Related papers: Accelerating RNN-based Speech Enhancement on a Mul…

Recurrent Neural Networks (RNNs) with sophisticated units that implement a gating mechanism have emerged as powerful technique for modeling sequential signals such as speech or electroencephalography (EEG). The latter is the focus on this…

The imperative to deploy Deep Neural Network (DNN) models on resource-constrained edge devices, spurred by privacy concerns, has become increasingly apparent. To facilitate the transition from cloud to edge computing, this paper introduces…

The FloatSD technology has been shown to have excellent performance on low-complexity convolutional neural networks (CNNs) training and inference. In this paper, we applied FloatSD to recurrent neural networks (RNNs), specifically long…

Large-scale language models (LLMs) have demonstrated impressive performance, but their deployment presents challenges due to their significant memory usage. This issue can be alleviated through quantization. In this paper, we identify that…

As deep neural networks (DNNs) see increased deployment on mobile and edge devices, optimizing model efficiency has become crucial. Mixed-precision quantization is widely favored, as it offers a superior balance between efficiency and…

We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up…

Current neural audio codecs typically use residual vector quantization (RVQ) to discretize speech signals. However, they often experience codebook collapse, which reduces the effective codebook size and leads to suboptimal performance. To…

Prompt tuning is one of the successful approaches for parameter-efficient tuning of pre-trained language models. Despite being arguably the most parameter-efficient (tuned soft prompts constitute <0.1% of total parameters), it typically…

Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the…

Reduction of training time is an important issue in many tasks like patent translation involving neural networks. Data parallelism and model parallelism are two common approaches for reducing training time using multiple graphics processing…

Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the…

Large language models (LLMs) have shown immense potential across various domains, but their high memory requirements and inference costs remain critical challenges for deployment. Post-training quantization (PTQ) has emerged as a promising…

Residual neural networks are widely used in computer vision tasks. They enable the construction of deeper and more accurate models by mitigating the vanishing gradient problem. Their main innovation is the residual block which allows the…

Recurrent Neural Networks and in particular Long Short-Term Memory (LSTM) networks have demonstrated state-of-the-art accuracy in several emerging Artificial Intelligence tasks. However, the models are becoming increasingly demanding in…

Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization…

Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time…

In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are…

Deep learning-based speech enhancement (SE) methods often face significant computational challenges when needing to meet low-latency requirements because of the increased number of frames to be processed. This paper introduces the SlowFast…

The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial neural networks (ANNs).…

As large language models become increasingly prevalent, memory bandwidth constraints significantly limit inference throughput, motivating post-training quantization (PTQ). In this paper, we propose FireQ, a co-designed PTQ framework and an…