Related papers: Is Phase Really Needed for Weakly-Supervised Derev…

Speech separation is a fundamental task in audio processing, typically addressed with fully supervised systems trained on paired mixtures. While effective, such systems typically rely on synthetic data pipelines, which may not reflect…

Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…

While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio…

Speech dereverberation aims to alleviate the negative impact of late reverberant reflections. The weighted prediction error (WPE) method is a well-established technique known for its superior performance in dereverberation. However, in…

We present a method to remove unknown convolutive noise introduced to speech by reverberations of recording environments, utilizing some amount of training speech data from the reverberant environment, and any available non-reverberant…

The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem. Majority of the existing approaches focus on learning a common representation by…

In this paper, we exploit the effective way to leverage contextual information to improve the speech dereverberation performance in real-world reverberant environments. We propose a temporal-contextual attention approach on the deep neural…

The paper introduces Diff-Filter, a multichannel speech enhancement approach based on the diffusion probabilistic model, for improving speaker verification performance under noisy and reverberant conditions. It also presents a new two-step…

Various sources have reported the WaveNet deep learning architecture being able to generate high-quality speech, but to our knowledge there haven't been studies on the interpretation or visualization of trained WaveNets. This study…

A system capturing the association between video frames and textual queries offer great potential for better video analysis. However, training such a system in a fully supervised way inevitably demands a meticulously curated video dataset…

Speech time reversal refers to the process of reversing the entire speech signal in time, causing it to play backward. Such signals are completely unintelligible since the fundamental structures of phonemes and syllables are destroyed.…

Whisper fails to correctly transcribe dementia speech because persons with dementia (PwDs) often exhibit irregular speech patterns and disfluencies such as pauses, repetitions, and fragmented sentences. It was trained on standard speech and…

Background noise, interfering speech and room reverberation frequently distort target speech in real listening environments. In this study, we address joint speech separation and dereverberation, which aims to separate target speech from…

Time-series forecasting is crucial for numerous real-world applications including weather prediction and financial market modeling. While temporal-domain methods remain prevalent, frequency-domain approaches can effectively capture…

Speaker separation refers to isolating speech of interest in a multi-talker environment. Most methods apply real-valued Time-Frequency (T-F) masks to the mixture Short-Time Fourier Transform (STFT) to reconstruct the clean speech. Hence…

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize…

Neural network based speech dereverberation has achieved promising results in recent studies. Nevertheless, many are focused on recovery of only the direct path sound and early reflections, which could be beneficial to speech perception,…

Unsupervised speech models are becoming ubiquitous in the speech and machine learning communities. Upstream models are responsible for learning meaningful representations from raw audio. Later, these representations serve as input to…

Typically, neural network-based speech dereverberation models are trained on paired data, composed of a dry utterance and its corresponding reverberant utterance. The main limitation of this approach is that such models can only be trained…

Learning with noisy labels remains challenging because over-parameterized networks memorize corrupted supervision. Meta-learning-based sample reweighting mitigates this by using a small clean subset to guide training, yet its behavior and…