相关论文: TFCN: Temporal-Frequential Convolutional Network f…

Ensuring intelligible speech communication for hearing assistive devices in low-latency scenarios presents significant challenges in terms of speech enhancement, coding and transmission. In this paper, we propose novel solutions for…

With recent research advancements, deep learning models are becoming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models can achieve outstanding results in terms of speech quality…

Speaker recognition using i-vector has been replaced by speaker recognition using deep learning. Speaker recognition based on Convolutional Neural Networks (CNNs) has been widely used in recent years, which learn low-level speech…

In this paper, various structures and methods of Deep Artificial Neural Networks (DNN) will be evaluated and compared for the purpose of continuous Persian speech recognition. One of the first models of neural networks used in speech…

Today, Time Delay Neural Network (TDNN) has become the mainstream architecture for speaker verification task, in which the ECAPA-TDNN is one of the state-of-the-art models. The current works that focus on improving TDNN primarily address…

Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…

This paper proposes a tree-based convolutional neural network (TBCNN) for discriminative sentence modeling. Our models leverage either constituency trees or dependency trees of sentences. The tree-based convolution process extracts…

Recent speech enhancement methods based on convolutional neural networks (CNNs) and transformer have been demonstrated to efficaciously capture time-frequency (T-F) information on spectrogram. However, the correlation of each channels of…

This paper describes the IDLab submission for the text-independent task of the Short-duration Speaker Verification Challenge 2021 (SdSVC-21). This speaker verification competition focuses on short duration test recordings and cross-lingual…

This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the…

Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial…

Sequence prediction and classification are ubiquitous and challenging problems in machine learning that can require identifying complex dependencies between temporally distant inputs. Recurrent Neural Networks (RNNs) have the ability, in…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…

Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing…

In this work, we propose Tiny-CRNN (Tiny Convolutional Recurrent Neural Network) models applied to the problem of wakeword detection, and augment them with scaled dot product attention. We find that, compared to Convolutional Neural Network…

We present TVF (Time-Varying Filtering), a low-latency speech enhancement model with 1 million parameters. Combining the interpretability of Digital Signal Processing (DSP) with the adaptability of deep learning, TVF bridges the gap between…

Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation. However, a typical FCN usually requires lots of floating point computation and large run-time memory,…

We propose a generalized convolutional neural network (CNN) architecture that first decomposes the input signal into subbands by an adaptive filter bank structure, and then uses convolutional layers to extract features from each subband…

This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw…