CN114373482A - Method and system for recognizing animal emotion through voice based on convolutional neural network - Google Patents
Method and system for recognizing animal emotion through voice based on convolutional neural network Download PDFInfo
- Publication number
- CN114373482A CN114373482A CN202111582306.9A CN202111582306A CN114373482A CN 114373482 A CN114373482 A CN 114373482A CN 202111582306 A CN202111582306 A CN 202111582306A CN 114373482 A CN114373482 A CN 114373482A
- Authority
- CN
- China
- Prior art keywords
- animal
- emotion
- voice
- neural network
- convolutional neural
- 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.)
- Pending
Links
- 241001465754 Metazoa Species 0.000 title claims abstract description 83
- 230000008451 emotion Effects 0.000 title claims abstract description 73
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 9
- 239000000284 extract Substances 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 claims description 3
- 241000282414 Homo sapiens Species 0.000 abstract description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 230000008909 emotion recognition Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Child & Adolescent Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for recognizing animal emotion through voice based on a convolutional neural network, which comprises the following steps: (1) collecting animal sound and converting the animal sound into a digital signal; (2) processing and compressing the digital signal and transmitting the digital signal to a sound characteristic identification module; (3) the voice feature recognition module extracts voice features by using a trained convolutional neural network model, converts the voice features and outputs the converted voice features to the emotion category recognition module; the trained convolutional neural network model is obtained by inputting the animal sound marked with sound characteristics into a convolutional neural network algorithm for training; (4) the emotion classification recognition module obtains emotion classifications corresponding to animal sounds by applying an SVM model; the method realizes the effect of recognizing the emotion of the animal according to the voice of the animal, so that the human can better understand the animal.
Description
Technical Field
The invention relates to the field of voice recognition, in particular to a method for recognizing animal emotion through voice based on a convolutional neural network, and further relates to a system for recognizing animal emotion through voice based on the convolutional neural network.
Background
With the development of animal behavioral research, how to recognize the emotion of animals and apply the emotion to production and life becomes a future direction, for example, recognizing the emotion of a guide dog makes blind people more aware of the behavior of the guide dog, and recognizing the emotion of a police dog makes workers better understand the intention of the blind people. Animal emotion can often be expressed from the sound emitted by the animal emotion recognition device, but the animal emotion recognition device usually needs a plurality of experienced persons to accurately judge and recognize the animal emotion, and in a special case, when the animal emotion recognition person is inexperienced, task failure can be caused, and even serious consequences can be caused.
Disclosure of Invention
In view of the above, one of the objects of the present invention is to provide a method for recognizing emotion of an animal through voice based on a convolutional neural network, which can accurately recognize emotion of the animal according to voice of the animal without professional personnel, so that humans can better understand the animal.
One of the purposes of the invention is realized by the following technical scheme:
the method for recognizing the animal emotion through the voice based on the convolutional neural network comprises the following steps:
(1) collecting animal sound and converting the animal sound into a digital signal;
(2) processing and compressing the digital signal and transmitting the digital signal to a sound characteristic identification module;
(3) the voice feature recognition module extracts voice features by using a trained convolutional neural network model, converts the voice features and outputs the converted voice features to the emotion category recognition module; the trained convolutional neural network model is obtained by inputting the animal voice marked with the voice characteristics into a convolutional neural network algorithm for training;
(4) and the emotion category recognition module obtains the emotion category corresponding to the animal voice by using the SVM model.
Further, in the step (1), a microphone is used for collecting animal sound and converting the animal sound into a digital signal.
Further, the digital signal is processed in the step (2) to establish a data matrix that can be identified by the trained convolutional neural network model.
Further, the emotion categories in the step (4) are sad, happy and neutral.
The second purpose of the invention is realized by the following technical scheme:
the system for recognizing the animal emotion through voice based on the convolutional neural network comprises a voice input and converter, a data preprocessor, a voice feature recognition module, an emotion category recognition module and an animal emotion output module;
the voice recording and converting device is used for collecting animal voice and converting the animal voice into digital signals;
the data preprocessor is used for processing and compressing the digital signal and then transmitting the digital signal to the sound characteristic identification module;
the voice feature recognition module extracts voice features by using a trained convolutional neural network model, converts the voice features and outputs the converted voice features to the emotion category recognition module; the trained convolutional neural network model is obtained by inputting animal sounds with marked sound features into a convolutional neural network algorithm for training;
the emotion type recognition module obtains emotion types corresponding to animal sounds by using an SVM model;
the animal emotion output module is used for outputting animal emotion.
