相关论文: Foster Strengths and Circumvent Weaknesses: a Spee…

There are two approaches for pairwise sentence scoring: Cross-encoders, which perform full-attention over the input pair, and Bi-encoders, which map each input independently to a dense vector space. While cross-encoders often achieve higher…

Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the large parameter sizes and high computational complexity. By…

In recent years generative adversarial network (GAN) based models have been successfully applied for unsupervised speech-to-speech conversion.The rich compact harmonic view of the magnitude spectrogram is considered a suitable choice for…

Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…

Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation is equally important.…

This paper addresses the problem of multi-channel multi-speech separation based on deep learning techniques. In the short time Fourier transform domain, we propose an end-to-end narrow-band network that directly takes as input the…

In speech enhancement (SE), phase estimation is important for perceptual quality, so many methods take clean speech's complex short-time Fourier transform (STFT) spectrum or the complex ideal ratio mask (cIRM) as the learning target. To…

Sub-band models have achieved promising results due to their ability to model local patterns in the spectrogram. Some studies further improve the performance by fusing sub-band and full-band information. However, the structure for the…

We propose a novel framework for electrolaryngeal speech intelligibility enhancement through the use of robust linguistic encoders. Pretraining and fine-tuning approaches have proven to work well in this task, but in most cases, various…

Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performance. Motivated by that, we propose a dual-branch…

Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on…

When designing fully-convolutional neural network, there is a trade-off between receptive field size, number of parameters and spatial resolution of features in deeper layers of the network. In this work we present a novel network design…

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…

Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategies, exhibit…

In this contribution, we present a novel online approach to multichannel speech enhancement. The proposed method estimates the enhanced signal through a filter-and-sum framework. More specifically, complex-valued masks are estimated by a…

Speech foundation models trained with self-supervised learning produce generic speech representations that support a wide range of speech processing tasks. When further adapted with supervised learning, these models can achieve strong…

In the evolving wireless communications landscape, addressing the challenges of multipath fading and high mobility remains paramount. This paper introduces the Unified Sequency-Frequency Multiplexing (USFM) framework, a pioneering…

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…

Multi-channel speech separation in dynamic environments is challenging as time-varying spatial and spectral features evolve at different temporal scales. Existing methods typically employ sequential architectures, forcing a single network…

This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consideration. Specifically, we propose to use generative learning…