479 citations · 827 across the 35 of their papers we have counts for
35 papers
Native Multi-Band Audio Coding within Hyper-Autoencoded Reconstruction Propagation Networks
Darius Petermann, Inseon Jang, Minje Kim
Spectral sub-bands do not portray the same perceptual relevance. In audio coding, it is therefore desirable to have independent control over each of the constituent bands so that b…
The Potential of Neural Speech Synthesis-based Data Augmentation for Personalized Speech Enhancement
Anastasia Kuznetsova, Aswin Sivaraman, Minje Kim
With the advances in deep learning, speech enhancement systems benefited from large neural network architectures and achieved state-of-the-art quality. However, speaker-agnostic me…
Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech Coding
Haici Yang, Wootaek Lim, Minje Kim
Low and ultra-low-bitrate neural speech coding achieves unprecedented coding gain by generating speech signals from compact speech features. This paper introduces additional coding…
Upmixing via style transfer: a variational autoencoder for disentangling spatial images and musical content
Haici Yang, Sanna Wager, Spencer Russell +3
In the stereo-to-multichannel upmixing problem for music, one of the main tasks is to set the directionality of the instrument sources in the multichannel rendering results. In thi…
SpaIn-Net: Spatially-Informed Stereophonic Music Source Separation
Darius Petermann, Minje Kim
With the recent advancements of data driven approaches using deep neural networks, music source separation has been formulated as an instrument-specific supervised problem. While e…
BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement
Sunwoo Kim, Minje Kim
In this paper, we present a blockwise optimization method for masking-based networks (BLOOM-Net) for training scalable speech enhancement networks. Here, we design our network with…
HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding
Darius Petermann, Seungkwon Beack, Minje Kim
An autoencoder-based codec employs quantization to turn its bottleneck layer activation into bitstrings, a process that hinders information flow between the encoder and decoder par…
Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization
Haici Yang, Shivani Firodiya, Nicholas J. Bryan +1
The task of manipulating the level and/or effects of individual instruments to recompose a mixture of recordings, or remixing, is common across a variety of applications such as mu…
Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation
Sunwoo Kim, Minje Kim
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…
Zero-Shot Personalized Speech Enhancement through Speaker-Informed Model Selection
Aswin Sivaraman, Minje Kim
This paper presents a novel zero-shot learning approach towards personalized speech enhancement through the use of a sparsely active ensemble model. Optimizing speech denoising sys…
Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification
Aswin Sivaraman, Sunwoo Kim, Minje Kim
Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If t…
Efficient Personalized Speech Enhancement through Self-Supervised Learning
Aswin Sivaraman, Minje Kim
This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly ad…
Scalable and Efficient Neural Speech Coding: A Hybrid Design
Kai Zhen, Jongmo Sung, Mi Suk Lee +2
We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neur…
Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
Kai Zhen, Mi Suk Lee, Jongmo Sung +2
Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded…
Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement
Aswin Sivaraman, Minje Kim
This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifical…
Source-Aware Neural Speech Coding for Noisy Speech Compression
Haici Yang, Kai Zhen, Seungkwon Beack +1
This paper introduces a novel neural network-based speech coding system that can process noisy speech effectively. The proposed source-aware neural audio coding (SANAC) system harm…
Sparse Mixture of Local Experts for Efficient Speech Enhancement
Aswin Sivaraman, Minje Kim
In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task i…
Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation
Sunwoo Kim, Haici Yang, Minje Kim
Speech enhancement tasks have seen significant improvements with the advance of deep learning technology, but with the cost of increased computational complexity. In this study, we…
Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization
Kai Zhen, Mi Suk Lee, Jongmo Sung +2
Scalability and efficiency are desired in neural speech codecs, which supports a wide range of bitrates for applications on various devices. We propose a collaborative quantization…
Deep Autotuner: a Pitch Correcting Network for Singing Performances
Sanna Wager, George Tzanetakis, Cheng-i Wang +1
We introduce a data-driven approach to automatic pitch correction of solo singing performances. The proposed approach predicts note-wise pitch shifts from the relationship between…
Nearest Neighbor Search-Based Bitwise Source Separation Using Discriminant Winner-Take-All Hashing
Sunwoo Kim, Minje Kim
We propose an iteration-free source separation algorithm based on Winner-Take-All (WTA) hash codes, which is a faster, yet accurate alternative to a complex machine learning model…
Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation
Sunwoo Kim, Mrinmoy Maity, Minje Kim
This paper proposes a Bitwise Gated Recurrent Unit (BGRU) network for the single-channel source separation task. Recurrent Neural Networks (RNN) require several sets of weights wit…
A Dual-Staged Context Aggregation Method Towards Efficient End-To-End Speech Enhancement
Kai Zhen, Mi Suk Lee, Minje Kim
In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask esti…
Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding
Kai Zhen, Jongmo Sung, Mi Suk Lee +2
Speech codecs learn compact representations of speech signals to facilitate data transmission. Many recent deep neural network (DNN) based end-to-end speech codecs achieve low bitr…