paper-with-me

홈 › Papers

Memory Controlled Sequential Self Attention for Sound Recognition

2020-05-13 · Arjun Pankajakshan, Helen L. Bear, Vinod Subramanian, Emmanouil Benetos

In this paper we investigate the importance of the extent of memory in sequential self attention for sound recognition. We propose to use a memory controlled sequential self attention mechanism on top of a convolutional recurrent neural network (CRNN) model for polyphonic sound event detection (SED). Experiments on the URBAN-SED dataset demonstrate the impact of the extent of memory on sound recognition performance with the self attention induced SED model. We extend the proposed idea with a multi-head self attention mechanism where each attention head processes the audio embedding with explicit attention width values. The proposed use of memory controlled sequential self attention offers a way to induce relations among frames of sound event tokens. We show that our memory controlled self attention model achieves an event based F -score of 33.92% on the URBAN-SED dataset, outperforming the F -score of 20.10% reported by the model without self attention.

📄 PDF Abstract BibTeX arXiv:2005.06650

Code (1)

arjunp17/MemoryControlled-MultiheadSelfAtt 공식 구현

Tasks

Event DetectionSound Event Detection

Similar Papers 제목 키워드 기반

Iterative Memory Network for Long Sequential User Behavior Modeling in Recommender Systems

2021-09-29 · Qianying Lin, Wen-Ji Zhou, Yanshi Wang, Qing Da 외

Sequential user behavior modeling is a key feature in modern recommender systems, seeking to capture users' interest based on their past activities. There are two usual approaches to sequential modeling : Recurrent Neura…

Recommendation Systems

A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition

2020-06-30 · ICML 2020 1 · Anurag Kumar, Vamsi Krishna Ithapu

An important problem in machine auditory perception is to recognize and detect sound events. In this paper, we propose a sequential self-teaching approach to learning sounds. Our main proposition is that it is harder to …

Audio ClassificationTransfer Learning

DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition

2019-10-28 · Zhao You, Dan Su, Jie Chen, Chao Weng 외

Self-attention networks (SAN) have been introduced into automatic speech recognition (ASR) and achieved state-of-the-art performance owing to its superior ability in capturing long term dependency. One of the key ingredi…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Lightweight Self-Attentive Sequential Recommendation

2021-08-25 · Yang Li, Tong Chen, Peng-Fei Zhang, Hongzhi Yin

Modern deep neural networks (DNNs) have greatly facilitated the development of sequential recommender systems by achieving state-of-the-art recommendation performance on various sequential recommendation tasks. Given a s…

Recommendation SystemsSequential Recommendation

Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention

2021-05-28 · Yongji Wu, Lu Yin, Defu Lian, Mingyang Yin 외

Sequential recommendation plays an increasingly important role in many e-commerce services such as display advertisement and online shopping. With the rapid development of these services in the last two decades, users ha…

Sequential Recommendation