube D1, wherein a negative input terminal of the first comparator U3B is connected to one end of the resistor R33, the other end of the resistor R33 is connected to one end of the capacitor C19, one end of the capacitor C19 is connected to one end of the resistor R34 and one end of the capacitor C21, the other end of the resistor R34 is connected to one end of the resistor R32, one end of the capacitor C22 and one end of the ESD tube D1, the other end of the resistor R1 is connected to one end of the resistor R1 and one end of the capacitor C1, the other end of the resistor R1 is connected to the first analog power supply AVCC1, the capacitor C1 is connected in parallel with the resistor R1, and the other end of the capacitor C1 is grounded; the positive input end of a first comparator U3B is connected with one ends of a resistor R35 and a resistor R36, the other end of the resistor R36 is connected with a reference voltage VREF, the other end of a resistor R35 is connected with one end of a capacitor C23, the other end of the capacitor C23 is connected with the other end of a capacitor C21, the other end of the capacitor C22 and the other end of an ESD tube D1, and the other end of the capacitor C23 is grounded; the output end of the first comparator U3B is connected with one end of a capacitor C20, one end of a resistor R31 and one end of a capacitor C18, the other end of a resistor R31 and the other end of a capacitor C18 are respectively connected with the negative input end of the first comparator U3B, the other end of the capacitor C20 corresponds to the output end MIC _ OUT of the sound collection module, and one end of the capacitor C22 corresponds to the input end MIC _ IN of the sound collection module.
In one embodiment, the male voice-based determining unit includes resistors R1-R14, capacitors C1-C8, a second comparator U1A, a third comparator U1B and a first triode Q1, a negative input terminal of the second comparator U1A is connected to one end of a capacitor C6 and one end of a resistor R14, the other end of the capacitor C6 is connected to one end of a capacitor C8, one end of a resistor R9 and one end of a resistor R13, one end of a resistor R9 is connected to an output terminal MIC _ OUT of the voice collecting module, the other end of a resistor R13 is grounded, the other ends of a resistor R14 and a capacitor C8 are connected to an output terminal of the second comparator U1A, a positive input terminal of the second comparator U1A is connected to one end of a resistor R6 and one end of a resistor R4, the other end of the resistor R6 is grounded, the other end of the resistor R4 is connected to one end of a resistor R1, one end of a capacitor C2, one end of a capacitor C3 and one end of a second analog power supply, the other end of the capacitor AVCC2, the resistor R1 is connected to a capacitor C1, and one end of the capacitor AVCC voltage supply voltage of the capacitor AVCC 3668 are connected to the capacitor C1, The other end of the capacitor C2 and the other end of the capacitor C3 are both grounded; the output end of the second comparator U1A is connected with a resistor R8, a resistor R8 is connected with one end of a resistor R11, one end of a capacitor C5 and one end of a capacitor C7, the other end of the resistor R11 is grounded, the other end of the capacitor C5 is connected with the negative input end of the third comparator U1B and the resistor R12, the other end of the capacitor C7 and the other end of the resistor R12 are connected with the output end of the third comparator U1B, the positive input end of the third comparator U1B is connected with one end of a resistor R5 and one end of a resistor R3, the other end of the resistor R5 is grounded, and the resistor R3 is connected with a second analog power supply AVCC 2; the output end of the third comparator U1B is connected with one end of a capacitor C4, the other end of the capacitor C4 is connected with one end of a resistor R7, the other end of the resistor R7 is connected with one end of a resistor R10 and the base electrode of a first triode Q1, the other end of the resistor R10 is connected with the collector electrode of the first triode Q1 and one end of a resistor R2, the other end of the resistor R2 is connected with a power supply voltage VCC, and the emitter electrode of the first triode Q1 is grounded; wherein, the collector of the first triode Q1 corresponds to the output terminal DELL1_ DET of the male voice base determination unit.
In one embodiment, the female voice-based determining unit includes resistors R15 to R28, capacitors C9 to C16, a fourth comparator U2A, a fifth comparator U2B, and a second triode Q3, a negative input terminal of the fourth comparator U2 3 is connected to one end of capacitor C3 and one end of resistor R3, the other end of capacitor C3 is connected to one end of capacitor C3, one end of resistor R3 and one end of resistor R3, one end of resistor R3 is connected to MIC _ OUT, the other end of resistor R3 is grounded, the other ends of resistor R3 and capacitor C3 are connected to an output terminal of the fourth comparator U2 3, a positive input terminal of the fourth comparator U2 3 is connected to one end of resistor R3 and one end of resistor R3, the other end of resistor R3 is connected to ground, the other end of resistor R3 is connected to one end, one end of capacitor C3 and one end of a second analog power supply source, the other end of resistor R3 is connected to one terminal of capacitor AVCC 3, one terminal of capacitor C3 and one of capacitor C3 are connected to the capacitor C3, one terminal of the second AVCC voltage supply voltage, one terminal of the second terminal of the resistor R3 is connected to the capacitor C3, and one of the capacitor C3 is connected to the capacitor C3, and one terminal of the second terminal of the capacitor C3 is connected to the capacitor C3, and the second AVCC voltage supply voltage, The other end of the capacitor C10 and the other end of the capacitor C11 are both grounded; the output end of the fourth comparator U2A is connected with a resistor R22, a resistor R22 is connected with one end of a resistor R25, one end of a capacitor C13 and one end of a capacitor C15, the other end of the resistor R25 is grounded, the other end of the capacitor C13 is connected with the negative input end of the fifth comparator U2B and the resistor R26, the other end of the capacitor C15 and the other end of the resistor R26 are connected with the output end of the fifth comparator U2B, the positive input end of the fifth comparator U2B is connected with one end of a resistor R19 and one end of a resistor R17, the other end of the resistor R19 is grounded, and the resistor R17 is connected with a second analog power supply AVCC 2; the output end of the fifth comparator U2B is connected with one end of a capacitor C12, the other end of the capacitor C12 is connected with one end of a resistor R21, the other end of the resistor R21 is connected with one end of a resistor R24 and the base electrode of a second triode Q3, the other end of the resistor R24 is connected with the collector electrode of the second triode Q3 and one end of a resistor R16, the other end of the resistor R16 is connected with a power supply voltage VCC, and the emitter electrode of the second triode Q3 is grounded; the collector of the second transistor Q3 corresponds to the output terminal DELL2_ DET of the female sound-based determination unit.
