Attentive max feature map and joint training for acoustic scene classification
Various attention mechanisms are being widely applied to acoustic scene classification. However, we empirically found that the attention mechanism can excessively discard potentially valuable information, despite improving performance. We propose the attentive max feature map that combines two effective techniques, attention and a max feature map, to further elaborate the attention mechanism and mitigate the above-mentioned phenomenon. We also explore various joint training methods, including multi-task learning, that allocate additional abstract labels for each audio recording. Our proposed system demonstrates state-of-the-art performance for single systems on Subtask A of the DCASE 2020 challenge by applying the two proposed techniques using relatively fewer parameters. Furthermore, adopting the proposed attentive max feature map, our team placed fourth in the recent DCASE 2021 challenge.
Code (0)
등록된 구현이 없습니다.
Tasks
Acoustic Scene ClassificationMulti-Task LearningScene ClassificationSimilar Papers 제목 키워드 기반
Binaural Signal Representations for Joint Sound Event Detection and Acoustic Scene Classification
Sound event detection (SED) and Acoustic scene classification (ASC) are two widely researched audio tasks that constitute an important part of research on acoustic scene analysis. Considering shared information between s…
Acoustic Scene ClassificationEvent DetectionScene ClassificationSound Event DetectionAcoustic Scene Clustering Using Joint Optimization of Deep Embedding Learning and Clustering Iteration
Recent efforts have been made on acoustic scene classification in the audio signal processing community. In contrast, few studies have been conducted on acoustic scene clustering, which is a newly emerging problem. Acous…
Acoustic Scene ClassificationAudio Signal ProcessingClusteringScene ClassificationDeep Learning for Joint Acoustic Echo and Acoustic Howling Suppression in Hybrid Meetings
Hybrid meetings have become increasingly necessary during the post-COVID period and also brought new challenges for solving audio-related problems. In particular, the interplay between acoustic echo and acoustic howling …
Speech SeparationAttentive Adversarial Learning for Domain-Invariant Training
Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in automatic speech recognition (ASR). In ADIT…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)domain classificationspeech-recognition+1JTAV: Jointly Learning Social Media Content Representation by Fusing Textual, Acoustic, and Visual Features
Learning social media content is the basis of many real-world applications, including information retrieval and recommendation systems, among others. In contrast with previous works that focus mainly on single modal or b…
Information RetrievalRecommendation SystemsRetrieval