Related papers: Improving Frame-Online Neural Speech Enhancement w…

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models. However, much of this work focuses on using the deepest or final…

We present a neural network for rendering binaural speech from given monaural audio, position, and orientation of the source. Most of the previous works have focused on synthesizing binaural speeches by conditioning the positions and…

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

Distant speech recognition is being revolutionized by deep learning, that has contributed to significantly outperform previous HMM-GMM systems. A key aspect behind the rapid rise and success of DNNs is their ability to better manage large…

The short-time Fourier transform (STFT) usually computes the same number of frequency components as the frame length while overlapping adjacent time frames by more than half. As a result, the number of components of a spectrogram matrix…

Online speech recognition is crucial for developing natural human-machine interfaces. This modality, however, is significantly more challenging than off-line ASR, since real-time/low-latency constraints inevitably hinder the use of future…

While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural…

We propose a method using a long short-term memory (LSTM) network to estimate the noise power spectral density (PSD) of single-channel audio signals represented in the short time Fourier transform (STFT) domain. An LSTM network common to…

Many audio signal processing methods are formulated in the time-frequency (T-F) domain which is obtained by the short-time Fourier transform (STFT). The properties of the STFT are fully characterized by window function, number of frequency…

Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer…

Simultaneous machine translation (SMT) takes streaming input utterances and incrementally produces target text. Existing SMT methods mainly use the partial utterance that has already arrived at the input and the generated hypothesis.…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…

Algorithms for processing data in short-time batches are critical for both online and offline processing of streamed and large data respectively due to the quadratic relation between signal length and computational cost of convolution-based…

Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…

The inverse short-time Fourier transform network (iSTFTNet) has garnered attention owing to its fast, lightweight, and high-fidelity speech synthesis. It obtains these characteristics using a fast and lightweight 1D CNN as the backbone and…

In this work, we extend our previously proposed offline SpatialNet for long-term streaming multichannel speech enhancement in both static and moving speaker scenarios. SpatialNet exploits spatial information, such as the spatial/steering…

This paper presents a gradient-based method for on-the-fly optimization for both per-frame and per-frequency window length of the short-time Fourier transform (STFT), related to previous work in which we developed a differentiable version…

Deep learning-based techniques for automatic dysarthric speech detection have recently attracted interest in the research community. State-of-the-art techniques typically learn neurotypical and dysarthric discriminative representations by…