Related papers: Amortized Neural Networks for Low-Latency Speech R…

This paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames. While previous works have made significant…

Sequence transducers, such as the RNN-T and the Conformer-T, are one of the most promising models of end-to-end speech recognition, especially in streaming scenarios where both latency and accuracy are important. Although various methods,…

Due to the unprecedented breakthroughs brought about by deep learning, speech enhancement (SE) techniques have been developed rapidly and play an important role prior to acoustic modeling to mitigate noise effects on speech. To increase the…

As wireless communication systems evolve, automatic modulation recognition (AMR) plays a key role in improving spectrum efficiency, especially in cognitive radio systems. Traditional AMR methods face challenges in complex, noisy…

End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training, as well as heavyweight computation for inference. Of course, this impedes…

Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks…

End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system. RNN transducer (RNN-T) is one of the popular end-to-end methods. Previous studies have…

Neural transducers (NT) provide an effective framework for speech streaming, demonstrating strong performance in automatic speech recognition (ASR). However, the application of NT to speech translation (ST) remains challenging, as existing…

Self-attention models have been successfully applied in end-to-end speech recognition systems, which greatly improve the performance of recognition accuracy. However, such attention-based models cannot be used in online speech recognition,…

Acceleration of deep neural networks to meet a specific latency constraint is essential for their deployment on mobile devices. In this paper, we design an architecture aware latency constrained sparse (ALCS) framework to prune and…

One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge…

Conventional speech enhancement technique such as beamforming has known benefits for far-field speech recognition. Our own work in frequency-domain multi-channel acoustic modeling has shown additional improvements by training a spatial…

In this work, we propose Retentive Network (RetNet) as a foundation architecture for large language models, simultaneously achieving training parallelism, low-cost inference, and good performance. We theoretically derive the connection…

Unification of automatic speech recognition (ASR) systems reduces development and maintenance costs, but training a single model to perform well in both offline and low-latency streaming settings remains challenging. We present a Unified…

Long short-term memory (LSTM) recurrent neural networks (RNNs) have been shown to give state-of-the-art performance on many speech recognition tasks, as they are able to provide the learned dynamically changing contextual window of all…

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…

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.…

This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR). In standard RNN-T, the emission of a blank symbol consumes exactly one input frame; in our proposed method, we introduce additional…

Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…