Related papers: Improved Multi-Stage Training of Online Attention-…

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

In this study, a novel open-source brain-computer interface (BCI) platform was developed to decode scalp electroencephalography (EEG) signals associated with sustained attention. The EEG signal collection was conducted using a wireless…

Automated segmentation of structural defects from visual inspection imagery remains challenging due to the diversity of damage types, extreme class imbalance, and the need for precise boundary delineation. This paper presents DeltaSeg, a…

Current high-performing intracortical speech neuroprostheses achieve low word error rates but typically rely on external language models during inference, increasing memory, computation, and latency. In this work, we investigate whether…

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…

Interleaved texts, where posts belonging to different threads occur in one sequence, are a common occurrence, e.g., online chat conversations. To quickly obtain an overview of such texts, existing systems first disentangle the posts by…

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…

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…

Current speech enhancement (SE) research has largely neglected channel attention and spatial attention, and encoder-decoder architecture-based networks have not adequately considered how to provide efficient inputs to the intermediate…

With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-trained models are optimized for next-token prediction and…

This paper presents a novel open-domain dialogue generation model emphasizing the differentiation of speakers in multi-turn conversations. Differing from prior work that solely relies on the content of conversation history to generate a…

In this paper, we propose a bidimensional attention based recursive autoencoder (BattRAE) to integrate clues and sourcetarget interactions at multiple levels of granularity into bilingual phrase representations. We employ recursive…

The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we study how to reduce…

In self-supervised learning, it is challenging to reduce the gap between the enhancement performance on the estimated and target speech signals with existed pre-tasks. In this paper, we propose a multi-task pre-training method to improve…

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

A sequence-to-sequence model is a neural network module for mapping two sequences of different lengths. The sequence-to-sequence model has three core modules: encoder, decoder, and attention. Attention is the bridge that connects the…

The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network…

In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously. The proposed framework is not only more compact but can also yield comparable…

In this paper, we investigate the usage of large language models (LLMs) to improve the performance of competitive speech recognition systems. Different from previous LLM-based ASR error correction methods, we propose a novel multi-stage…

Advancements in non-invasive electroencephalogram (EEG)-based Brain-Computer Interface (BCI) technology have enabled communication through brain activity, offering significant potential for individuals with motor impairments. Existing…