The invention also provides a human voice automatic restoration method, which comprises the following steps:
collecting and processing a human voice audio signal through a voice collecting module;
judging the human voice audio signal through a human voice identification module to obtain a voice base judgment signal;
based on the sound base judgment signal, the signal processing module adjusts the human voice audio signal according to the preset EQ parameters to obtain human voice audio adjustment sound.
The method for acquiring the human voice audio regulation sound by regulating the human voice audio signal by the signal processing module according to the preset EQ parameters based on the sound base judgment signal comprises the following specific operations:
when the male voice base judgment unit sends a male voice base judgment signal to the MCU module through the corresponding IO detection port, the MCU module judges that the corresponding voice audio signal is a male speaker; after judging the gender attribute of the voice, the MCU module sends the preset EQ parameters corresponding to the male voice to the audio processing module, and the audio processing module adjusts the audio signals of the human voice to obtain the human voice audio adjusting sound.
In one embodiment, in the step of determining the signal based on the sound base, the signal processing module adjusts the human voice audio signal according to the preset EQ parameter to obtain the human voice audio adjustment sound, and the specific operations include:
when the female voice base judgment unit sends a female voice base judgment signal to the MCU module through the corresponding IO detection port, the MCU module judges that the corresponding voice audio signal is a female speaker; after judging the gender attribute of the voice, the MCU module sends the preset EQ parameters corresponding to the female voice to the audio processing module, and the audio processing module adjusts the audio signals of the human voice to obtain the human voice audio adjusting voice.
In summary, the system and method for automatically restoring sound of the present invention identify a human voice audio signal through a human voice identification module to obtain a voice base determination signal corresponding to a voice gender attribute, and then send the human voice audio signal to a signal processing module, wherein the signal processing module adjusts the human voice audio signal according to the voice base determination signal and through a preset EQ parameter, so as to improve the sound amplification sound quality and restore the sound effect of male or female voice with higher quality.
Drawings
Fig. 1 is a block diagram of a first human voice automatic restoring system according to an embodiment of the present invention;
fig. 2 is a block diagram of a second human voice automatic restoring system according to an embodiment of the present invention;
fig. 3 is a block diagram of a third human voice automatic restoring system according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of a method for automatically restoring human voice according to an embodiment of the present invention;
fig. 5 is a schematic circuit diagram of a sound collection module according to an embodiment of the present invention;
FIG. 6 is a schematic circuit diagram of a human voice recognition module according to an embodiment of the present invention;
FIG. 7 is a frequency-amplitude response graph of a frequency point signal centered at 200Hz according to an embodiment of the present invention;
fig. 8 is a frequency-group delay curve diagram corresponding to a male voice-based determination signal according to an embodiment of the present invention;
fig. 9 is a graph of a jump signal corresponding to a male voice base determination signal according to an embodiment of the present invention;
FIG. 10 is a graph of frequency-amplitude response of a frequency bin signal centered at 400Hz in accordance with an embodiment of the present invention;
FIG. 11 is a frequency-group delay curve diagram of a female voice-based decision signal according to an embodiment of the present invention;
fig. 12 is a graph of a jump signal corresponding to a female voice-based determination signal according to an embodiment of the present invention.
Detailed Description
For further understanding of the features and technical means of the present invention, as well as the specific objects and functions attained by the present invention, the present invention will be described in further detail with reference to the accompanying drawings and detailed description.
Based on the relationship between the pitch frequency of the male voice and the female voice and the length, thickness, toughness, stiffness, pronunciation habit and the like of vocal cords, male and female characteristics are reflected to a great extent, the pitch frequency of the female voice is higher than that of the male voice, the pitch frequency of the male voice is lower, the pitch frequency range of the male voice is 50-250Hz, the pitch frequency of the female voice is relatively higher, and the pitch frequency range of the female voice is 100 plus 500 Hz; the system and the method for automatically restoring the human voice provided by the embodiment of the invention can be particularly applied to an intelligent terminal, and the system for automatically restoring the human voice comprises a voice acquisition module, a human voice recognition module and a signal processing module, wherein the human voice recognition module is used for recognizing human voice audio signals to obtain a voice base judgment signal corresponding to the gender attribute of the voice, and then sending the human voice audio signals to the signal processing module, and the signal processing module is used for adjusting the human voice audio signals through presetting EQ (equalizer) parameters according to the voice base judgment signal to improve the sound amplification quality and restore the sound effect of male voice or female voice with higher quality. The following describes in detail a system and a method for automatically restoring human voice provided in this embodiment.
