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

Understanding how speech foundation models capture non-verbal cues is crucial for improving their interpretability and adaptability across diverse tasks. In our work, we analyze several prominent models such as Whisper, Seamless, Wav2Vec,…

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

In this work, we present a two-stage method for speaker extraction under reverberant and noisy conditions. Given a reference signal of the desired speaker, the clean, but the still reverberant, desired speaker is first extracted from the…

Environmental sound recordings often contain intelligible speech, raising privacy concerns that limit analysis, sharing and reuse of data. In this paper, we introduce a method that renders speech unintelligible while preserving both the…

Reverberation results in reduced intelligibility for both normal and hearing-impaired listeners. This paper presents a novel psychoacoustic approach of dereverberation of a single speech source by recycling a pre-trained binaural anechoic…

Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it allows training models with noisy annotations obtained from…

Partial deepfake speech detection requires identifying manipulated regions that may occur within short temporal portions of an otherwise bona fide utterance, making the task particularly challenging for conventional utterance-level…

This paper proposes a weakly-supervised learning framework for dynamics estimation from human motion. Although there are many solutions to capture pure human motion readily available, their data is not sufficient to analyze quality and…

The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…

We propose a novel method for generating scene-aware training data for far-field automatic speech recognition. We use a deep learning-based estimator to non-intrusively compute the sub-band reverberation time of an environment from its…

One key aspect differentiating data-driven single- and multi-channel speech enhancement and dereverberation methods is that both the problem formulation and complexity of the solutions are considerably more challenging in the latter case.…

Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic…

Scene Parsing is a crucial step to enable autonomous systems to understand and interact with their surroundings. Supervised deep learning methods have made great progress in solving scene parsing problems, however, come at the cost of…

Speech dereverberation is often an important requirement in robust speech processing tasks. Supervised deep learning (DL) models give state-of-the-art performance for single-channel speech dereverberation. Temporal convolutional networks…

This letter proposes a new time domain absorption approach designed to reduce masking components of speech signals under noisy-reverberant conditions. In this method, the non-stationarity of corrupted signal segments is used to detect…

This paper aims at eliminating the interfering speakers' speech, additive noise, and reverberation from the noisy multi-talker speech mixture that benefits automatic speech recognition (ASR) backend. While the recently proposed Weighted…

Both reverberation and additive noises degrade the speech quality and intelligibility. Weighted prediction error (WPE) method performs well on the dereverberation but with limitations. First, WPE doesn't consider the influence of the…

Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not…

While significant advances have been made with respect to the separation of overlapping speech signals, studies have been largely constrained to mixtures of clean, near anechoic speech, not representative of many real-world scenarios.…

This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional…