Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 21 for “"Mel Spectrograms"”.
-
Synthetic data generation methods and their application to incomplete experimental design /
… (cGAN) was employed to generate synthetic Mel spectrograms based on contextual information. The proposed methodology involves preprocessing raw vibration signals by injecting Laplace noise, segmenting them into overlapping windows, finally transforming, signals into Mel spectrograms. These …
-
Muzikos rekomendacijų informacinė sistema /
… processing of raw data and transformation into mel—spectrograms, converting signal representation from mel—spectrograms to embeddings. The preparation and use of OpenL3 and CLAP models differed from converting MusicRecNet’s audio signal into embeddings, as these models did not need to convert …
-
ENGINEERED ACOUSTIC FEATURES AND NEURAL NETWORKS FOR MUSIC EMOTION RECOGNITION: AN EMPIRICAL COMPARISON ON THE DEAM DATASET
… while the CNN learns from 30-second log-mel spectrograms. The evaluation uses five saved song-level train, validation, and test partitions. The original XGBoost baseline achieves mean RMSE of 0.780 for Valence and 0.793 for Arousal, below every tested CNN configuration on both targets in …
-
Kalbos emociju˛ atpažinimas naudojant mašinini˛ mokymąsi /
… into segments of fixed duration, creates their mel spectrograms, and applies a deep learning model for emotion classification. The model was trained using the RAVDESS dataset, and its performance was evaluated using several classification quality metrics. Experimental results showed that the …
-
Adversarial Representation Learning for Synthetic Replacement of Sensitive Speech Data
… one. The model is based on a CNN that takes mel-spectrograms as input. A MelGAN is used to invert the spectrograms back to raw audio waveforms. We show that it is possible to hide sensitive information such as gender by generating new data, trained adversarially to maintain utility and …
-
Specific Loudness Features for Sound Event Classification and Localization in Machine Learning
… systems that classify and localize sound events. Mel spectrograms are the de factostandard in audio machine learning, yet they are an incomplete perceptual transform: they warp the frequency axis to match human hearing but leave the magnitude axis in raw logpower, omitting the equal-loudness …
-
Akustinių garso signalo požymių parinkimas muzikos žanro klasifikavimo uždaviniui spręsti /
… on a 58 feature vector, a 17 feature vector, spectrograms and mel spectrograms. The best results were obtained by using the random forest algorithm with the vector containing 58 features. The results of this algorithm were equal to 0,76 for precision score, 0,77 for recall value and 0,76 for …
-
Audio Based Road Type Classification Using CNNs and AST: Development of Audio Based Road Type Classification Models with Focus on Convolutional Neural Networks and The Audio Spectrogram Transformer Model
… using feature extraction techniques such as Mel-spectrograms and Mel-frequency cepstral coefficients (MFCCs). Multiple CNN models were developed and trained, while a pre-trained Audio Spectrogram Transformer model was fine-tuned for the task. All models were evaluated using stratified 5-fold …
-
From Data to Generation: Methods in Deep Learning for Audio
… vocoder that reconstructs 44.1\,kHz audio from mel spectrograms using a generative adversarial encoder-decoder architecture informed by recent advances in neural audio codecs, achieving state-of-the-art performance in polyphonic music synthesis. We further address source separation by adapting …
-
Time-Series Data Analysis in Biomedical Applications
… advanced feature extraction techniques, such as Mel spectrograms, the algorithm effectively distinguishes cough events from other audio signals, achieving high accuracy. Its adaptability to varying noise conditions makes it ideal for real-time respiratory monitoring, with strong potential for …
-
Analysis of Limitations of AI Tools for Pediatric Speech Language Pathology Documentation and Mitigation Strategies
… using the cosine distance between their mel-spectrograms. The samples were also passed through a phoneme-based ASR model to get the layer activations. The cosine distances and layer outputs were then tested as predictive measures of articulation accuracy, with layer outputs yielding the …
-
Online evaluation of weld quality for Friction Stir Welding process
… are identified through patterns observed on the spectrograms obtained from the recorded AE signals of the FSW process. For the classification of welds according to the type of defects and flaws, convolutional neural networks (CNN) are utilized with spectrograms and mel-spectrograms as the input …
-
Linear decoding models of rich audiovisual stimuli utilizing intracranial recordings
… information of electrodes to the pitch, and the mel-spectrogram of their respective movie trailers. Utilizing an anatomical ablation method, we were able to demonstrate the importance of primary auditory cortical signals in the robustness of our predicted acoustic features. Next, we found …
-
A Deep Representation Learning Framework for Medical Imaging Data Analysis
… data representation, which is computed from mel spectrograms within specific frequency ranges. Deep feature learning from the representations has achieved an F-score of 0.9767. When deployed to the detection of abnormalities in mammograms, the framework trains patch CNNs and builds …
-
Data efficiency and domain robustness in speech-based biomarking of health
… feature extraction was explored using mel-frequency cepstral coefficients (MFCCs) with long frames that de-emphasize vocal-tract detail, glottal-source MFCCs that exclude vocal-tract resonances, and transformer-based self-supervised representations (wav2vec 2.0, HuBERT). Across binary …
-
Speech Mode Classification using the Fusion of CNNs and LSTM Networks
… the usage of pre-trained deep neural networks, namely AlexNet, ResNet18 and SqueezeNet. Thus, we compare the classification efficiency of a set of deep learning-based classifiers, while we also assess the impact of different 2D image representations (spectrograms, mel-spectrograms, and their …
-
A Call Recognition Approach for Endangered or Threatened Chorusing Amphibian Species using Deep Learning Architectures
… the Hamming window function to each frame. Mel-frequency Cepstral Coefficients (MFCCs) with their first and second derivatives or Spectral Sub-band Centroids (SSCs) or Mel-spectrograms audio features have been extracted for each frame. These features were used to train the predictive or …
-
Deep Learning Based Sound Event Detection and Classification
… of identifying objects in images by treating the spectrograms of the sound as images. AudioMask first applies Mask R-CNN, an algorithm for detecting objects in images, to the log-scaled mel-spectrograms of the sound files. Then we use a frame-based sound event classifier trained independently from …
-
Advancing Edge Intelligence: Strategies for Improving Machine Learning on Embedded Devices
… processes the broad energy context of Log-Mel spectrograms alongside the fine-grained acoustic texture of Mel-frequency cepstral coefficients (MFCCs). This unified feature set is fused through grouped depthwise and pointwise convolutions, allowing the DFM-KWS model to drastically reduce …
-
NON-DESTRUCTIVE DEEP LEARNING APPROACHES FOR FRUIT QUALITY PREDICTION AND CLASSIFICATION: PAPAYA AND AVOCADO
… the audio data were converted to log-Mel spectrograms, and the avocado firmness data were processed using Box-Cox transformation. The collected data were split into training, validation, and test sets in an 8:1:1 ratio for model training and evaluation. A multimodal ripeness …
Page 1 of 2