As shown in fig. 1, the system for automatically restoring human voice of the present invention includes a sound collection module 100, a human voice recognition module 200, and a signal processing module 300, wherein the sound collection module 100 is respectively connected to the human voice recognition module 200 and the signal processing module 300, the human voice recognition module 200 is connected to the signal processing module 300, the sound collection module 100 is configured to collect a human voice audio signal and send the human voice audio signal to the human voice recognition module 200 and the signal processing module 300, the human voice recognition module 200 is configured to recognize the human voice audio signal and send a sound base judgment signal to the signal processing module 300, and the signal processing module 300 selects an adapted preset EQ parameter according to the sound base judgment signal to adjust the human voice audio signal.
As shown in fig. 4, the sound collection module 100 includes a first comparator U3, a resistor R, a capacitor C, and an ESD tube D, wherein a negative input terminal of the first comparator U3 is connected to one end of the resistor R, the other end of the resistor R is connected to one end of the capacitor C, one end of the capacitor C is connected to one end of the resistor R and one end of the capacitor C, the other end of the resistor R is connected to one end of the resistor R, one end of the capacitor C, and one end of the ESD tube D, the other end of the resistor R is connected to one end of the resistor R and one end of the capacitor C, the other end of the resistor R is connected to the first analog power supply AVCC, the capacitor C is connected to the resistor R in parallel, and the other end of the capacitor C is grounded; the positive input end of a first comparator U3B is connected with one ends of a resistor R35 and a resistor R36, the other end of the resistor R36 is connected with a reference voltage VREF, the other end of a resistor R35 is connected with one end of a capacitor C23, the other end of the capacitor C23 is connected with the other end of a capacitor C21, the other end of the capacitor C22 and the other end of an ESD tube D1, and the other end of the capacitor C23 is grounded; the output end of the first comparator U3B is connected with one end of a capacitor C20, one end of a resistor R31 and one end of a capacitor C18, the other end of a resistor R31 and the other end of a capacitor C18 are respectively connected with the negative input end of the first comparator U3B, the other end of the capacitor C20 corresponds to the output end MIC _ OUT of the sound collection module 100, and one end of the capacitor C22 corresponds to the input end MIC _ IN of the sound collection module 100; the first comparator U3B is made of LM 358.
The sound collection module 100 is implemented IN such a manner that a microphone receives a voice audio signal of a speaker, the voice audio signal enters the sound collection module 100 through an input terminal MIC _ IN of the sound collection module 100, noise frequencies except for voice are eliminated through an n-type filter composed of a capacitor C22, a resistor R34 and a capacitor C21, the noise frequencies are coupled through a capacitor C19, and then a negative feedback operational amplification unit is formed by a resistor R33, a resistor R31 and a first comparator U3B, so that the voice audio signal collected by the sound collection module 100 is amplified, and the amplified voice audio signal is transmitted to the voice identification module 200 through an output terminal MIC _ OUT of the sound collection module 100.
As shown in fig. 2, the voice recognition module 200 includes a male voice base determination unit 210 and a female voice base determination unit 220, the voice base determination signal includes a male voice base determination signal and a female voice base determination signal, and the male voice base determination unit 210 is configured to receive a voice audio signal and send the male voice base determination signal to the signal processing module 300; the female voice base determination unit 220 is configured to receive a voice audio signal, and send the acquired female voice base determination signal to the signal processing module 300.
As shown in fig. 5, the male voice base determination unit 210 and the female voice base determination unit 220 are disposed in parallel, the input terminals of the male voice base determination unit 210 and the female voice base determination unit 220 are connected to the output terminal of the voice acquisition module 100, the male voice base determination unit 210 includes resistors R1 to R14, capacitors C1 to C8, a second comparator U1A, a third comparator U1B and a first transistor Q1, the negative input terminal of the second comparator U1A is connected to one end of a capacitor C6 and one end of a resistor R14, the other end of a capacitor C6 is connected to one end of a capacitor C8, one end of a resistor R9 and one end of a resistor R13, one end of the resistor R9 is connected to the output terminal MIC _ OUT of the voice acquisition module 100, the other end of the resistor R13 is grounded, the other ends of the resistor R14 and the other end of the capacitor C8 are connected to the output terminal of a second comparator U1A, the positive input terminal of the second comparator U1U 52 is connected to one end of the resistor R6 and one end of the resistor R369372 and the resistor R6, the other end of the resistor R4 is connected with one end of a resistor R1, one end of a capacitor C2, one end of a capacitor C3 and a second analog power supply AVCC2, the other end of the resistor R1 is connected with one end of the capacitor C1 and a power supply voltage VCC, and the other end of the capacitor C1, the other end of the capacitor C2 and the other end of the capacitor C3 are all grounded; the output end of the second comparator U1A is connected with a resistor R8, a resistor R8 is connected with one end of a resistor R11, one end of a capacitor C5 and one end of a capacitor C7, the other end of the resistor R11 is grounded, the other end of the capacitor C5 is connected with the negative input end of the third comparator U1B and the resistor R12, the other end of the capacitor C7 and the other end of the resistor R12 are connected with the output end of the third comparator U1B, the positive input end of the third comparator U1B is connected with one end of a resistor R5 and one end of a resistor R3, the other end of the resistor R5 is grounded, and the resistor R3 is connected with a second analog power supply AVCC 2; the output end of the third comparator U1B is connected with one end of a capacitor C4, the other end of the capacitor C4 is connected with one end of a resistor R7, the other end of the resistor R7 is connected with one end of a resistor R10 and the base of a first triode Q1, the other end of the resistor R10 is connected with the collector of the first triode Q1 and one end of a resistor R2, the other end of the resistor R2 is connected with a power supply voltage VCC, and the emitter of the first triode Q1 is grounded; the collector of the first transistor Q1 corresponds to the output terminal DELL1_ DET of the male voice-based determining unit 210, and the second comparator U1A and the third comparator U1B both adopt OPA1678 chips.
