相关论文: PlumberNet: Fixing interference leakage after GEV …

The performance of speaker recognition system is highly dependent on the amount of speech used in enrollment and test. This work presents a detailed experimental review and analysis of the GMM-SVM based speaker recognition system in…

In this paper, we propose two mask-based beamforming methods using a deep neural network (DNN) trained by multichannel loss functions. Beamforming technique using time-frequency (TF)-masks estimated by a DNN have been applied to many…

This paper describes a versatile method that accelerates multichannel source separation methods based on full-rank spatial modeling. A popular approach to multichannel source separation is to integrate a spatial model with a source model…

This paper proposes attentive statistics pooling for deep speaker embedding in text-independent speaker verification. In conventional speaker embedding, frame-level features are averaged over all the frames of a single utterance to form an…

Recently proposed speech recognition systems are designed to predict using representations generated by their top layers, employing greedy decoding which isolates each timestep from the rest of the sequence. Aiming for improved performance,…

In this work, we propose a deep beamforming framework for speech enhancement in dynamic acoustic environments. The framework learns time-varying beamformer weights from noisy multichannel signals via a deep neural network, guided by a…

Speech enhancement has seen great improvement in recent years mainly through contributions in denoising, speaker separation, and dereverberation methods that mostly deal with environmental effects on vocal audio. To enhance speech beyond…

We consider the task of region-based source separation of reverberant multi-microphone recordings. We assume pre-defined spatial regions with a single active source per region. The objective is to estimate the signals from the individual…

When a speaker verification (SV) system operates far from the sound sourced, significant challenges arise due to the interference of noise and reverberation. Studies have shown that incorporating phonetic information into speaker embedding…

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

Generative modeling has recently achieved remarkable success across image, video, and audio domains, demonstrating powerful capabilities for unified representation learning. Yet speech front-end tasks such as speech enhancement (SE), target…

Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…

Language models (LM) have grown with non-stop in the last decade, from sequence-to-sequence architectures to the state-of-the-art and utter attention-based Transformers. In this work, we demonstrate how the inclusion of deep generative…

Since its inception, the field of deep speech enhancement has been dominated by predictive (discriminative) approaches, such as spectral mapping or masking. Recently, however, novel generative approaches have been applied to speech…

Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning. The former severely limits the…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Speech clarity and spatial audio immersion are the two most critical factors in enhancing remote conferencing experiences. Existing methods are often limited: either due to the lack of spatial information when using only one microphone, or…

Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM rewrites existing text while applying generation-time watermarking, to protect…

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…