相关论文: Efficient conformer: Progressive downsampling and …

Continual learning involves training neural networks incrementally for new tasks while retaining the knowledge of previous tasks. However, efficiently fine-tuning the model for sequential tasks with minimal computational resources remains a…

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…

A key challenge for automatic speech recognition (ASR) systems is to model the speaker level variability. In this paper, compact speaker dependent learning hidden unit contributions (LHUC) are used to facilitate both speaker adaptive…

Finding synthetic artifacts of spoofing data will help the anti-spoofing countermeasures (CMs) system discriminate between spoofed and real speech. The Conformer combines the best of convolutional neural network and the Transformer,…

With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attention condenser networks…

Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches…

To enhance the performance of end-to-end (E2E) speech recognition systems in noisy or low signal-to-noise ratio (SNR) conditions, this paper introduces NoisyD-CT, a novel tri-stage training framework built on the Conformer-Transducer…

Automatic Audio Captioning (AAC) refers to the task of translating audio into a natural language that describes the audio events, source of the events and their relationships. The limited samples in AAC datasets at present, has set up a…

Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution…

Self-attention mechanisms are commonly included in a convolutional neural networks to achieve an improved efficiency performance balance. However, adding self-attention mechanisms adds additional hyperparameters to tune for the application…

The attention mechanisms are playing a boosting role in advancements in sequence-to-sequence problems. Transformer architecture achieved new state of the art results in machine translation, and it's variants are since being introduced in…

We introduce a novel architecture design that enhances expressiveness by incorporating multiple head classifiers (\ie, classification heads) instead of relying on channel expansion or additional building blocks. Our approach employs…

Conventional Deep Learning frameworks for continuous sign language recognition (CSLR) are comprised of a single or multi-modal feature extractor, a sequence-learning module, and a decoder for outputting the glosses. The sequence learning…

With the proliferation of video platforms on the internet, recording musical performances by mobile devices has become commonplace. However, these recordings often suffer from degradation such as noise and reverberation, which negatively…

Transformers, originally proposed for natural language processing (NLP) tasks, have recently achieved great success in automatic speech recognition (ASR). However, adjacent acoustic units (i.e., frames) are highly correlated, and…

Researchers are exploring novel computational paradigms such as sparse coding and neuromorphic computing to bridge the efficiency gap between the human brain and conventional computers in complex tasks. A key area of focus is neuromorphic…

Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We…

Considering the bimodal nature of human speech perception, lips, and teeth movement has a pivotal role in automatic speech recognition. Benefiting from the correlated and noise-invariant visual information, audio-visual recognition systems…