The man voice base determination unit 210 has the following specific working principle that when a man voice audio signal is sent by a man speaker, the amplified man voice audio signal is coupled through a resistor R9, forms a first-order low-pass filter to filter a high-frequency signal in cooperation with a resistor R13 and a capacitor C6, and performs a second-order filtering processing in cooperation with a second comparator U1A through a resistor R14 and a capacitor C8, so that a more gentle frequency point signal and a group delay signal which take 200Hz as a center are obtained, as shown in fig. 7; as shown in fig. 8, the group delay signal is coupled through the resistor R8 and enters the step response circuit composed of the capacitor C5, the capacitor C7, the resistor R12 and the third comparator U1B, so as to obtain a value that the transition signal becomes close to 0, as shown in fig. 9, at this time, the first transistor Q1 is turned on, so that the output terminal DELL1_ DET of the male voice base determination unit 210 becomes 0 level, so as to obtain the male voice base determination signal, and send the male voice base determination signal to the signal processing module 300.
The female voice base judgment unit 220 comprises resistors R15-R28, capacitors C9-C16, a fourth comparator U2A, a fifth comparator U2B and a second triode Q3, the negative input end of the fourth comparator U2A is connected with one end of a capacitor C14 and one end of a resistor R28, the other end of the capacitor C14 is connected with one end of a capacitor C16, one end of a resistor R23 and one end of a resistor R27, one end of a resistor R23 is connected with the output end MIC _ OUT of the sound collection module 100, the other end of the resistor R27 is grounded, the other end of the resistor R28 and the other end of the capacitor C16 are both connected with the output end of the fourth comparator U2A, the positive input end of the fourth comparator U2A is connected with one end of a resistor R20 and one end of a resistor R18, the other end of the resistor R20 is grounded, the other end of the resistor R18 is connected with one end of a resistor R15, one end of a capacitor C10, one end of a capacitor C11 and a second analog power supply AVCC1, the other end of the resistor R15 is connected with one end of a capacitor C9 and a power supply voltage VCC, and the other end of the capacitor C9, the other end of the capacitor C10 and the other end of the capacitor C11 are grounded; the output end of the fourth comparator U2A is connected with a resistor R22, a resistor R22 is connected with one end of a resistor R25, one end of a capacitor C13 and one end of a capacitor C15, the other end of the resistor R25 is grounded, the other end of the capacitor C13 is connected with the negative input end of the fifth comparator U2B and the resistor R26, the other end of the capacitor C15 and the other end of the resistor R26 are connected with the output end of the fifth comparator U2B, the positive input end of the fifth comparator U2B is connected with one end of a resistor R19 and one end of a resistor R17, the other end of the resistor R19 is grounded, and the resistor R17 is connected with a second analog power supply AVCC 2; the output end of the fifth comparator U2B is connected with one end of a capacitor C12, the other end of the capacitor C12 is connected with one end of a resistor R21, the other end of the resistor R21 is connected with one end of a resistor R24 and the base electrode of a second triode Q3, the other end of the resistor R24 is connected with the collector electrode of the second triode Q3 and one end of a resistor R16, the other end of the resistor R16 is connected with a power supply voltage VCC, and the emitter electrode of the second triode Q3 is grounded; the collector of the second transistor Q3 corresponds to the output terminal DELL2_ DET of the female sound-based determining unit 220, and the fourth comparator U2A and the fifth comparator U2B both adopt OPA1678 chips.
The specific working principle of the female voice base determination unit 220 is as follows, when a voice audio signal is sent by a female speaker, the amplified voice audio signal is coupled through a resistor R23, forms a first-order low-pass filter by matching with a resistor R27 and a capacitor C14 to filter a high-frequency signal, and performs a second-order filtering processing through matching of a resistor R28, a capacitor C16 and a fourth comparator U2A, so that a more gentle frequency point signal and a group delay signal centering on 400Hz are obtained, as shown in fig. 10; as shown in fig. 11, the group delay signal is coupled through a resistor R8 and enters a step response circuit composed of a capacitor C13, a capacitor C15, a resistor R26 and a fifth comparator U2B, so as to obtain a value that a transition signal becomes close to 0, as shown in fig. 12, at this time, the second triode Q3 is turned on, so that the output terminal DELL2_ DET of the female voice base determining unit 220 becomes 0 level, so as to obtain a female voice base determining signal, and send the female voice base determining signal to the signal processing module 300.
As shown in fig. 3, the signal processing module 300 includes an MCU module 310 and an audio processing module 320, an input end of the MCU module 310 is connected to the human voice recognition module 200, specifically, an input end of the MCU module 310 is connected to the male voice base determination unit 210 and the female voice base determination unit 220, respectively, wherein the male voice base determination unit 210 and the female voice base determination unit 220 are connected to different IO detection ports of the MCU module 310, respectively, so that the MCU module 310 can obtain a voice gender attribute result corresponding to the voice base determination signal according to the input signal at the IO detection port; the output of MCU module 310 is connected with audio processing module 320, audio processing module 320 is connected with sound collection module 100, MCU module 310 storage has the EQ parameter of predetermineeing, MCU module 310 selects suitable EQ parameter of predetermineeing based on the sound base judgement signal and sends for audio processing module 320, sound collection module 100 sends the vocal audio signal for audio processing module 320, audio processing module 320 carries out adjustment processing with the vocal audio signal according to predetermineeing the EQ parameter, acquires the vocal audio and adjusts sound, and then promotes the public address tone quality of vocal audio signal, the sound effect of higher quality reduction man's voice or female voice.
