Related papers: Temporal-Channel Modeling in Multi-head Self-Atten…

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Transformer has shown promising results in many sequence to sequence transformation tasks recently. It utilizes a number of feed-forward self-attention layers to replace the recurrent neural networks (RNN) in attention-based encoder decoder…

Transformer-based time series forecasting has recently gained strong interest due to the ability of transformers to model sequential data. Most of the state-of-the-art architectures exploit either temporal or inter-channel dependencies,…

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Selective auditory attention decoding aims to identify the speaker of interest from listeners' neural signals, such as electroencephalography (EEG), in the presence of multiple concurrent speakers. Most existing methods operate at the…

End-to-end speech recognition has become popular in recent years, since it can integrate the acoustic, pronunciation and language models into a single neural network. Among end-to-end approaches, attention-based methods have emerged as…

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

In this work we propose a novel token-based training strategy that improves Transformer-Transducer (T-T) based speaker change detection (SCD) performance. The conventional T-T based SCD model loss optimizes all output tokens equally. Due to…

Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…

In exploring Predictive Health Management (PHM) strategies for Proton Exchange Membrane Fuel Cells (PEMFC), the Transformer model, widely used in data-driven approaches, excels in many fields but struggles with time series analysis due to…

In recent years, numerous Transformer-based models have been applied to long-term time-series forecasting (LTSF) tasks. However, recent studies with linear models have questioned their effectiveness, demonstrating that simple linear layers…

Self-supervised learning (SSL) models for speaker verification (SV) have gained significant attention in recent years. However, existing SSL-based SV systems often struggle to capture local temporal dependencies and generalize across…

Speech enhancement is a demanding task in automated speech processing pipelines, focusing on separating clean speech from noisy channels. Transformer based models have recently bested RNN and CNN models in speech enhancement, however at the…

Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers an alternative. However, existing methods lack the specific…

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping…

The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of filters to capture the speaker characteristics at any local…

Joint sound event localization and detection (SELD) is an emerging audio signal processing task adding spatial dimensions to acoustic scene analysis and sound event detection. A popular approach to modeling SELD jointly is using…

In this study, we propose the global context guided channel and time-frequency transformations to model the long-range, non-local time-frequency dependencies and channel variances in speaker representations. We use the global context…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Spiking neural networks (SNNs) offer a promising path toward energy-efficient speech command recognition (SCR) by leveraging their event-driven processing paradigm. However, existing SNN-based SCR methods often struggle to capture rich…