The invention has the beneficial effects that:
the method for recognizing the animal emotion through the voice based on the convolutional neural network comprises the steps of firstly extracting animal voice characteristics through a trained convolutional neural network model, then inputting the animal voice characteristics into an SVM model to obtain emotion categories corresponding to animal voices, achieving the effect of recognizing the emotion of the animals according to the animal voices, and enabling human beings to understand the animals better.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of a method for recognizing animal emotion through voice based on a convolutional neural network.
FIG. 2 is a convolutional neural network model in the method for recognizing animal emotion through voice based on convolutional neural network.
FIG. 3 shows the classification of the emotion of the SVM model in the method for recognizing the emotion of an animal by voice based on the convolutional neural network.
Detailed Description
Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be understood that the preferred embodiments are illustrative of the invention only and are not limiting upon the scope of the invention.
As shown in fig. 1-3, the method for recognizing animal emotion through voice based on convolutional neural network comprises the following steps:
(1) collecting animal sounds by a microphone and converting the animal sounds into digital signals;
(2) processing and compressing the digital signal and transmitting the digital signal to a sound characteristic identification module; processing the digital signal to establish a data matrix which can be identified by a trained convolutional neural network model;
(3) the voice feature recognition module extracts voice features by using a trained convolutional neural network model, converts the voice features and outputs the converted voice features to the emotion category recognition module; the trained convolutional neural network model is used for extracting sound characteristics from keyword time points of 3 angles of a time domain, a frequency domain and a cepstrum domain of sound; the trained convolutional neural network model is obtained by inputting the animal sound marked with sound characteristics into a convolutional neural network algorithm for training;
the convolutional neural network algorithm is as follows:
wherein L (x, z) is:
L(x,z)＝-lnp(z|x)
setting:
(4) the emotion classification recognition module obtains emotion classifications corresponding to animal sounds by applying an SVM model; the mood categories are sad, happy and neutral.
The SVM model algorithm is as follows:
wherein w is a target function and α is a langerhan multiplier;
the method for recognizing the animal emotion through the voice based on the convolutional neural network has two using modes, wherein the first mode can be offline animal emotion calculation, and corresponding emotion classification results are directly output after corresponding emotion classes are recognized by a voice feature recognition module and an emotion class recognition module; and secondly, performing real-time online emotion category calculation, namely inputting voice into a voice characteristic recognition module according to fixed time frequency, and obtaining an emotion result of an animal timeline through the emotion category recognition module, so that the intention of the animal can be well understood.
The system for recognizing the animal emotion through voice based on the convolutional neural network comprises a voice input and converter, a data preprocessor, a voice feature recognition module, an emotion category recognition module and an animal emotion output module;
the voice recording and converting device is used for collecting animal voice and converting the animal voice into digital signals;
the data preprocessor is used for processing and compressing the digital signal and then transmitting the digital signal to the sound characteristic identification module;
the voice feature recognition module extracts voice features by using a trained convolutional neural network model, converts the voice features and outputs the converted voice features to the emotion category recognition module; the trained convolutional neural network model is obtained by inputting animal sound with a marked sound characteristic into a convolutional neural network algorithm for training;
the emotion classification recognition module obtains emotion classifications corresponding to animal sounds by applying an SVM model;
animal emotion output module for outputting animal emotion
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all that should be covered by the claims of the present invention.
Claims (5)
1. A method for recognizing animal emotion through voice based on a convolutional neural network is characterized in that: the method comprises the following steps:
(1) collecting animal sound and converting the animal sound into a digital signal;
(2) processing and compressing the digital signal and transmitting the digital signal to a sound characteristic identification module;
(3) the voice feature recognition module extracts voice features by using a trained convolutional neural network model, converts the voice features and outputs the converted voice features to the emotion category recognition module; the trained convolutional neural network model is obtained by inputting the animal sound marked with sound characteristics into a convolutional neural network algorithm for training;
(4) and the emotion category recognition module obtains the emotion category corresponding to the animal voice by using the SVM model.
2. The method for recognizing emotion of animal by voice based on convolutional neural network as claimed in claim 1, wherein: and (2) adopting a microphone to collect animal sound and converting the animal sound into a digital signal in the step (1).