When the male voice base determination unit 210 sends the male voice base determination signal to the MCU module 310 through the corresponding IO detection port, the MCU module 310 determines that the corresponding voice audio signal is a male speaker; after the MCU module 310 determines the gender attribute of the voice, the preset EQ parameters corresponding to the male voice are sent to the audio processing module 320, and the audio processing module 320 adjusts the audio signal of the human voice to obtain the voice adjustment sound, so as to improve the sound amplification quality of the voice signal and restore the sound effect of the male voice or the female voice with higher quality.
In this embodiment, the specific process of the audio processing module 320 performing adjustment processing on the human audio signal is as follows: when the human voice audio signal is in the frequency band of 150Hz-300Hz, the audio processing module 320 performs a gain boost of 3dB on the human voice audio signal, since this frequency band is the bass fundamental tone frequency of boys, if this frequency band is lacking, the tone will appear soft and floating, and the voice becomes soft and lingering; when the human voice audio signal is in the frequency band of 300Hz-500Hz, the audio processing module 320 performs 1dB gain boost on the human voice audio signal, the frequency range of the segment is full, the voice has strength, and if the frequency range of the segment is insufficient, the voice appears to be hollow and not firm; when the voice audio signal is in the frequency band of 500Hz-1KHz, the audio processing module 320 performs 1dB gain improvement on the voice audio signal, the frequency of the voice base frequency point of the voice in the frequency band is rich, the outline of the voice is clear, the integral sense is good, and if the frequency of the voice base frequency point is insufficient, the voice can generate a contraction sense; the preset EQ parameter adjustment is carried out on the main middle and low audio frequency segments of the male voice, so that the speech of the male can be adapted to the emotional expression at the moment in different scenes, and the sound effect of the male voice or the female voice can be effectively restored.
When the female voice base determination unit 220 sends a female voice base determination signal to the MCU module 310 through the corresponding IO detection port, the MCU module 310 determines that the corresponding voice audio signal is a female speaker; after the MCU module 310 determines the gender attribute of the voice, the preset EQ parameters corresponding to the female voice are sent to the audio processing module 320, and the audio processing module 320 adjusts the audio signal of the human voice to obtain the voice adjustment sound, so as to improve the sound amplification quality of the audio signal of the human voice and restore the sound effect of the female voice or the female voice with higher quality.
In this embodiment, when the MCU module 310 determines that the corresponding human voice audio signal is a female speaker, the specific process of the audio processing module 320 performing adjustment processing on the human voice audio signal is as follows: when the human voice audio signal is in the frequency band of 300Hz-500Hz, the audio processing module 320 performs 1dB gain boost on the human voice audio signal, the frequency range of the segment is full, the voice has strength, and if the frequency range of the segment is insufficient, the voice appears to be hollow and not firm; when the voice audio signal is in the frequency band of 500Hz-1KHz, the audio processing module 320 performs 1dB gain increase on the voice audio signal, the frequency of the section is full, the outline of the voice is clear, the integral sense is good, and if the frequency of the section is insufficient, the voice can generate a contraction sense; when the human voice audio signal is in the frequency band of 1KHz-2KHz, the audio processing module 320 performs 1dB gain improvement on the human voice audio signal, the frequency range of the section is transparent and obvious, and smooth, and if the section is poor in smoothness, the tone is loose and the tone is disjointed; through the preset EQ parameter adjustment of the main middle and high audio frequency section of the female voice, the female can adapt to the emotional expression at the time when speaking in different scenes, and the voice effect of the female voice or the female voice is effectively reduced.
As shown in fig. 6, according to the above-mentioned automatic human voice restoring system of the present invention, the present invention provides an automatic human voice restoring method, in which the sound collection module 100, the human voice recognition module 200 and the signal processing module 300 involved in the method may be the same as the technical features described in the above-mentioned embodiment of the automatic human voice restoring system, and can produce the same technical effects. The invention relates to a human voice automatic restoration method, which is characterized in that a human voice identification module 200 identifies a human voice audio signal to obtain a sound base judgment signal corresponding to the gender attribute of the voice, and then the human voice audio signal is sent to a signal processing module 300, and the signal processing module 300 adjusts the human voice audio signal according to the sound base judgment signal and through preset EQ parameters, so that the sound amplification sound quality is improved, and the sound effect of male or female voice is restored with higher quality.
Fig. 6 is a schematic flow chart of a method for automatically restoring human voice according to an embodiment of the present invention, and as shown in fig. 6, the method for automatically restoring human voice includes steps S110 to S130, which specifically include the following steps:
step S110, collecting and processing a human voice audio signal through the voice collecting module 100; the sound collection module 100 processes the collected human voice audio signal to obtain a processed human voice audio signal.
Step S120, judging the human voice audio signal through the human voice identification module 200 to obtain a voice base judgment signal; the voice base determination signal includes a male voice base determination signal and a female voice base determination signal, the voice recognition module 200 includes a male voice base determination unit 210 and a female voice base determination unit 220, and the male voice base determination unit 210 is configured to receive a voice audio signal and send the male voice base determination signal to the signal processing module 300; the female voice base determination unit 220 is configured to receive a voice audio signal, and send the acquired female voice base determination signal to the signal processing module 300.
