Related papers: Wideband Power Amplifier Behavioral Modeling Using…

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending…

Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captioning (AC). Most research focuses on training an adapter…

In this short note, we present an extension of long short-term memory (LSTM) neural networks to using a depth gate to connect memory cells of adjacent layers. Doing so introduces a linear dependence between lower and upper layer recurrent…

Long short-term memory (LSTM) has been widely used for sequential data modeling. Researchers have increased LSTM depth by stacking LSTM cells to improve performance. This incurs model redundancy, increases run-time delay, and makes the…

Speech intelligibility can be affected by multiple factors, such as noisy environments, channel distortions or physiological issues. In this work, we deal with the problem of automatic prediction of the speech intelligibility level in this…

Long Short-Term Memory (LSTM) neural networks have penetrated healthcare applications where real-time requirements and edge computing capabilities are essential. Gait analysis that detects abnormal steps to prevent patients from falling is…

The ever-increasing demand to extract temporal correlations across sequential data and perform context-based learning in this era of big data has led to the development of long short-term memory (LSTM) networks. Furthermore, there is an…

Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more…

Wake word (WW) spotting is challenging in far-field due to the complexities and variations in acoustic conditions and the environmental interference in signal transmission. A suite of carefully designed and optimized audio front-end (AFE)…

Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-MEM (Dopamine-Gated Agentic Memory), a biologically inspired…

With global IMT traffic expected to grow 10-100 times from 2020 to 20301, the Terahertz (THz) spectrum offers a promising solution to satisfy such forecasts. However, occupying the THz spectrum comes with its own challenges, an important…

Recurrent neural architectures such as LSTM and GRU remain widely used in sequence modeling, but they continue to face two core limitations: redundant gate-specific parameters and reduced ability to retain information across long temporal…

Language Models (LMs) are important components in several Natural Language Processing systems. Recurrent Neural Network LMs composed of LSTM units, especially those augmented with an external memory, have achieved state-of-the-art results.…

Abnormal event detection is a challenging task that requires effectively handling intricate features of appearance and motion. In this paper, we present an approach of detecting anomalies in videos by learning a novel LSTM based…

The progress of the Internet of Things(IoT) technologies and applications requires the efficient low power circuits and architectures to maintain and improve the performance of the increasingly growing data processing systems. Memristive…

M-MIMO is one of the crucial technologies for increasing spectral and energy efficiency of wireless networks. Most of the current works assume that M-MIMO arrays are equipped with a linear front end. However, ongoing efforts to make…

Recently, recurrent neural networks have become state-of-the-art in acoustic modeling for automatic speech recognition. The long short-term memory (LSTM) units are the most popular ones. However, alternative units like gated recurrent unit…

Many advances in Natural Language Processing have been based upon more expressive models for how inputs interact with the context in which they occur. Recurrent networks, which have enjoyed a modicum of success, still lack the…

This paper builds upon an existing speech emotion recognition model by adding an additional LSTM layer to improve the accuracy and processing efficiency of emotion recognition from audio data. By capturing the long-term dependencies within…

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of…