Joo-Han Noh

Deep networks have been successfully applied to unsupervised feature learning for single modalities (e.g., text, images or audio). In this work, we propose a novel application of deep networks to learn features over multiple modalities. We present a series of tasks for multimodal learning and show how to train deep networks that learn features to address these tasks. In particular, we demonstrate cross modality feature learning, where better features for one modality (e.g., video) can be learned

Convolutional Neural Networks (CNN) have been applied to diverse machine learning tasks for different modalities of raw data in an end-to-end fashion. In the audio domain, a raw waveform-based approach has been explored to directly learn hierarchical characteristics of audio. However, the majority of previous studies have limited their model capacity by taking a frame-level structure similar to short-time Fourier transforms. We previously proposed a CNN architecture which learns representations

Over the last decade, music-streaming services have grown dramatically. Pandora, one company in the field, has pioneered and popularized streaming music by successfully deploying the Music Genome Project [1] (https://www.pandora.com/about/mgp) based on human-annotated content analysis. Another company, Spotify, has a catalog of over 40 million songs and over 180 million users as of mid-2018 (https://press.spotify.com/us/about/), making it a leading music service provider worldwide. Giant technol

Recently, the end-to-end approach that learns hierarchical representations from raw data using deep convolutional neural networks has been successfully explored in the image, text and speech domains. This approach was applied to musical signals as well but has been not fully explored yet. To this end, we propose sample-level deep convolutional neural networks which learn representations from very small grains of waveforms (e.g. 2 or 3 samples) beyond typical frame-level input representations. Ou

Recent work has shown that the end-to-end approach using convolutional neural network (CNN) is effective in various types of machine learning tasks. For audio signals, the approach takes raw waveforms as input using an 1-D convolution layer. In this paper, we improve the 1-D CNN architecture for music auto-tagging by adopting building blocks from state-of-the-art image classification models, ResNets and SENets, and adding multi-level feature aggregation to it. We compare different combinations o

End-to-end learning with convolutional neural networks (CNNs) has become a standard approach in image classification. However, in audio classification, CNN-based models that use time-frequency representations as input are still popular. A recently proposed CNN architecture called SampleCNN takes raw waveforms directly and has very small sizes of filters. The architecture has proven to be effective in music classification tasks. In this paper, we scrutinize SampleCNN further by comparing it with

Singing melody extraction essentially involves two tasks: one is detecting the activity of a singing voice in polyphonic music, and the other is estimating the pitch of a singing voice in the detected voiced segments. In this paper, we present a joint detection and classification (JDC) network that conducts the singing voice detection and the pitch estimation simultaneously. The JDC network is composed of the main network that predicts the pitch contours of the singing melody and an auxiliary ne

[TODO] Add abstract here.

[TODO] Add abstract here.

[TODO] Add abstract here.

Music similarity search is useful for a variety of creative tasks such as replacing one music recording with another recording with a similar "feel", a common task in video editing. For this task, it is typically necessary to define a similarity metric to compare one recording to another. Music similarity, however, is hard to define and depends on multiple simultaneous notions of similarity (i.e. genre, mood, instrument, tempo). While prior work ignore this issue, we embrace this idea and introd

Music, speech, and acoustic scene sound are often handled separately in the audio domain because of their different signal characteristics. However, as the image domain grows rapidly by versatile image classification models, it is necessary to study extensible classification models in the audio domain as well. In this study, we approach this problem using two types of sample-level deep convolutional neural networks that take raw waveforms as input and uses filters with small granularity. One is

The short-time Fourier transform (STFT) based spectrogram is commonly used to analyze the time-frequency content of a signal. Depending on window size, the STFT provides a trade-off between time and frequency resolutions. This paper presents a novel method that achieves high resolution simultaneously in both time and frequency. We extend Probabilistic Latent Component Analysis (PLCA) to jointly decompose two spectrograms, one with a high time resolution and one with a high frequency resolution.

One of the challenges in virtual analog synthesis is avoiding aliasing when generating classic waveforms such as sawtooth and square wave which have theoretically infinite bandwidth in their ideal forms. The human auditory system renders a certain amount of aliasing inaudible, which allows room for finding cost-effective algorithms. This paper suggests efficient algorithms to reduce the aliasing using low-order fractional delay filters in the framework of bandlimited impulse train (BLIT) synthes