相关论文: Decoupling and Interacting Multi-Task Learning Net…

A main challenge in applying deep learning to music processing is the availability of training data. One potential solution is Multi-task Learning, in which the model also learns to solve related auxiliary tasks on additional datasets to…

In recent years, a number of time-domain speech separation methods have been proposed. However, most of them are very sensitive to the environments and wide domain coverage tasks. In this paper, from the time-frequency domain perspective,…

We present an efficient speech separation neural network, ARFDCN, which combines dilated convolutions, multi-scale fusion (MSF), and channel attention to overcome the limited receptive field of convolution-based networks and the high…

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the…

Non-autoregressive (NAR) models have achieved a large inference computation reduction and comparable results with autoregressive (AR) models on various sequence to sequence tasks. However, there has been limited research aiming to explore…

Wireless signal recognition (WSR) is crucial in modern and future wireless communication networks since it aims to identify the properties of the received signal in a no-collaborative manner. However, it is challenging to accurately…

Siamese networks have shown effective results in unsupervised visual representation learning. These models are designed to learn an invariant representation of two augmentations for one input by maximizing their similarity. In this paper,…

Semantic segmentation is an essential part of deep learning. In recent years, with the development of remote sensing big data, semantic segmentation has been increasingly used in remote sensing. Deep convolutional neural networks (DCNNs)…

Despite the recent advancements in Automatic Speech Recognition (ASR), the recognition of accented speech still remains a dominant problem. In order to create more inclusive ASR systems, research has shown that the integration of accent…

We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable…

Citrinet is an end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. To capture local and global contextual information, 1D time-channel separable convolutions combined with…

The past decade has witnessed great progress in Automatic Speech Recognition (ASR) due to advances in deep learning. The improvements in performance can be attributed to both improved models and large-scale training data. Key to training…

To better model the contextual information and increase the generalization ability of Speech Activity Detection (SAD) system, this paper leverages a multi-lingual Automatic Speech Recognition (ASR) system to perform SAD. Sequence…

Connectionist temporal classification (CTC) provides an end-to-end acoustic model (AM) training strategy. CTC learns accurate AMs without time-aligned phonetic transcription, but sometimes fails to converge, especially in…

Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle…

Multi-task learning has recently emerged as a promising solution for a comprehensive understanding of complex scenes. In addition to being memory-efficient, multi-task models, when appropriately designed, can facilitate the exchange of…

Deep learning has emerged as a powerful alternative to hand-crafted methods for emotion recognition on combined acoustic and text modalities. Baseline systems model emotion information in text and acoustic modes independently using Deep…