Related papers: Diagnostic-Driven Layer-Wise Compensation for Post…

Synthetic aperture radar automatic target recognition (SAR ATR) is of considerable importance in marine navigation and disaster monitoring. However, the coherent speckle noise inherent in SAR imagery often obscures salient target features,…

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced.…

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

Automatic Speech Recognition (ASR) systems suffer considerably when source speech is corrupted with noise or room impulse responses (RIR). Typically, speech enhancement is applied in both mismatched and matched scenario training and…

With the rising popularity of Large Language Models (LLMs), there has been an increasing interest in compression techniques that enable their efficient deployment. This study focuses on the Post-Training Quantization (PTQ) of LLMs. Drawing…

Owing to the complicated characteristics of 5G communication system, designing RF components through mathematical modeling becomes a challenging obstacle. Moreover, such mathematical models need numerous manual adjustments for various…

The attention-based encoder-decoder (AED) speech recognition model has been widely successful in recent years. However, the joint optimization of acoustic model and language model in end-to-end manner has created challenges for text…

Recent convolutional neural network (CNN) development continues to advance the state-of-the-art model accuracy for various applications. However, the enhanced accuracy comes at the cost of substantial memory bandwidth and storage…

State-of-the-art hybrid automatic speech recognition (ASR) system exploits deep neural network (DNN) based acoustic models (AM) trained with Lattice Free-Maximum Mutual Information (LF-MMI) criterion and n-gram language models. The AMs…

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be…

We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…

Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…

Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is its slow convergence and early performance plateau,…

Estimating covariance matrix from massive high-dimensional and distributed data is significant for various real-world applications. In this paper, we propose a data-aware weighted sampling based covariance matrix estimator, namely DACE,…

Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag behind: typical mean opinion score (MOS) estimators perform…

Existing methods to recover model accuracy on analog-digital hardware in the presence of quantization and analog noise include noise-injection training. However, it can be slow in practice, incurring high computational costs, even when…

Diabetic Retinopathy (DR) requires timely screening to prevent irreversible vision loss. However, its early detection remains a significant challenge since often the subtle pathological manifestations (lesions) get overlooked due to…

Denoising diffusion models have emerged as state-of-the-art in generative tasks across image, audio, and video domains, producing high-quality, diverse, and contextually relevant data. However, their broader adoption is limited by high…

In low-latency or mobile applications, lower computation complexity, lower memory footprint and better energy efficiency are desired. Many prior works address this need by removing redundant parameters. Parameter quantization replaces…

The development of edge computing places critical demands on energy-efficient model deployment for multiple-input multiple-output (MIMO) detection tasks. Deploying deep unfolding models such as PGD-Nets and ADMM-Nets into…