Related papers: Attention and DCT based Global Context Modeling fo…

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…

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In particular, we derive new context vectors using time…

Target speaker extraction focuses on extracting a target speech signal from an environment with multiple speakers by leveraging an enrollment. Existing methods predominantly rely on speaker embeddings obtained from the enrollment,…

Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism has shown to be effective in improving the model…

Conventional time-delay neural networks (TDNNs) struggle to handle long-range context, their ability to represent speaker information is therefore limited in long utterances. Existing solutions either depend on increasing model complexity…

Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases.…

Long-context models (LCMs) have demonstrated great potential in processing long sequences, facilitating many real-world applications. The success of LCMs can be attributed to their ability to locate implicit critical information within the…

Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks.…

The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

The use of channel-wise attention in CNN based speaker representation networks has achieved remarkable performance in speaker verification (SV). But these approaches do simple averaging on time and frequency feature maps before channel-wise…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

DIFF Transformer addresses the issue of irrelevant context interference by introducing a differential attention mechanism that enhances the robustness of local attention. However, it has two critical limitations: the lack of global context…

While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i)…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

Sound event localization frameworks based on deep neural networks have shown increased robustness with respect to reverberation and noise in comparison to classical parametric approaches. In particular, recurrent architectures that…

Transformer tends to overallocate attention to irrelevant context. In this work, we introduce Diff Transformer, which amplifies attention to the relevant context while canceling noise. Specifically, the differential attention mechanism…

Recently, many attention-based deep neural networks have emerged and achieved state-of-the-art performance in environmental sound classification. The essence of attention mechanism is assigning contribution weights on different parts of…

Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long context windows, their accuracy often deteriorates as input length grows. In practice, models…