相关论文: Cocktail-Party Audio-Visual Speech Recognition

Accurate estimation of Room Impulse Response (RIR), which captures an environment's acoustic properties, is important for speech processing and AR/VR applications. We propose AV-RIR, a novel multi-modal multi-task learning approach to…

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…

In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust…

Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…

With computers getting more and more powerful and integrated in our daily lives, the focus is increasingly shifting towards more human-friendly interfaces, making Automatic Speech Recognition (ASR) a central player as the ideal means of…

Modern automatic speech recognition (ASR) systems need to be robust under acoustic variability arising from environmental, speaker, channel, and recording conditions. Ensuring such robustness to variability is a challenge in modern day…

Audio-visual recognition (AVR) has been considered as a solution for speech recognition tasks when the audio is corrupted, as well as a visual recognition method used for speaker verification in multi-speaker scenarios. The approach of AVR…

Audio-Visual Question Answering (AVQA) is a challenging task that involves answering questions based on both auditory and visual information in videos. A significant challenge is interpreting complex multi-modal scenes, which include both…

Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as independent units, potentially compromising contextual…

Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition. A common solution is to segment the audio in advance using a separate voice…

With the widespread use of intelligent systems, such as smart speakers, addressee recognition has become a concern in human-computer interaction, as more and more people expect such systems to understand complicated social scenes, including…

Pre-trained models have been a foundational approach in speech recognition, albeit with associated additional costs. In this study, we propose a regularization technique that facilitates the training of visual and audio-visual speech…

Police body-worn cameras have the potential to improve accountability and transparency in policing. Yet in practice, they result in millions of hours of footage that is never reviewed. We investigate the potential of large pre-trained…

Audio-Visual Speech Recognition (AVSR) leverages both acoustic and visual information for robust recognition under noise. However, how models balance these modalities remains unclear. We present Dr. SHAP-AV, a framework using Shapley values…

Automatic Speech Recognition (ASR) systems often fail to accurately transcribe speech from Deaf and Hard of Hearing (DHH) individuals, especially during real-time conversations. Existing personalization approaches typically require…

With the growing adoption of wearable devices such as smart glasses for AI assistants, wearer speech recognition (WSR) is becoming increasingly critical to next-generation human-computer interfaces. However, in real environments,…

We introduce LRS-VoxMM, an in-the-wild benchmark for audio-visual speech recognition (AVSR). The benchmark is derived from VoxMM, a dataset of diverse real-world spoken conversations with human-annotated transcriptions. We select…

Automatic speech recognition (ASR) has made remarkable progress but heavily relies on large-scale labeled data, which is scarce for low-resource languages like Vietnamese. While existing systems such as Whisper, USM, and MMS achieve…

Automatic Speech Recognition (ASR) systems in real-world settings need to handle imperfect audio, often degraded by hardware limitations or environmental noise, while accommodating diverse user groups. In human-robot interaction (HRI),…

We present a cross-modal unsupervised framework for active speaker detection in media content such as TV shows and movies. Machine learning advances have enabled impressive performance in identifying individuals from speech and facial…