相关论文: Should Audio Front-ends be Adaptive? Comparing Lea…

Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fundamental…

While much of modern speech and audio processing relies on deep neural networks trained using fixed audio representations, recent studies suggest great potential in acoustic frontends learnt jointly with a backend. In this study, we focus…

We propose a learnable content adaptive front end for audio signal processing. Before the modern advent of deep learning, we used fixed representation non-learnable front-ends like spectrogram or mel-spectrogram with/without neural…

Deep audio classification, traditionally cast as training a deep neural network on top of mel-filterbanks in a supervised fashion, has recently benefited from two independent lines of work. The first one explores "learnable frontends",…

In audio signal processing, learnable front-ends have shown strong performance across diverse tasks by optimizing task-specific representation. However, their parameters remain fixed once trained, lacking flexibility during inference and…

In audio classification, differentiable auditory filterbanks with few parameters cover the middle ground between hard-coded spectrograms and raw audio. LEAF (arXiv:2101.08596), a Gabor-based filterbank combined with Per-Channel Energy…

The purpose of this paper is to compare different learnable frontends in medical acoustics tasks. A framework has been implemented to classify human respiratory sounds and heartbeats in two categories, i.e. healthy or affected by…

Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV). This paper…

Autonomous recording units and passive acoustic monitoring present minimally intrusive methods of collecting bioacoustics data. Combining this data with species agnostic bird activity detection systems enables the monitoring of activity…

This paper presents a circuit-algorithm co-design framework for learnable analog front-end (AFE) in audio signal classification. Designing AFE and backend classifiers separately is a common practice but non-ideal, as shown in this paper.…

Recent years have witnessed a boom in self-supervised learning (SSL) in various areas including speech processing. Speech based SSL models present promising performance in a range of speech related tasks. However, the training of SSL models…

Deep learning has been applied to diverse audio semantics tasks, enabling the construction of models that learn hierarchical levels of features from high-dimensional raw data, delivering state-of-the-art performance. But do these algorithms…

Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain…

There is increasing interest in the use of the LEArnable Front-end (LEAF) in a variety of speech processing systems. However, there is a dearth of analyses of what is actually learnt and the relative importance of training the different…

While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing and make it…

Current speech recognition architectures perform very well from the point of view of machine learning, hence user interaction. This suggests that they are emulating the human biological system well. We investigate whether the inference can…

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often…

Voice assistants, such as smart speakers, have exploded in popularity. It is currently estimated that the smart speaker adoption rate has exceeded 35% in the US adult population. Manufacturers have integrated speaker identification…

State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we study end-to-end systems trained directly from the raw…

Source separation and other audio applications have traditionally relied on the use of short-time Fourier transforms as a front-end frequency domain representation step. The unavailability of a neural network equivalent to forward and…