3. The method for recognizing emotion of animal by voice based on convolutional neural network as claimed in claim 1 or 2, wherein: and (3) processing the digital signals in the step (2) to establish a data matrix which can be identified by the trained convolutional neural network model.
4. The method for recognizing emotion of animal by voice based on convolutional neural network as claimed in claim 1 or 2 or 3, wherein: the emotion categories in the step (4) are sad, happy and neutral.
5. A system for implementing the method for recognizing emotion of animal by voice based on convolutional neural network as claimed in claim 1, wherein: the system comprises a voice input and converter, a data preprocessor, a voice feature recognition module, an emotion category recognition module and an animal emotion output module;
the voice recording and converting device is used for collecting animal voice and converting the animal voice into digital signals;
the data preprocessor is used for processing and compressing the digital signal and then transmitting the digital signal to the sound characteristic identification module;
the voice feature recognition module extracts voice features by using a trained convolutional neural network model, converts the voice features and outputs the converted voice features to the emotion category recognition module; the trained convolutional neural network model is obtained by inputting animal sounds with marked sound features into a convolutional neural network algorithm for training;
the emotion type recognition module obtains emotion types corresponding to animal sounds by using an SVM model;
the animal emotion output module is used for outputting animal emotion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111582306.9A CN114373482A (en) | 2021-12-22 | 2021-12-22 | Method and system for recognizing animal emotion through voice based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111582306.9A CN114373482A (en) | 2021-12-22 | 2021-12-22 | Method and system for recognizing animal emotion through voice based on convolutional neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114373482A true CN114373482A (en) | 2022-04-19 |
Family
ID=81139235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111582306.9A Pending CN114373482A (en) | 2021-12-22 | 2021-12-22 | Method and system for recognizing animal emotion through voice based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114373482A (en) |
-
2021
- 2021-12-22 CN CN202111582306.9A patent/CN114373482A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11776530B2 (en) | Speech model personalization via ambient context harvesting | |
| CN107799126B (en) | Voice endpoint detection method and device based on supervised machine learning | |
| CN110364143B (en) | Voice awakening method and device and intelligent electronic equipment | |
| Shin et al. | Automatic detection system for cough sounds as a symptom of abnormal health condition | |
| Kumar et al. | Multilayer Neural Network Based Speech Emotion Recognition for Smart Assistance. | |
| Prasomphan | Improvement of speech emotion recognition with neural network classifier by using speech spectrogram | |
| CN110211594B (en) | Speaker identification method based on twin network model and KNN algorithm | |
| JPWO2003015076A1 (en) | Dog emotion discrimination device and method based on voice feature analysis | |
| US20220084543A1 (en) | Cognitive Assistant for Real-Time Emotion Detection from Human Speech | |
| Renjith et al. | Speech based emotion recognition in Tamil and Telugu using LPCC and hurst parameters—A comparitive study using KNN and ANN classifiers | |
| CN111145763A (en) | GRU-based voice recognition method and system in audio | |
| CN113851136A (en) | Clustering-based speaker recognition method, device, equipment and storage medium | |
| Tripathi et al. | Focal loss based residual convolutional neural network for speech emotion recognition | |
| CN108074581A (en) | For the control system of human-computer interaction intelligent terminal | |
| Anggraeni et al. | Control of robot arm based on speech recognition using Mel-Frequency Cepstrum Coefficients (MFCC) and K-Nearest Neighbors (KNN) method | |
| Chandrakala et al. | Multi-view representation for sound event recognition | |
| Zwerts et al. | Introducing a central African primate vocalisation dataset for automated species classification | |
| KR20170086233A (en) | Method for incremental training of acoustic and language model using life speech and image logs | |
| KR20200018154A (en) | Acoustic information recognition method and system using semi-supervised learning based on variational auto encoder model | |
| CN114373482A (en) | Method and system for recognizing animal emotion through voice based on convolutional neural network | |
| CN116682463A (en) | Multi-mode emotion recognition method and system | |
| Mane et al. | Identification & Detection System for Animals from their Vocalization | |
| Shin et al. | Speaker-invariant psychological stress detection using attention-based network | |
| KR102429365B1 (en) | System and method for analyzing emotion of speech | |
| CN114492579A (en) | Emotion recognition method, camera device, emotion recognition device and storage device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |