相关论文: Computation and Parameter Efficient Multi-Modal Fu…

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors. Generally, neural correction models are composed of encoder-decoder…

In this paper, we present a new open source toolkit for speech recognition, named CAT (CTC-CRF based ASR Toolkit). CAT inherits the data-efficiency of the hybrid approach and the simplicity of the E2E approach, providing a full-fledged…

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

The ability to interpret social cues comes naturally for most people, but for those living with Autism Spectrum Disorder (ASD), some experience a deficiency in this area. This paper presents the development of a multimodal augmented reality…

Facial expression recognition is a challenging classification task that holds broad application prospects in the field of human-computer interaction. This paper aims to introduce the method we will adopt in the 8th Affective and Behavioral…

Event cameras offer unique advantages for facial keypoint alignment under challenging conditions, such as low light and rapid motion, due to their high temporal resolution and robustness to varying illumination. However, existing RGB facial…

End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Intra-sentential code-switching (CS) refers to the alternation between languages that happens within a single utterance and is a significant challenge for Automatic Speech Recognition (ASR) systems. For example, when a Vietnamese speaker…

End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a…

The demand for edge AI in vision-language tasks requires models that achieve real-time performance on resource-constrained devices with limited power and memory. This paper proposes two adaptive compression techniques -- Sparse Temporal…

This paper explores the development of a multimodal sentiment analysis model that integrates text, audio, and visual data to enhance sentiment classification. The goal is to improve emotion detection by capturing the complex interactions…

Audio-Visual Speech Recognition (AVSR) leverages both acoustic and visual cues to improve speech recognition under noisy conditions. A central question is how to design a fusion mechanism that allows the model to effectively exploit visual…

Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…

Existing robotic manipulation methods primarily rely on visual and proprioceptive observations, which may struggle to infer contact-related interaction states in partially observable real-world environments. Acoustic cues, by contrast,…

End-to-end automatic speech recognition (E2E-ASR) can be classified by its decoder architectures, such as connectionist temporal classification (CTC), recurrent neural network transducer (RNN-T), attention-based encoder-decoder, and…

Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and…

Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural network. In these models,…

Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the…