相关论文: Multi-Stage Speech Bandwidth Extension with Flexib…

For the difficulty and large computational complexity of modeling more frequency bands, full-band speech enhancement based on deep neural networks is still challenging. Previous studies usually adopt compressed full-band speech features in…

This paper aims to synthesize the target speaker's speech with desired speaking style and emotion by transferring the style and emotion from reference speech recorded by other speakers. We address this challenging problem with a two-stage…

In this paper, we tackle the problem of handling narrowband and wideband speech by building a single acoustic model (AM), also called mixed bandwidth AM. In the proposed approach, an auxiliary input feature is used to provide the bandwidth…

Recently, diffusion-based generative models have demonstrated remarkable performance in speech enhancement tasks. However, these methods still encounter challenges, including the lack of structural information and poor performance in low…

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement…

This paper proposes a speech enhancement method which exploits the high potential of residual connections in a Wide Residual Network architecture. This is supported on single dimensional convolutions computed alongside the time domain,…

Most of the current speech data augmentation methods operate on either the raw waveform or the amplitude spectrum of speech. In this paper, we propose a novel speech data augmentation method called PhasePerturbation that operates…

In networks, there are often more than one source of capacity. The capacities can be permanently or temporarily owned by the decision maker. Depending on the nature of sources, we identify the permanent capacity, spot market capacity and…

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of…

Speech self-supervised learning (SSL) has made great progress in various speech processing tasks, but there is still room for improvement in speech enhancement (SE). This paper presents BSP-MPNet, a dual-path framework that combines…

Speech bandwidth expansion is crucial for expanding the frequency range of low-bandwidth speech signals, thereby improving audio quality, clarity and perceptibility in digital applications. Its applications span telephony, compression,…

We propose a multi-stage framework for universal speech enhancement, designed for the Interspeech 2025 URGENT Challenge. Our system first employs a Sparse Compression Network to robustly separate sources and extract an initial clean speech…

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

Large-scale mobile communication systems tend to contain legacy transmission channels with narrowband bottlenecks, resulting in characteristic "telephone-quality" audio. While higher quality codecs exist, due to the scale and heterogeneity…

Speech enhancement (SE) based on diffusion probabilistic models has exhibited impressive performance, while requiring a relatively high number of function evaluations (NFE). Recently, SE based on flow matching has been proposed, which…

Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function…

Audio bandwidth extension involves the realistic reconstruction of high-frequency spectra from bandlimited observations. In cases where the lowpass degradation is unknown, such as in restoring historical audio recordings, this becomes a…

To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the…

Multilingual Word Embeddings (MWEs) represent words from multiple languages in a single distributional vector space. Unsupervised MWE (UMWE) methods acquire multilingual embeddings without cross-lingual supervision, which is a significant…

The direct expansion of deep neural network (DNN) based wide-band speech enhancement (SE) to full-band processing faces the challenge of low frequency resolution in low frequency range, which would highly likely lead to deteriorated…