scholar.google.com › citations
This work utilizes monotonic Parametric Signal Temporal Logic (PSTL) to design features for unsupervised classification of time series data that enables ...
Sep 30, 2024 · In this work, we utilize monotonic parametric signal temporal logic (PSTL) to design features for unsupervised classification of time series ...
The performance of an Acoustic Event Recognition (AER) system highly depends on the statistical information and the temporal dynamics in the audio signals.
Missing: Auditable Projection.
We focus on training convolutional features on unlabeled video data, using only the assumption that adjacent video frames contain semantically similar ...
Missing: Auditable | Show results with:Auditable
Mar 15, 2024 · In this paper, a classification system based on psychoacoustic features extracted from sound recordings is investigated.
Missing: Auditable Projection.
Our method uses unsupervised feature learning, a technique which learns regularities in spectro-temporal con- tent without reference to the training labels, ...
Missing: Auditable | Show results with:Auditable
RepLAI uses the audio signals in two unique ways: (1) to identify moments in time that are conducive to better self-supervised learning and (2) to learn ...
In this paper, we propose to learn features in an unsupervised manner directly from time-frequency images. Automatically learn- ing the features frees us ...
Feature extraction in automatic speech recognition (ASR) can be regarded as learning representations from lower-level to more abstract higher-level fea- tures.
Missing: Auditable | Show results with:Auditable
Jul 17, 2014 · Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning. Research Article.