相关论文: Towards High-Quality and Efficient Speech Bandwidt…

Automatic Speaker Verification (ASV) technology has become commonplace in virtual assistants. However, its performance suffers when there is a mismatch between the train and test domains. Mixed bandwidth training, i.e., pooling training…

Audio bandwidth extension aims to expand the spectrum of narrow-band audio signals. Although this topic has been broadly studied during recent years, the particular problem of extending the bandwidth of historical music recordings remains…

Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not yet reached that of…

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

In this paper we propose a lightweight model for frequency bandwidth extension of speech signals, increasing the sampling frequency from 8kHz to 16kHz while restoring the high frequency content to a level almost indistinguishable from the…

In recent years, generative adversarial networks (GANs) have made significant progress in generating audio sequences. However, these models typically rely on bandwidth-limited mel-spectrograms, which constrain the resolution of generated…

Wake word (WW) spotting is challenging in far-field due to the complexities and variations in acoustic conditions and the environmental interference in signal transmission. A suite of carefully designed and optimized audio front-end (AFE)…

This paper presents a novel neural speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra. The proposed model is a cascade of a residual convolutional network and a parallel estimation…

The human brain contextually exploits heterogeneous sensory information to efficiently perform cognitive tasks including vision and hearing. For example, during the cocktail party situation, the human auditory cortex contextually integrates…

We introduce EffiFusion-GAN (Efficient Fusion Generative Adversarial Network), a lightweight yet powerful model for speech enhancement. The model integrates depthwise separable convolutions within a multi-scale block to capture diverse…

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…

Speech super-resolution/Bandwidth Extension (BWE) can improve downstream tasks like Automatic Speaker Verification (ASV). We introduce a simple novel technique called Self-FiLM to inject self-supervision into existing BWE models via…

We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work demonstrates that GANs can effectively…

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,…

It is promising to design a single model that can suppress various distortions and improve speech quality, i.e., universal speech enhancement (USE). Compared to supervised learning-based predictive methods, diffusion-based generative models…

This paper proposes SEFGAN, a Deep Neural Network (DNN) combining maximum likelihood training and Generative Adversarial Networks (GANs) for efficient speech enhancement (SE). For this, a DNN is trained to synthesize the enhanced speech…

Speech systems developed for a particular choice of acoustic domain and sampling frequency do not translate easily to others. The usual practice is to learn domain adaptation and bandwidth extension models independently. Contrary to this,…

Online Speech Enhancement was mainly reserved for predictive models. A key advantage of these models is that for an incoming signal frame from a stream of data, the model is called only once for enhancement. In contrast, generative Speech…

With the rapid development of neural networks in recent years, the ability of various networks to enhance the magnitude spectrum of noisy speech in the single-channel speech enhancement domain has become exceptionally outstanding. However,…

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…