Related papers: AV Speech Enhancement Challenge using a Real Noisy…
Audio-Visual Speech Recognition (AVSR) systems nowadays integrate Large Language Model (LLM) decoders with transformer-based encoders, achieving state-of-the-art results. However, the relative contributions of improved language modelling…
A judicious combination of dictionary learning methods, block sparsity and source recovery algorithm are used in a hierarchical manner to identify the noises and the speakers from a noisy conversation between two people. Conversations are…
Traditionally, adaptive filters have been deployed to achieve AEC by estimating the acoustic echo response using algorithms such as the Normalized Least-Mean-Square (NLMS) algorithm. Several approaches have been proposed over recent years…
Prior works on improving speech quality with visual input typically study each type of auditory distortion separately (e.g., separation, inpainting, video-to-speech) and present tailored algorithms. This paper proposes to unify these…
Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…
We propose to explore a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the…
Deepfake audio detection has progressed rapidly with strong pre-trained encoders (e.g., WavLM, Wav2Vec2, MMS). However, performance in realistic capture conditions - background noise (domestic/office/transport), room reverberation, and…
Body-conduction microphone signals (BMS) bypass airborne sound, providing strong noise resistance. However, a complementary modality is required to compensate for the inherent loss of high-frequency information. In this study, we propose a…
Audio-visual speech separation (AVSS) aims to extract a target speech signal from a mixed signal by leveraging both auditory and visual (lip movement) cues. However, most existing AVSS methods exhibit complex architectures and rely on…
Since facial actions such as lip movements contain significant information about speech content, it is not surprising that audio-visual speech enhancement methods are more accurate than their audio-only counterparts. Yet, state-of-the-art…
The ability to capture and segment sounding objects in dynamic visual scenes is crucial for the development of Audio-Visual Segmentation (AVS) tasks. While significant progress has been made in this area, the interaction between audio and…
Recent work on audio-visual navigation targets a single static sound in noise-free audio environments and struggles to generalize to unheard sounds. We introduce the novel dynamic audio-visual navigation benchmark in which an embodied AI…
This paper investigates the impact of head movements on audio-visual speech enhancement (AVSE). Although being a common conversational feature, head movements have been ignored by past and recent studies: they challenge today's…
The primary objective of speech enhancement is to reduce background noise while preserving the target's speech. A common dilemma occurs when a speaker is confined to a noisy environment and receives a call with high background and…
End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…
The ICASSP 2023 Acoustic Echo Cancellation Challenge is intended to stimulate research in acoustic echo cancellation (AEC), which is an important area of speech enhancement and is still a top issue in audio communication. This is the fourth…
Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance, a phenomenon we term studio-bias. To diagnose this mismatch, we introduce Vividh-ASR, a…
Recent advancements in speaker verification techniques show promise, but their performance often deteriorates significantly in challenging acoustic environments. Although speech enhancement methods can improve perceived audio quality, they…
This report presents VibeVoice-ASR, a general-purpose speech understanding framework built upon VibeVoice, designed to address the persistent challenges of context fragmentation and multi-speaker complexity in long-form audio (e.g.,…
Speech enhancement (SE) is crucial for reliable communication devices or robust speech recognition systems. Although conventional artificial neural networks (ANN) have demonstrated remarkable performance in SE, they require significant…