Results 31 to 40 of about 7,229,432 (222)
Mel Spectrogram Inversion with Stable Pitch [PDF]
CoRR, 2022 7 pages, 5 figures, Proceedings of the 23st International Society for Music Information Retrieval Conference, ISMIR ...
Bruno Di Giorgi +2 more
openaire +2 more sources
Multitaper-Mel Spectrograms for Keyword Spotting
IEEE Signal Processing Letters, 2022 Keyword spotting (KWS) is one of the speech recognition tasks most sensitive to the quality of the feature representation. However, the research on KWS has traditionally focused on new model topologies, putting little emphasis on other aspects like feature extraction.
Douglas David Baptista de Souza +3 more
openaire +2 more sources
Research on Speech Synthesis Based on Mixture Alignment Mechanism
Sensors, 2023 In recent years, deep learning-based speech synthesis has attracted a lot of attention from the machine learning and speech communities. In this paper, we propose Mixture-TTS, a non-autoregressive speech synthesis model based on mixture alignment ...
Yan Deng +4 more
doaj +1 more source
Evaluation of Respiratory Sounds Using Image-Based Approaches for Health Measurement Applications
IEEE Open Journal of Engineering in Medicine and Biology, 2022 Goal: The evaluation of respiratory events using audio sensing in an at-home setting can be indicative of worsening health conditions. This paper investigates the use of image-based transfer learning applied to five audio visualizations to evaluate three
Madison Cohen-McFarlane +6 more
doaj +1 more source
Applied Sciences, 2022 In the background of artificial intelligence, the realization of smooth communication between people and machines has become the goal pursued by people. Mel spectrograms is a common method used in speech emotion recognition, focusing on the low-frequency
Juan Li +5 more
doaj +1 more source
Pain Level Classification from Speech Using GRU-Mixer Architecture with Log-Mel Spectrogram Features. [PDF]
Diagnostics (Basel)Background/Objectives: Automatic pain detection from speech signals holds strong promise for non-invasive and real-time assessment in clinical and caregiving settings, particularly for populations with limited capacity for self-report.
Alhudhaif A.
europepmc +2 more sources
Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms
CoRR, 2022 We describe our approach for the generative emotional vocal burst task (ExVo Generate) of the ICML Expressive Vocalizations Competition. We train a conditional StyleGAN2 architecture on mel-spectrograms of preprocessed versions of the audio samples. The mel-spectrograms generated by the model are then inverted back to the audio domain. As a result, our
Marco Jiralerspong, Gauthier Gidel
openaire +2 more sources
Automated Detection of COVID-19 Cough Sound using Mel-Spectrogram Images and Convolutional Neural Network [PDF]
, 2023 COVID-19 is a new disease caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) variant. The initial symptoms of the disease commonly include fever (83-98%), fatigue or myalgia, dry cough (76-82%), and shortness of breath (31-55 ...
Indriani, Fatma +4 more
core +1 more source