Related papers: AST: Audio Spectrogram Transformer
Voice controlled virtual assistants (VAs) are now available in smartphones, cars, and standalone devices in homes. In most cases, the user needs to first "wake-up" the VA by saying a particular word/phrase every time he or she wants the VA…
The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very recently, as an alternative to LSTM layers, the Conformer…
Autism spectrum disorder (ASD) is a neurodevelopmental disorder which results in altered behavior, social development, and communication patterns. In past years, autism prevalence has tripled, with 1 in 54 children now affected. Given that…
Audio Sentiment Analysis is a popular research area which extends the conventional text-based sentiment analysis to depend on the effectiveness of acoustic features extracted from speech. However, current progress on audio sentiment…
Acoustic Echo Cancellation (AEC) plays a key role in speech interaction by suppressing the echo received at microphone introduced by acoustic reverberations from loudspeakers. Since the performance of linear adaptive filter (AF) would…
In NLP, convolutional neural networks (CNNs) have benefited less than recurrent neural networks (RNNs) from attention mechanisms. We hypothesize that this is because the attention in CNNs has been mainly implemented as attentive pooling…
A major advantage of a deep convolutional neural network (CNN) is that the focused receptive field size is increased by stacking multiple convolutional layers. Accordingly, the model can explore the long-range dependency of features from…
This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audios. We study three categories of Automatic Speech Recognition(ASR) models based on their core architecture: (1) convolutional, (2)…
This study presents a novel transfer learning approach and data augmentation technique for mental stability classification using human voice signals and addresses the challenges associated with limited data availability. Convolutional…
In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio tagging (AT) task, termed AST-SED. Pretrained AST models have…
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…
In this paper, ensembles of classifiers that exploit several data augmentation techniques and four signal representations for training Convolutional Neural Networks (CNNs) for audio classification are presented and tested on three freely…
Transformer structures have demonstrated outstanding skills in the deep learning space recently, significantly increasing the accuracy of models across a variety of domains. Researchers have started to question whether such a sophisticated…
Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum,via a naive convolution…
Transformers have become central to recent advances in audio classification. However, training an audio spectrogram transformer, e.g. AST, from scratch can be resource and time-intensive. Furthermore, the complexity of transformers heavily…
In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…
This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseN-ets are very deep, compact convolutional neural networks, which have…
Vision transformers (ViT) have made substantial progress for classification tasks in computer vision. Recently, Gong et. al. '21, introduced attention-based modeling for several audio tasks. However, relatively unexplored is the use of a…
Recent successful applications of convolutional neural networks (CNNs) to audio classification and speech recognition have motivated the search for better input representations for more efficient training. Visual displays of an audio…
Recently, convolutional neural networks (CNN) have achieved the state-of-the-art performance in acoustic scene classification (ASC) task. The audio data is often transformed into two-dimensional spectrogram representations, which are then…