Related papers: HiFi++: a Unified Framework for Bandwidth Extensio…
Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on a single type of distortion, such as speech denoising or dereverberation. However, speech signals can be degraded by several different…
In recent years, large language models (LLM) have made significant progress in the task of generation error correction (GER) for automatic speech recognition (ASR) post-processing. However, in complex noisy environments, they still face…
The performance of speaker verification (SV) models may drop dramatically in noisy environments. A speech enhancement (SE) module can be used as a front-end strategy. However, existing SE methods may fail to bring performance improvements…
Advancing defensive mechanisms against adversarial attacks in generative models is a critical research topic in machine learning. Our study focuses on a specific type of generative models - Variational Auto-Encoders (VAEs). Contrary to…
We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…
Recent advancements in large language models have demonstrated that extended inference through techniques can markedly improve performance, yet these gains come with increased computational costs and the propagation of inherent biases found…
In real acoustic environment, speech enhancement is an arduous task to improve the quality and intelligibility of speech interfered by background noise and reverberation. Over the past years, deep learning has shown great potential on…
Background noise is a well-known factor that deteriorates the accuracy and reliability of speaker verification (SV) systems by blurring speech intelligibility. Various studies have used separate pretrained enhancement models as the…
Several of the latest GAN-based vocoders show remarkable achievements, outperforming autoregressive and flow-based competitors in both qualitative and quantitative measures while synthesizing orders of magnitude faster. In this work, we…
A person tends to generate dynamic attention towards speech under complicated environments. Based on this phenomenon, we propose a framework combining dynamic attention and recursive learning together for monaural speech enhancement. Apart…
Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time…
High-quality speech corpora are essential foundations for most speech applications. However, such speech data are expensive and limited since they are collected in professional recording environments. In this work, we propose an…
Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically motivated speech perception metrics as part of model training…
Nowadays more and more applications can benefit from edge-based text-to-speech (TTS). However, most existing TTS models are too computationally expensive and are not flexible enough to be deployed on the diverse variety of edge devices with…
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…
Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when generalising to…
Signal-dependent beamformers are advantageous over signal-independent beamformers when the acoustic scenario - be it real-world or simulated - is straightforward in terms of the number of sound sources, the ambient sound field and their…
In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task into non-overlapping subproblems and introducing a…
Music generation models can produce high-fidelity coherent accompaniment given complete audio input, but are limited to editing and loop-based workflows. We study real-time audio-to-audio accompaniment: as a model hears an input audio…
Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While…