Related papers: Wake Word Detection with Alignment-Free Lattice-Fr…

Spectral mapping uses a deep neural network (DNN) to map directly from noisy speech to clean speech. Our previous study found that the performance of spectral mapping improves greatly when using helpful cues from an acoustic model trained…

Keyword Spotting (KWS) remains challenging to achieve the trade-off between small footprint and high accuracy. Recently proposed metric learning approaches improved the generalizability of models for the KWS task, and 1D-CNN based KWS…

Sign spotting, the task of identifying and localizing individual signs within continuous sign language video, plays a pivotal role in scaling dataset annotations and addressing the severe data scarcity issue in sign language translation.…

Offline handwriting recognition (HWR) has improved significantly with the advent of deep learning architectures in recent years. Nevertheless, it remains a challenging problem and practical applications often rely on post-processing…

People are regularly confronted with potentially deceptive statements (e.g., fake news, misleading product reviews, or lies about activities). Only few works on automated text-based deception detection have exploited the potential of deep…

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…

Handwriting recognition has seen significant success with the use of deep learning. However, a persistent shortcoming of neural networks is that they are not well-equipped to deal with shifting data distributions. In the field of…

Since Bahdanau et al. [1] first introduced attention for neural machine translation, most sequence-to-sequence models made use of attention mechanisms [2, 3, 4]. While they produce soft-alignment matrices that could be interpreted as…

Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns.…

We describe an online handwriting system that is able to support 102 languages using a deep neural network architecture. This new system has completely replaced our previous Segment-and-Decode-based system and reduced the error rate by…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users. With the use of federated learning (FL), we introduce an efficient approach on…

Semantic correspondence methods have advanced to obtaining high-quality correspondences employing complicated networks, aiming to maximize the model capacity. However, despite the performance improvements, they may remain constrained by the…

Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a sleep-like consolidation mechanism in which a model…

In this paper, a tool for detecting LLM AI text generation is developed based on the Transformer model, aiming to improve the accuracy of AI text generation detection and provide reference for subsequent research. Firstly the text is…

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Instruction-based Large Language Models (LLMs) have proven effective in numerous few-shot or zero-shot Natural Language Processing (NLP) tasks. However, creating human-annotated instruction data is time-consuming, expensive, and often…

Automated speech recognition coverage of the world's languages continues to expand. However, standard phoneme based systems require handcrafted lexicons that are difficult and expensive to obtain. To address this problem, we propose a…

To address the growing demand for on-device LLM inference in resource-constrained environments, hybrid language models (HLM) have emerged, combining lightweight local models with powerful cloud-based LLMs. Recent studies on HLM have…

Recent advances in multimodal large language models (LLMs) have enabled unified reasoning across images, audio, and video, but extending such capability to brain imaging remains largely unexplored. Bridging this gap is essential to link…