Step S130, based on the sound-based determination signal, the signal processing module 300 adjusts the human voice audio signal according to the preset EQ parameter, and obtains a human voice audio adjustment sound, so as to improve the sound amplification sound quality of the human voice audio signal, and restore the sound effect of male or female with higher quality.
Specifically, the signal processing module 300 includes an MCU module 310 and an audio processing module 320, and the male voice base determining unit 210 and the female voice base determining unit 220 are respectively connected to different IO detection ports of the MCU module 310, so that the MCU module 310 can obtain a voice gender attribute result corresponding to the voice base determining signal according to the input signal at the IO detection port.
In an embodiment, the method of step S130 specifically includes:
when the male voice base determination unit 210 sends the male voice base determination signal to the MCU module 310 through the corresponding IO detection port, the MCU module 310 determines that the corresponding voice audio signal is a male speaker; after the MCU module 310 determines the gender attribute of the voice, the preset EQ parameters corresponding to the male voice are sent to the audio processing module 320, and the audio processing module 320 adjusts the audio signal of the human voice to obtain the voice adjustment sound, so as to improve the sound amplification quality of the voice signal and restore the sound effect of the male voice or the female voice with higher quality.
In another embodiment, the method of step S130 specifically includes:
when the female voice base determination unit 220 sends a female voice base determination signal to the MCU module 310 through the corresponding IO detection port, the MCU module 310 determines that the corresponding voice audio signal is a female speaker; after the MCU module 310 determines the gender attribute of the voice, the preset EQ parameters corresponding to the female voice are sent to the audio processing module 320, and the audio processing module 320 adjusts the audio signal of the human voice to obtain the voice adjustment sound, so as to improve the sound amplification quality of the audio signal of the human voice and restore the sound effect of the female voice or the female voice with higher quality.
In summary, in the system and method for automatically restoring human voice according to the present invention, the human voice recognition module 200 recognizes the human voice audio signal to obtain the sound base determination signal corresponding to the gender attribute of the voice, and then sends the human voice audio signal to the signal processing module 300, and the signal processing module 300 adjusts the human voice audio signal according to the sound base determination signal by using the preset EQ parameter, so as to improve the sound amplification sound quality and restore the sound effect of male or female voice with higher quality.
The above examples are merely illustrative of several embodiments of the present invention, and the description thereof is more specific and detailed, but not to be construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.
Claims (10)
1. A human voice automatic reduction system is characterized in that: including sound collection module, voice recognition module and signal processing module, sound collection module connects voice recognition module and signal processing module respectively, voice recognition module is connected with signal processing module, sound collection module is used for gathering voice audio signal to send voice audio signal for voice recognition module and signal processing module, voice recognition module is used for discerning voice audio signal to send the sound base to judge the signal and give signal processing module, and signal processing module judges the preset EQ parameter of signal selection adaptation according to the sound base and adjusts voice audio signal to the voice audio signal.
2. The system according to claim 1, wherein: the signal processing module comprises an MCU module and an audio processing module, wherein the input end of the MCU module is connected with the human voice recognition module, the output end of the MCU module is connected with the audio processing module, and the audio processing module is connected with the sound acquisition module.
3. The system according to claim 2, wherein: the MCU module stores preset EQ parameters, and selects proper preset EQ parameters to send to the audio processing module based on the sound base judgment signals.
4. The human voice automatic restoring system according to claim 1 or 2, characterized in that: the voice recognition module comprises a male voice base judgment unit and a female voice base judgment unit, the male voice base judgment unit and the female voice base judgment unit are arranged in parallel, the voice base judgment signal comprises a male voice base judgment signal and a female voice base judgment signal, and the male voice base judgment unit is used for receiving a voice audio signal and sending the male voice base judgment signal to the signal processing module; the female voice base judgment unit is used for receiving the voice audio signal of the person and sending the acquired female voice base judgment signal to the signal processing module.
5. The human voice automatic restoring system according to claim 1 or 2, characterized in that: the sound collection module comprises a first comparator U3B, a resistor R29, a resistor R30, a resistor R31, a resistor R32, a resistor R33, a resistor R34, a resistor R35, a resistor R36, a capacitor C17, a capacitor C18, a capacitor C19, a capacitor C20, a capacitor C21, a capacitor C22, a capacitor C23 and an ESD tube D1, wherein the negative input end of the first comparator U3B is connected with one end of a resistor R33, the other end of the resistor R33 is connected with one end of a capacitor C19, one end of a capacitor C19 is connected with one end of the resistor R34 and one end of the capacitor C21, the other end of the resistor R34 is connected with one end of a resistor R32, one end of a capacitor C22 and one end of the ESD tube D1, the other end of the resistor R32 is connected with one end of a resistor R30 and one end of a capacitor C17, the other end of the resistor R30 is connected with a first analog power supply source AVCC1, the capacitor C17 is connected with the resistor R29 in parallel, and the other end of the capacitor C17 is grounded; the positive input end of a first comparator U3B is connected with one ends of a resistor R35 and a resistor R36, the other end of the resistor R36 is connected with a reference voltage VREF, the other end of a resistor R35 is connected with one end of a capacitor C23, the other end of the capacitor C23 is connected with the other end of a capacitor C21, the other end of the capacitor C22 and the other end of an ESD tube D1, and the other end of the capacitor C23 is grounded; the output end of the first comparator U3B is connected with one end of a capacitor C20, one end of a resistor R31 and one end of a capacitor C18, the other end of a resistor R31 and the other end of a capacitor C18 are respectively connected with the negative input end of the first comparator U3B, the other end of the capacitor C20 corresponds to the output end MIC _ OUT of the sound collection module, and one end of the capacitor C22 corresponds to the input end MIC _ IN of the sound collection module.
