相关论文: Spatio-Temporal Attention Mechanism and Knowledge …

Spoken Language Understanding (SLU) is a core component of conversational systems, enabling machines to interpret user utterances. Despite its importance, developing effective SLU systems remains challenging due to the scarcity of labeled…

Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…

Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific…

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…

Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments. Unfortunately, most of current separation strategies prefer a straightforward fusion based on…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Explaining the decision of a multi-modal decision-maker requires to determine the evidence from both modalities. Recent advances in XAI provide explanations for models trained on still images. However, when it comes to modeling multiple…

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

This paper describes a novel knowledge distillation framework that leverages acoustically qualified speech data included in an existing training data pool as privileged information. In our proposed framework, a student network is trained…

A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Prior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential language models. However, their computational complexity renders…

Multilingual speech data often suffer from long-tailed language distribution, resulting in performance degradation. However, multilingual text data is much easier to obtain, yielding a more useful general language model. Hence, we are…

Speaker extraction algorithm relies on the speech sample from the target speaker as the reference point to focus its attention. Such a reference speech is typically pre-recorded. On the other hand, the temporal synchronization between…

Lipreading is a challenging cross-modal task that aims to convert visual lip movements into spoken text. Existing lipreading methods often extract visual features that include speaker-specific lip attributes (e.g., shape, color, texture),…

Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

We address the challenging problem of learning motion representations using deep models for video recognition. To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for…

Machine lipreading is a special type of automatic speech recognition (ASR) which transcribes human speech by visually interpreting the movement of related face regions including lips, face, and tongue. Recently, deep neural network based…

Deep learning has achieved outstanding performance for face recognition benchmarks, but performance reduces significantly for low resolution (LR) images. We propose an attention similarity knowledge distillation approach, which transfers…