相关论文: Splitformer: An improved early-exit architecture f…

Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer's quadratic complexity with respect to the input sequence length…

In contrast to other sequence tasks modeling hidden layer features with three axes, Dual-Path time and time-frequency domain speech enhancement models are effective and have low parameters but are computationally demanding due to their…

Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community. While previous architecture choices revolve around time-delay neural networks (TDNN) and long short-term…

This work introduces the Cleanformer, a streaming multichannel neural based enhancement frontend for automatic speech recognition (ASR). This model has a conformer-based architecture which takes as inputs a single channel each of raw and…

Despite the great success in Natural Language Processing (NLP) area, large pre-trained language models like BERT are not well-suited for resource-constrained or real-time applications owing to the large number of parameters and slow…

The impressive performance of transformer models has sparked the deployment of intelligent applications on resource-constrained edge devices. However, ensuring high-quality service for real-time edge systems is a significant challenge due…

On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…

Automatic speech quality assessment is essential for audio researchers, developers, speech and language pathologists, and system quality engineers. The current state-of-the-art systems are based on framewise speech features (hand-engineered…

Recently, deep neural networks have been outperforming conventional machine learning algorithms in many computer vision-related tasks. However, it is not computationally acceptable to implement these models on mobile and IoT devices and the…

Transformers have enabled impressive improvements in deep learning. They often outperform recurrent and convolutional models in many tasks while taking advantage of parallel processing. Recently, we proposed the SepFormer, which obtains…

The SepFormer architecture shows very good results in speech separation. Like other learned-encoder models, it uses short frames, as they have been shown to obtain better performance in these cases. This results in a large number of frames…

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…

Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks, yet their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and…

In recent years, deep learning models have become ubiquitous in industry and academia alike. Deep neural networks can solve some of the most complex pattern-recognition problems today, but come with the price of massive compute and memory…

Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision and reinforcement learning. In the field of natural language processing for example,…

Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging. This paper presents novel techniques that leverage the temporal…

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability…

Conformer-based attention models have become the de facto backbone model for Automatic Speech Recognition tasks. A blank symbol is usually introduced to align the input and output sequences for CTC or RNN-T models. Unfortunately, the long…

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

Ensuring the safety and efficiency of AI systems is a central goal of modern research. Formal verification provides guarantees of neural network robustness, while early exits improve inference efficiency by enabling intermediate…