6. The human voice automatic reduction system according to claim 4, characterized in that: the male voice base judging unit comprises resistors R1-R14, capacitors C1-C8, a second comparator U1A, a third comparator U1B and a first triode Q1, the negative input end of the second comparator U1A is connected with one end of a capacitor C6 and one end of a resistor R14, the other end of the capacitor C6 is connected with one end of a capacitor C8, one end of a resistor R9 and one end of a resistor R13, one end of a resistor R9 is connected with the output end MIC _ OUT of the sound collection module, the other end of the resistor R13 is grounded, the other end of the resistor R14 and the other end of the capacitor C8 are both connected with the output end of the second comparator U1A, the positive input end of the second comparator U1A is connected with one end of a resistor R6 and one end of a resistor R4, the other end of the resistor R6 is grounded, the other end of the resistor R4 is connected with one end of a resistor R1, one end of a capacitor C2, one end of a capacitor C3 and a second analog power supply AVCC2, the other end of the resistor R1 is connected with one end of a capacitor C1 and a power supply voltage VCC, and the other end of the capacitor C1, the other end of the capacitor C2 and the other end of the capacitor C3 are grounded; the output end of the second comparator U1A is connected with a resistor R8, a resistor R8 is connected with one end of a resistor R11, one end of a capacitor C5 and one end of a capacitor C7, the other end of the resistor R11 is grounded, the other end of the capacitor C5 is connected with the negative input end of the third comparator U1B and the resistor R12, the other end of the capacitor C7 and the other end of the resistor R12 are connected with the output end of the third comparator U1B, the positive input end of the third comparator U1B is connected with one end of a resistor R5 and one end of a resistor R3, the other end of the resistor R5 is grounded, and the resistor R3 is connected with a second analog power supply AVCC 2; the output end of the third comparator U1B is connected with one end of a capacitor C4, the other end of the capacitor C4 is connected with one end of a resistor R7, the other end of the resistor R7 is connected with one end of a resistor R10 and the base electrode of a first triode Q1, the other end of the resistor R10 is connected with the collector electrode of the first triode Q1 and one end of a resistor R2, the other end of the resistor R2 is connected with a power supply voltage VCC, and the emitter electrode of the first triode Q1 is grounded; wherein, the collector of the first transistor Q1 corresponds to the output terminal DELL1_ DET of the male voice base determination unit.
7. The human voice automatic reduction system according to claim 4, characterized in that: the female sound base judging unit comprises resistors R15-R28, capacitors C9-C16, a fourth comparator U2A, a fifth comparator U2B and a second triode Q3, the negative input end of the fourth comparator U2A is connected with one end of a capacitor C14 and one end of a resistor R28, the other end of the capacitor C14 is connected with one end of a capacitor C16, one end of a resistor R23 and one end of a resistor R27, one end of a resistor R23 is connected with the output end MIC _ OUT of the sound collection module, the other end of the resistor R27 is grounded, the other end of the resistor R28 and the other end of the capacitor C16 are both connected with the output end of the fourth comparator U2A, the positive input end of the fourth comparator U2A is connected with one end of a resistor R20 and one end of a resistor R18, the other end of the resistor R20 is grounded, the other end of the resistor R18 is connected with one end of a resistor R15, one end of a capacitor C10, one end of a capacitor C11 and a second analog power supply AVCC1, the other end of the resistor R15 is connected with one end of a capacitor C9 and a power supply voltage VCC, and the other end of the capacitor C9, the other end of the capacitor C10 and the other end of the capacitor C11 are grounded; the output end of the fourth comparator U2A is connected with a resistor R22, a resistor R22 is connected with one end of a resistor R25, one end of a capacitor C13 and one end of a capacitor C15, the other end of the resistor R25 is grounded, the other end of the capacitor C13 is connected with the negative input end of the fifth comparator U2B and the resistor R26, the other end of the capacitor C15 and the other end of the resistor R26 are connected with the output end of the fifth comparator U2B, the positive input end of the fifth comparator U2B is connected with one end of a resistor R19 and one end of a resistor R17, the other end of the resistor R19 is grounded, and the resistor R17 is connected with a second analog power supply AVCC 2; the output end of the fifth comparator U2B is connected with one end of a capacitor C12, the other end of the capacitor C12 is connected with one end of a resistor R21, the other end of the resistor R21 is connected with one end of a resistor R24 and the base electrode of a second triode Q3, the other end of the resistor R24 is connected with the collector electrode of the second triode Q3 and one end of a resistor R16, the other end of the resistor R16 is connected with a power supply voltage VCC, and the emitter electrode of the second triode Q3 is grounded; the collector of the second transistor Q3 corresponds to the output terminal DELL2_ DET of the female sound-based determination unit.
8. A human voice automatic reduction method is characterized by comprising the following steps:
collecting and processing a human voice audio signal through a voice collecting module;
judging the human voice audio signal through a human voice identification module to obtain a voice base judgment signal;
based on the sound base judgment signal, the signal processing module adjusts the human voice audio signal according to the preset EQ parameters to obtain human voice audio adjustment sound.
