Related papers: Multi-View Frequency-Attention Alternative to CNN …

We study transfer learning in convolutional network architectures applied to the task of recognizing audio, such as environmental sound events and speech commands. Our key finding is that not only is it possible to transfer representations…

Transformers have been extensively studied in medical image segmentation to build pairwise long-range dependence. Yet, relatively limited well-annotated medical image data makes transformers struggle to extract diverse global features,…

In this paper, we tackle the high computational overhead of Transformers for efficient image super-resolution~(SR). Motivated by the observations of self-attention's inter-layer repetition, we introduce a convolutionized self-attention…

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we…

The transformer architecture has catalyzed revolutionary advances in language modeling. However, recent architectural recipes, such as state-space models, have bridged the performance gap. Motivated by this, we examine the benefits of…

UniSpeech has achieved superior performance in cross-lingual automatic speech recognition (ASR) by explicitly aligning latent representations to phoneme units using multi-task self-supervised learning. While the learned representations…

Speaker recognition is the process of identifying a speaker based on the voice. The technology has attracted more attention with the recent increase in popularity of smart voice assistants, such as Amazon Alexa. In the past few years,…

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…

End-to-end models are favored in automatic speech recognition (ASR) because of their simplified system structure and superior performance. Among these models, Transformer and Conformer have achieved state-of-the-art recognition accuracy in…

The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain.…

In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the effectiveness and robustness of automatic speech recognition (ASR) contextual biasing without introducing additional parameters. A common…

Connectionist Temporal Classification (CTC) models are popular for their balance between speed and performance for Automatic Speech Recognition (ASR). However, these CTC models still struggle in other areas, such as personalization towards…

Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts. This improvement could be due to the powerful modeling ability of the multi-head…

For many Automatic Speech Recognition (ASR) tasks audio features as spectrograms show better results than Mel-frequency Cepstral Coefficients (MFCC), but in practice they are hard to use due to a complex dimensionality of a feature space.…

End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we…

Speech representations learned in a self-supervised fashion from massive unlabeled speech corpora have been adapted successfully toward several downstream tasks. However, such representations may be skewed toward canonical data…

For a speech-enhancement algorithm, it is highly desirable to simultaneously improve perceptual quality and recognition rate. Thanks to computational costs and model complexities, it is challenging to train a model that effectively…

Attention mechanism has been widely utilized in speech enhancement (SE) because theoretically it can effectively model the long-term inherent connection of signal both in time domain and spectrum domain. However, the generally used global…

Inspired by the progress of the End-to-End approach [1], this paper systematically studies the effects of Number of Filters of convolutional layers on the model prediction accuracy of CNN+RNN (Convolutional Neural Networks adding to…

Transformer-based architectures for speaker verification typically require more training data than ECAPA-TDNN. Therefore, recent work has generally been trained on VoxCeleb1&2. We propose a backbone network based on self-attention, which…