相关论文: Towards Listening to 10 People Simultaneously: An …

New hardware can substantially increase the speed and efficiency of deep neural network training. To guide the development of future hardware architectures, it is pertinent to explore the hardware and machine learning properties of…

This paper investigates a non-negative matrix factorization (NMF)-based approach to the semi-supervised single-channel speech enhancement problem where only non-stationary additive noise signals are given. The proposed method relies on…

Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem. In this study, we provide a family of efficient neural network…

We present a single deep learning architecture that can both separate an audio recording of a musical mixture into constituent single-instrument recordings and transcribe these instruments into a human-readable format at the same time,…

We propose an end-to-end trainable approach to single-channel speech separation with unknown number of speakers. Our approach extends the MulCat source separation backbone with additional output heads: a count-head to infer the number of…

In recent years time domain speech separation has excelled over frequency domain separation in single channel scenarios and noise-free environments. In this paper we dissect the gains of the time-domain audio separation network (TasNet)…

Most of the current deep learning-based approaches for speech enhancement only operate in the spectrogram or waveform domain. Although a cross-domain transformer combining waveform- and spectrogram-domain inputs has been proposed, its…

Non-negative Matrix Factorization (NMF) has already been applied to learn speaker characterizations from single or non-simultaneous speech for speaker recognition applications. It is also known for its good performance in (blind) source…

Objective assessment of audio source-separation systems still mismatches subjective human perception, especially when interference from competing talkers and distortion of the target signal interact. We introduce Perceptual Separation (PS)…

Mutation analysis can provide valuable insights into both System Under Test (SUT) and its test suite. However, it is not scalable due to the cost of building and testing a large number of mutants. Predictive Mutation Testing (PMT) has been…

The current dominant approach for neural speech enhancement is based on supervised learning by using simulated training data. The trained models, however, often exhibit limited generalizability to real-recorded data. To address this, this…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Machine learning has achieved impressive performance in tomographic reconstruction, but supervised training requires paired measurements and ground-truth images that are often unavailable. This has motivated self-supervised approaches,…

As parallel training data is scarce for one-shot voice conversion (VC) tasks, waveform reconstruction is typically performed by various VC systems. A typical one-shot VC system comprises a content encoder and a speaker encoder. However, two…

Correctly estimating the discrepancy between two data distributions has always been an important task in Machine Learning. Recently, Cuturi proposed the Sinkhorn distance which makes use of an approximate Optimal Transport cost between two…

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In…

Audio source separation is a difficult machine learning problem and performance is measured by comparing extracted signals with the component source signals. However, if separation is motivated by the ultimate goal of re-mixing then…

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

Spiking Neural Networks (SNNs) often suffer from high time complexity $O(T)$ due to the sequential processing of $T$ spikes, making training computationally expensive. In this paper, we propose a novel Fixed-point Parallel Training (FPT)…

When training neural networks with custom objectives, such as ranking losses and shortest-path losses, a common problem is that they are, per se, non-differentiable. A popular approach is to continuously relax the objectives to provide…