Related papers: Deep factorization for speech signal

Speaker diarization is a task to label an audio or video recording with the identity of the speaker at each given time stamp. In this work, we propose a novel machine learning framework to conduct real-time multi-speaker diarization and…

Speaker diarization is a task to label audio or video recordings with classes that correspond to speaker identity, or in short, a task to identify "who spoke when". In the early years, speaker diarization algorithms were developed for…

Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal…

In response to the rapid growth of Internet of Things (IoT) devices and rising security risks, Radio Frequency Fingerprint (RFF) has become key for device identification and authentication. However, various changing factors - beyond the RFF…

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…

Fast Fourier convolution (FFC) is the recently proposed neural operator showing promising performance in several computer vision problems. The FFC operator allows employing large receptive field operations within early layers of the neural…

Speech deepfake detection (DFD) has benefited from diverse acoustic and semantic speech representations, many of which encode valuable speech information and are costly to train. Existing approaches typically enhance DFD by tuning the…

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution…

Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the…

Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. CRF models the conditional probability of the…

Algorithmic latency in speech processing is dominated by the frame length used for Fourier analysis, which in turn limits the achievable performance of magnitude-centric approaches. As previous studies suggest the importance of phase grows…

This paper proposes a novel approach that uses deep neural networks for classifying imagined speech, significantly increasing the classification accuracy. The proposed approach employs only the EEG channels over specific areas of the brain…

Transformer has obtained promising results on cognitive speech signal processing field, which is of interest in various applications ranging from emotion to neurocognitive disorder analysis. However, most works treat speech signal as a…

Speech emotion recognition is a crucial problem manifesting in a multitude of applications such as human computer interaction and education. Although several advancements have been made in the recent years, especially with the advent of…

Many problems in real-world applications involve predicting several random variables which are statistically related. Markov random fields (MRFs) are a great mathematical tool to encode such relationships. The goal of this paper is to…

In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features…

We present a factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision. Specifically, we exploit the multi-scale nature of information in sequential…

Deep learning is still not a very common tool in speaker verification field. We study deep convolutional neural network performance in the text-prompted speaker verification task. The prompted passphrase is segmented into word states - i.e.…

In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for…

Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, na\"ive context extension imposes significant computational and memory burdens, often resulting in inefficiencies…