9. The automatic human voice restoration method according to claim 8, wherein: the method for acquiring the human voice audio regulation sound by regulating the human voice audio signal by the signal processing module according to the preset EQ parameters based on the sound base judgment signal comprises the following specific operations:
when the male voice base judgment unit sends a male voice base judgment signal to the MCU module through the corresponding IO detection port, the MCU module judges that the corresponding voice audio signal is a male speaker; after judging the gender attribute of the voice, the MCU module sends the preset EQ parameters corresponding to the male voice to the audio processing module, and the audio processing module adjusts the audio signals of the human voice to obtain the human voice audio adjusting sound.
10. The automatic human voice restoration method according to claim 8, wherein: the method for acquiring the human voice audio regulation sound by regulating the human voice audio signal by the signal processing module according to the preset EQ parameters based on the sound base judgment signal comprises the following specific operations:
when the female voice base judgment unit sends a female voice base judgment signal to the MCU module through the corresponding IO detection port, the MCU module judges that the corresponding voice audio signal is a female speaker; after judging the gender attribute of the voice, the MCU module sends the preset EQ parameters corresponding to the female voice to the audio processing module, and the audio processing module adjusts the audio signals of the human voice to obtain the human voice audio adjusting voice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210174208.XA CN114554381B (en) | 2022-02-24 | 2022-02-24 | Automatic human voice restoration system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210174208.XA CN114554381B (en) | 2022-02-24 | 2022-02-24 | Automatic human voice restoration system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114554381A true CN114554381A (en) | 2022-05-27 |
| CN114554381B CN114554381B (en) | 2024-01-05 |
Family
ID=81676842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210174208.XA Active CN114554381B (en) | 2022-02-24 | 2022-02-24 | Automatic human voice restoration system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114554381B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008116534A (en) * | 2006-11-01 | 2008-05-22 | Yamaha Corp | Voice communication device |
| JP2011217328A (en) * | 2010-04-02 | 2011-10-27 | Alpine Electronics Inc | Audio device |
| JP2013083796A (en) * | 2011-10-11 | 2013-05-09 | Nippon Telegr & Teleph Corp <Ntt> | Method for identifying male/female voice, male/female voice identification device, and program |
| US20180219638A1 (en) * | 2015-09-30 | 2018-08-02 | Yamaha Corporation | Audio processing device and audio processing method |
| CN113409800A (en) * | 2020-03-16 | 2021-09-17 | 浙江宇视科技有限公司 | Processing method and device for monitoring audio, storage medium and electronic equipment |
-
2022
- 2022-02-24 CN CN202210174208.XA patent/CN114554381B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008116534A (en) * | 2006-11-01 | 2008-05-22 | Yamaha Corp | Voice communication device |
| JP2011217328A (en) * | 2010-04-02 | 2011-10-27 | Alpine Electronics Inc | Audio device |
| JP2013083796A (en) * | 2011-10-11 | 2013-05-09 | Nippon Telegr & Teleph Corp <Ntt> | Method for identifying male/female voice, male/female voice identification device, and program |
| US20180219638A1 (en) * | 2015-09-30 | 2018-08-02 | Yamaha Corporation | Audio processing device and audio processing method |
| CN113409800A (en) * | 2020-03-16 | 2021-09-17 | 浙江宇视科技有限公司 | Processing method and device for monitoring audio, storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 李昱瑛;: "不同传声器拾取男女语声的频率响应对比分析", 电声技术, no. 07 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114554381B (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2002224722B2 (en) | Method for determining an acoustic environment situation, application of the method and hearing aid | |
| KR100302370B1 (en) | Speech interval detection method and system, and speech speed converting method and system using the speech interval detection method and system | |
| US7158931B2 (en) | Method for identifying a momentary acoustic scene, use of the method and hearing device | |
| CN108198571B (en) | Bandwidth extension method and system based on self-adaptive bandwidth judgment | |
| JP2002366174A (en) | Method for covering g.729 annex b compliant voice activity detection circuit | |
| CN106887233B (en) | Audio data processing method and system | |
| CN106782586B (en) | Audio signal processing method and device | |
| US20200251120A1 (en) | Method and system for individualized signal processing of an audio signal of a hearing device | |
| CN103297581A (en) | Mobile terminal and method for adjusting equalizer thereof | |
| KR102655933B1 (en) | Method and apparatus for data augmentation | |
| CN114554381A (en) | Automatic human voice restoration system and method | |
| US7043427B1 (en) | Apparatus and method for speech recognition | |
| US20020118846A1 (en) | Acoustic signal processor | |
| CN106971734B (en) | Method and system for training and identifying model according to extraction frequency of model | |
| WO2021246304A1 (en) | Signal processing device, signal processing method, and program | |
| CN112951266B (en) | Tooth sound adjusting method, tooth sound adjusting device, electronic equipment and computer readable storage medium | |
| US20080228477A1 (en) | Method and Device For Processing a Voice Signal For Robust Speech Recognition | |
| CN115148193A (en) | Voice recognition method and system | |
| JPH0916193A (en) | Speech-rate conversion device | |
| CN107404625A (en) | The sound effect treatment method and device of terminal | |
| US5715362A (en) | Method of transmitting and receiving coded speech | |
| CN107978319B (en) | Method and device for processing human voice data | |
| CN115631743B (en) | High-precision voice recognition method and system based on voice chip | |
| CN111444381A (en) | Deep learning corpus-based classification method and storage device | |
| US7171245B2 (en) | Method for eliminating musical tone from becoming wind shear sound |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |