Related papers: Memory Controlled Sequential Self Attention for So…
Recent literature has demonstrated that the use of per-channel energy normalization (PCEN), has significant performance improvements over traditional log-scaled mel-frequency spectrograms in acoustic sound event detection (SED) in a…
Temporal detection problems appear in many fields including time-series estimation, activity recognition and sound event detection (SED). In this work, we propose a new approach to temporal event modeling by explicitly modeling event onsets…
Crash events identification and prediction plays a vital role in understanding safety conditions for transportation systems. While existing systems use traffic parameters correlated with crash data to classify and train these models, we…
Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection…
While multitask and transfer learning has shown to improve the performance of neural networks in limited data settings, they require pretraining of the model on large datasets beforehand. In this paper, we focus on improving the performance…
Due to the successful application of deep learning, audio spoofing detection has made significant progress. Spoofed audio with speech synthesis or voice conversion can be well detected by many countermeasures. However, an automatic speaker…
Several speech processing systems have demonstrated considerable performance improvements when deep complex neural networks (DCNN) are coupled with self-attention (SA) networks. However, the majority of DCNN-based studies on speech…
We describe a novel weakly labeled Audio Event Classification approach based on a self-supervised attention model. The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self-supervised…
Convolutional neural networks (CNN) are one of the best-performing neural network architectures for environmental sound classification (ESC). Recently, temporal attention mechanisms have been used in CNN to capture the useful information…
Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to…
In recent years, exploring effective sound separation (SSep) techniques to improve overlapping sound event detection (SED) attracts more and more attention. Creating accurate separation signals to avoid the catastrophic error accumulation…
This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model…
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 ingredients is the…
Sound event detection (SED), as a core module of acoustic environmental analysis, suffers from the problem of data deficiency. The integration of semi-supervised learning (SSL) largely mitigates such problem while bringing no extra…
In this paper, a combinative approach using Nonnegative Matrix Factorization (NMF) and Convolutional Neural Network (CNN) is proposed for audio clip Sound Event Detection (SED). The main idea begins with the use of NMF to approximate strong…
Environment shifts and conflicts present significant challenges for learning-based sound event localization and detection (SELD) methods. SELD systems, when trained in particular acoustic settings, often show restricted generalization…
Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are able to extract higher level features that are invariant to…
Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an unconstrained audio sample. Taking either the splitand-classify (i.e., frame-level) strategy or the more…
In a multi-speaker "cocktail party" scenario, a listener can selectively attend to a speaker of interest. Studies into the human auditory attention network demonstrate cortical entrainment to speech envelopes resulting in highly correlated…
Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue…