相关论文: ARiSE: Auto-Regressive Multi-Channel Speech Enhanc…

We propose a computational model of speech production combining a pre-trained neural articulatory synthesizer able to reproduce complex speech stimuli from a limited set of interpretable articulatory parameters, a DNN-based internal forward…

Automatic speech recognition (ASR) is a capability which enables a program to process human speech into a written form. Recent developments in artificial intelligence (AI) have led to high-accuracy ASR systems based on deep neural networks,…

In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…

Reverberation, which is generally caused by sound reflections from walls, ceilings, and floors, can result in severe performance degradation of acoustic applications. Due to a complicated combination of attenuation and time-delay effects,…

Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR by replacing the matrix inversion…

In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are…

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,…

Channel estimation is one of the main tasks in realizing practical intelligent reflecting surface-assisted multi-user communication (IRS-MC) systems. However, different from traditional communication systems, an IRS-MC system generally…

We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the patch level. Unlike prior methods that perform a single,…

Today, the optimal performance of existing noise-suppression algorithms, both data-driven and those based on classic statistical methods, is range bound to specific levels of instantaneous input signal-to-noise ratios. In this paper, we…

With the surge of online meetings, it has become more critical than ever to provide high-quality speech audio and live captioning under various noise conditions. However, most monaural speech enhancement (SE) models introduce processing…

This work introduces the Cleanformer, a streaming multichannel neural based enhancement frontend for automatic speech recognition (ASR). This model has a conformer-based architecture which takes as inputs a single channel each of raw and…

Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-linear distortions from regression-based objectives,…

End-to-end (E2E) automatic speech recognition (ASR) methods exhibit remarkable performance. However, since the performance of such methods is intrinsically linked to the context present in the training data, E2E-ASR methods do not perform…

Mix-based augmentation has been proven fundamental to the generalization of deep vision models. However, current augmentations only mix samples at the current data batch during training, which ignores the possible knowledge accumulated in…

This study addresses the speech enhancement (SE) task within the causal inference paradigm by modeling the noise presence as an intervention. Based on the potential outcome framework, the proposed causal inference-based speech enhancement…

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…

Masked diffusion models (MDMs) have emerged as a promising approach for language modeling, yet they face a performance gap compared to autoregressive models (ARMs) and require more training iterations. In this work, we present the…

Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial…

Recently, variational autoencoder (VAE), a deep representation learning (DRL) model, has been used to perform speech enhancement (SE). However, to the best of our knowledge, current VAE-based SE methods only apply VAE to the model speech…