2018 · 115 citations · 21 references
ComputingLinguisticsAcousticsComputational LinguisticsNatural Language ProcessingAudio RecordingAuditory Scene AnalysisDeep LearningDimensionality ReductionRepresentation LearningSpeech RecognitionAudio RetrievalClassification LossConvolutional Neural NetworksEvent ClassificationLow-dimensional EmbeddingsQuery By Example RetrievalSemantic ConstraintsTriplet Loss
Even in the absence of any explicit semantic annotation, vast collections of audio recordings provide valuable information for learning the categorical structure of sounds. We consider several class-agnostic semantic constraints that apply to unlabeled nonspeech audio: (i) noise and translations in time do not change the underlying sound category, (ii) a mixture of two sound events inherits the categories of the constituents, and (iii) the categories of events in close temporal proximity are likely to be the same or related. Without labels to ground them, these constraints are incompatible with classification loss functions. However, they may still be leveraged to identify geometric inequalities needed for triplet loss-based training of convolutional neural networks. The result is low-dimensional embeddings of the input spectrograms that recover 41% and 84% of the performance of their fully-supervised counterparts when applied to downstream query-by-example sound retrieval and sound event classification tasks, respectively. Moreover, in limited-supervision settings, our unsupervised embeddings double the state-of-the-art classification performance.
21
FaceNet: A unified embedding for face recognition and clustering
2015 · 11.2K citations · Full text
CNN architectures for large-scale audio classification
Shawn Hershey, Sourish Chaudhuri, Daniel P. W. Ellis et al. · 2017 · 2.5K citations
Learning Fine-Grained Image Similarity with Deep Ranking
Jiang Wang, Yang Song, Thomas Leung et al. · 2014 · 1.3K citations