Combined spectral and speech features for pig speech recognition

Abstract

The sound of the pig is one of its important signs, which can reflect various states such as hunger, pain or emotional state, and directly indicates the growth and health status of the pig. Existing speech recognition methods usually start with spectral features. The use of spectrograms to achieve classification of different speech sounds, while working well, may not be the best approach for solving such tasks with single-dimensional feature input. Based on the above assumptions, in order to more accurately grasp the situation of pigs and take timely measures to ensure the health status of pigs, this paper proposes a pig sound classification method based on the dual role of signal spectrum and speech. Spectrograms can visualize information about the characteristics of the sound under different time periods. The audio data are introduced, and the spectrogram features of the model input as well as the audio time-domain features are complemented with each other and passed into a pre-designed parallel network structure. The network model with the best results and the classifier were selected for combination. An accuracy of 93.39% was achieved on the pig speech classification task, while the AUC also reached 0.99163, demonstrating the superiority of the method. This study contributes to the direction of computer vision and acoustics by recognizing the sound of pigs. In addition, a total of 4,000 pig sound datasets in four categories are established in this paper to provide a research basis for later research scholars.

Study on a Pig Vocalization Classification Method Based on Multi-Feature Fusion

“…Sound is one of the important pieces of physical information of pigs, so it is significant to use the information contained in the sound of pigs to determine the current status of pigs [ 19 ]. The classification model developed in this study could be applied as a warning tool or/and supplementary method in assessing air quality inside livestock buildings, especially around the animal occupied zone, to facilitate efficient management and precision livestock farming.…”

“…Wang et al [ 18 ] reduced the dimensionality of the MFCC features of piglet coughing vocalization using principal component analysis (PCA), the input features were reduced to 13 from 24, and the accuracy achieved 95% using relatively mature and simple support vector machine algorithms. The sound of pig is one of its important pieces of physical information that closely reflect its growth status and health condition; different sound categories are considered as bases for judging the stress state of pigs [ 19 ]. In addition to coughing, typical pig sounds include grunting and squealing.…”

The Pig as a Translational Animal Model for Biobehavioral and Neurotrauma Research

“…Pigs are a vocal species, who communicate in a herd by calling to one another. A speech recognition paradigm for pigs was recently developed by Wu et al (2022), utilizing a fusion network that combines both spectral and audio features to classify individual pig speech patterns [ 47 ]. Vocal expression has also been used to assess emotional states in pigs.…”

Research on Pig Sound Recognition Based on Deep Neural Network and Hidden Markov Models

“…In the study of Wu et al [ 3 ], improved empirical mode decomposition-Teager energy operator (EMD-TEO) cepstral distance was used for the endpoint detection of pig sound signals, and the accuracy could reach 90.293%. In the research of pig sound recognition, Wu et al [ 4 ] proposed a pig sound classification method based on the dual roles of signal spectrum and speech, which achieved a classification accuracy of 93.39% in the pig sound classification task. Ji et al [ 5 ] extracted audio features including root-mean-square energy (RMS), mel-frequency cepstral coefficients (MFCCs), and zero-crossing rate (ZCR) from the audio signals of pigs, extracted visual features including localized binary pattern (LBP) and histogram of gradients (HOG) using constant Q transform (CQT) spectrograms, and fused the audio with the visual features to detect whether the pigs were coughing or not, with an accuracy of 96.45%.…”

“…(3) Model testing. After the DNN-HMM model was trained, we used the MFCC features extracted from the test sound samples corresponding to several pig behavior states to input into the five sound models ( , , ),( 1,2,3,4,5) n…”