相关论文: Audio-Visual Decision Fusion for WFST-based and se…

This paper presents our method for the estimation of valence-arousal (VA) in the 8th Affective Behavior Analysis in-the-Wild (ABAW) competition. Our approach integrates visual and audio information through a multimodal framework. The visual…

In this study, we revisit key training strategies in machine learning often overlooked in favor of deeper architectures. Specifically, we explore balancing strategies, activation functions, and fine-tuning techniques to enhance speech…

We present two multimodal fusion-based deep learning models that consume ASR transcribed speech and acoustic data simultaneously to classify whether a speaker in a structured diagnostic task has Alzheimer's Disease and to what degree,…

In video-based emotion recognition (ER), it is important to effectively leverage the complementary relationship among audio (A) and visual (V) modalities, while retaining the intra-modal characteristics of individual modalities. In this…

In this work, we try to answer two questions: Can deeply learned features with discriminative power benefit an ASR system's robustness to acoustic variability? And how to learn them without requiring framewise labelled sequence training…

Active speaker detection plays a vital role in human-machine interaction. Recently, a few end-to-end audiovisual frameworks emerged. However, these models' inference time was not explored and are not applicable for real-time applications…

Unlike traditional Automatic Speech Recognition (ASR), Audio-Visual Speech Recognition (AVSR) takes audio and visual signals simultaneously to infer the transcription. Recent studies have shown that Large Language Models (LLMs) can be…

In this paper, we study different approaches for classifying emotions from speech using acoustic and text-based features. We propose to obtain contextualized word embeddings with BERT to represent the information contained in speech…

Integration of information from non-auditory cues can significantly improve the performance of speech-separation models. Often such models use deep modality-specific networks to obtain unimodal features, and risk being too costly or…

Considering the bimodal nature of human speech perception, lips, and teeth movement has a pivotal role in automatic speech recognition. Benefiting from the correlated and noise-invariant visual information, audio-visual recognition systems…

Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech recognition model requires robust generalization capabilities…

Human lip-reading is a challenging task. It requires not only knowledge of underlying language but also visual clues to predict spoken words. Experts need certain level of experience and understanding of visual expressions learning to…

Large pre-trained models are essential in paralinguistic systems, demonstrating effectiveness in tasks like emotion recognition and stuttering detection. In this paper, we employ large pre-trained models for the ACM Multimedia Computational…

In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a…

Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply…

Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus. However, little guidance exists on deploying these methods to improve production ASR systems that are…

Audio-visual feature synchronization for real-time speech enhancement in hearing aids represents a progressive approach to improving speech intelligibility and user experience, particularly in strong noisy backgrounds. This approach…

Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the…

This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from…