Related papers: LightBeam: An Accurate and Memory-Efficient CTC De…

Narrowly finetuned language models memorize implanted content verbatim, but auditing what a deployed model has been taught, without access to its weights or training data, remains an open challenge. Recent work shows that activation…

Neural audio codecs are at the core of modern conversational speech technologies, converting continuous speech into sequences of discrete tokens that can be processed by LLMs. However, existing codecs typically operate at fixed frame rates,…

Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. The major challenges are catastrophic forgetting and parameter interference for finetuning…

Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training…

Recent neural-network-based architectures for image segmentation make extensive usage of feature forwarding mechanisms to integrate information from multiple scales. Although yielding good results, even deeper architectures and alternative…

It is highly desirable that speech enhancement algorithms can achieve good performance while keeping low latency for many applications, such as digital hearing aids, acoustically transparent hearing devices, and public address systems. To…

We propose FSB-LSTM, a novel long short-term memory (LSTM) based architecture that integrates full- and sub-band (FSB) modeling, for single- and multi-channel speech enhancement in the short-time Fourier transform (STFT) domain. The model…

Connectionist Temporal Classification (CTC) model is a very efficient method for modeling sequences, especially for speech data. In order to use CTC model as an Automatic Speech Recognition (ASR) task, the beam search decoding with an…

CTC-based ASR systems face computational and memory bottlenecks in resource-limited environments. Traditional CTC decoders, requiring up to 90% of processing time in systems (e.g., wav2vec2-large on L4 GPUs), face inefficiencies due to…

Thanks to its superior features of fast read/write speed and low power consumption, spin-torque transfer magnetic random access memory (STT-MRAM) has become a promising non-volatile memory (NVM) technology that is suitable for many…

Decoding language information from brain signals represents a vital research area within brain-computer interfaces, particularly in the context of deciphering the semantic information from the fMRI signal. Although existing work uses LLM to…

We propose a novel method that combines a convolutional neural network (CNN) with a long short-term memory (LSTM) mechanism for accurate prediction of intracranial hemorrhage on computed tomography (CT) scans. The CNN plays the role of a…

Accurate and efficient medical image segmentation is crucial but challenging due to anatomical variability and high computational demands on volumetric data. Recent hybrid CNN-Transformer architectures achieve state-of-the-art results but…

Non-intrusive speech intelligibility prediction remains challenging due to variability in speakers, noise conditions, and subjective perception. We propose an uncertainty-aware approach that leverages Whisper embeddings in combination with…

In recent years, End-to-End speech recognition technology based on deep learning has developed rapidly. Due to the lack of Turkish speech data, the performance of Turkish speech recognition system is poor. Firstly, this paper studies a…

Cone-beam computed tomography (CBCT) is routinely collected during image-guided radiation therapy (IGRT) to provide updated patient anatomy information for cancer treatments. However, CBCT images often suffer from streaking artifacts and…

Automated extraction of concepts from patient clinical records is an essential facilitator of clinical research. For this reason, the 2010 i2b2/VA Natural Language Processing Challenges for Clinical Records introduced a concept extraction…

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli, essentially images, from functional Magnetic Resonance Imaging (fMRI)…

One of the greatest goals of neuroscience in recent decades has been to rehabilitate individuals who no longer have a functional relationship between their mind and their body. Although neuroscience has produced technologies which allow the…

Gboard Decoder produces suggestions by looking for paths that best match input touch points on the context aware search space, which is backed by the language Finite State Transducers (FST). The language FST is currently an N-gram language…