Related papers: Deep Autotuner: a Pitch Correcting Network for Sin…

Neural network quantization is frequently used to optimize model size, latency and power consumption for on-device deployment of neural networks. In many cases, a target bit-width is set for an entire network, meaning every layer get…

Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view…

Previous approaches in singer identification have used one of monophonic vocal tracks or mixed tracks containing multiple instruments, leaving a semantic gap between these two domains of audio. In this paper, we present a system to learn a…

Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case sensitivity. Such conservative calibration often results in performance degradation,…

We propose self-teaching networks to improve the generalization capacity of deep neural networks. The idea is to generate soft supervision labels using the output layer for training the lower layers of the network. During the network…

Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audio models to annotate and parse the birdsong. Developing such models requires precise,…

This paper discusses real-time alignment of audio signals of music performance to the corresponding score (a.k.a. score following) which can handle tempo changes, errors and arbitrary repeats and/or skips (repeats/skips) in performances.…

This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge\cite{Yi2022ADD}. The very same system was used for both two rounds of evaluation in Track 3.2 with a similar training…

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

We introduce the concept of self-tuned criticality as a general mechanism for signal detection in sensory systems. In the case of hearing, we argue that active amplification of faint sounds is provided by a dynamical system which is…

We present an end-to-end system for musical key estimation, based on a convolutional neural network. The proposed system not only out-performs existing key estimation methods proposed in the academic literature; it is also capable of…

Building a high-quality singing corpus for a person who is not good at singing is non-trivial, thus making it challenging to create a singing voice synthesizer for this person. Learn2Sing is dedicated to synthesizing the singing voice of a…

Personalized speech intelligibility prediction is challenging. Previous approaches have mainly relied on audiograms, which are inherently limited in accuracy as they only capture a listener's hearing threshold for pure tones. Rather than…

We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the…

In realistic speech enhancement settings for end-user devices, we often encounter only a few speakers and noise types that tend to reoccur in the specific acoustic environment. We propose a novel personalized speech enhancement method to…

The single-speaker singing voice synthesis (SVS) usually underperforms at pitch values that are out of the singer's vocal range or associated with limited training samples. Based on our previous work, this work proposes a…

The present paper describes singing voice synthesis based on convolutional neural networks (CNNs). Singing voice synthesis systems based on deep neural networks (DNNs) are currently being proposed and are improving the naturalness of…

We present in this paper PerformacnceNet, a neural network model we proposed recently to achieve score-to-audio music generation. The model learns to convert a music piece from the symbolic domain to the audio domain, assigning…

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability…

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…