Juhan Nam

• PhD
• Professor (Associate) at Korea Advanced Institute of Science and Technology

Although being widely adopted for evaluating generated audio signals, the Fr\'echet Audio Distance (FAD) suffers from significant limitations, including reliance on Gaussian assumptions, sensitivity to sample size, and high computational complexity. As an alternative, we introduce the Kernel Audio Distance (KAD), a novel, distribution-free, unbiase...

We present TalkPlay, a multimodal music recommendation system that reformulates the recommendation task as large language model token generation. TalkPlay represents music through an expanded token vocabulary that encodes multiple modalities - audio, lyrics, metadata, semantic tags, and playlist co-occurrence. Using these rich representations, the...

CLaMP 3 is a unified framework developed to address challenges of cross-modal and cross-lingual generalization in music information retrieval. Using contrastive learning, it aligns all major music modalities--including sheet music, performance signals, and audio recordings--with multilingual text in a shared representation space, enabling retrieval...

Versatile audio super-resolution (SR) is the challenging task of restoring high-frequency components from low-resolution audio with sampling rates between 4kHz and 32kHz in various domains such as music, speech, and sound effects. Previous diffusion-based SR methods suffer from slow inference due to the need for a large number of sampling steps. In...

Diffusion models have been widely used in the generative domain due to their convincing performance in modeling complex data distributions. Moreover, they have shown competitive results on discriminative tasks, such as image segmentation. While diffusion models have also been explored for automatic music transcription, their performance has yet to...

Intent classification is a text understanding task that identifies user needs from input text queries. While intent classification has been extensively studied in various domains, it has not received much attention in the music domain. In this paper, we investigate intent classification models for music discovery conversation, focusing on pre-train...

A conversational music retrieval system can help users discover music that matches their preferences through dialogue. To achieve this, a conversational music retrieval system should seamlessly engage in multi-turn conversation by 1) understanding user queries and 2) responding with natural language and retrieved music. A straightforward solution w...

Text-to-Music Retrieval, finding music based on a given natural language query, plays a pivotal role in content discovery within extensive music databases. To address this challenge, prior research has predominantly focused on a joint embedding of music audio and text, utilizing it to retrieve music tracks that exactly match descriptive queries rel...

Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video both temporally and semantically. Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges. Systems lacking explicit temporal features suffer from poor controllability...

Deep learning models have seen widespread use in modelling LFO-driven audio effects, such as phaser and flanger. Although existing neural architectures exhibit high-quality emulation of individual effects, they do not possess the capability to manipulate the output via control parameters. To address this issue, we introduce Controllable Neural Fram...

The purpose of this research is to present a natural language processing-based approach to symbolic music analysis. We propose Mel2Word, a text-based representation including pitch and rhythm information, and a new natural language processing-based melody segmentation algorithm. We first show how to create a melody dictionary using Byte Pair Encodi...

In recent years, advancements in neural network designs and the availability of large-scale labeled datasets have led to significant improvements in the accuracy of piano transcription models. However, most previous work focused on high-performance offline transcription, neglecting deliberate consideration of model size. The goal of this work is to...

Lyric translation plays a pivotal role in amplifying the global resonance of music, bridging cultural divides, and fostering universal connections. Translating lyrics, unlike conventional translation tasks, requires a delicate balance between singability and semantics. In this paper, we present a computational framework for the quantitative evaluat...

This paper utilizes natural language processing (NLP) techniques to investigate the language of jazz and enhance our understanding of jazz solo improvisation. The study focuses on applying the Byte-Pair Encoding (BPE) algorithm to tokenize jazz melodies and analyze the patterns and language associated with different aspects of jazz, including artis...

Music is characterized by complex hierarchical structures. Developing a comprehensive model to capture these structures has been a significant challenge in the field of Music Information Retrieval (MIR). Prior research has mainly focused on addressing individual tasks for specific hierarchical levels, rather than providing a unified approach. In th...

Automatic music captioning, which generates natural language descriptions for given music tracks, holds significant potential for enhancing the understanding and organization of large volumes of musical data. Despite its importance, researchers face challenges due to the costly and time-consuming collection process of existing music-language datase...

Professional vocalists modulate their voice timbre or pitch to make their vocal performance more expressive. Such fluctuations are called singing techniques. Automatic detection of singing techniques from audio tracks can be beneficial to understand how each singer expresses the performance, yet it can also be difficult due to the wide variety of t...

While piano music transcription models have shown high performance for solo piano recordings, their performance degrades when applied to ensemble recordings. This study aims to analyze the impact of different data augmentation methods on piano transcription performance, specifically focusing on mixing techniques applied to violin-piano ensembles. W...

Note-level automatic music transcription is one of the most representative music information retrieval (MIR) tasks and has been studied for various instruments to understand music. However, due to the lack of high-quality labeled data, transcription of many instruments is still a challenging task. In particular, in the case of singing, it is diffic...

We introduce a framework that recommends music based on the emotions of speech. In content creation and daily life, speech contains information about human emotions, which can be enhanced by music. Our framework focuses on a cross-domain retrieval system to bridge the gap between speech and music via emotion labels. We explore different speech repr...

Automatically generating or captioning music playlist titles given a set of tracks is of significant interest in music streaming services as customized playlists are widely used in personalized music recommendation, and well-composed text titles attract users and help their music discovery. We present an encoder-decoder model that generates a playl...

Singing voice separation (SVS) is a task that separates singing voice audio from its mixture with instrumental audio. Previous SVS studies have mainly employed the spectrogram masking method which requires a large dimensionality in predicting the binary masks. In addition, they focused on extracting a vocal stem that retains the wet sound with the...

This paper introduces effective design choices for text-to-music retrieval systems. An ideal text-based retrieval system would support various input queries such as pre-defined tags, unseen tags, and sentence-level descriptions. In reality, most previous works mainly focused on a single query type (tag or sentence) which may not generalize to anoth...

Existing multi-instrumental datasets tend to be biased toward pop and classical music. In addition, they generally lack high-level annotations such as emotion tags. In this paper, we propose YM2413-MDB, an 80s FM video game music dataset with multi-label emotion annotations. It includes 669 audio and MIDI files of music from Sega and MSX PC games i...

Wake-up words (WUW) is a short sentence used to activate a speech recognition system to receive the user's speech input. WUW utterances include not only the lexical information for waking up the system but also non-lexical information such as speaker identity or emotion. In particular, recognizing the user's emotional state may elaborate the voice...

A growing number of VR games are published in the market as head-mounted devices (HMD) become more widespread. However, most VR games are targeted for a single-player audience, and cross-platform VR experiences where multiple players are engaged have yet to be fully explored. In this paper, we propose a VR-mobile cross-platform game based on tradit...

In this paper, we focus on singing techniques within the scope of music information retrieval research. We investigate how singers use singing techniques using real-world recordings of famous solo singers in Japanese popular music songs (J-POP). First, we built a new dataset of singing techniques. The dataset consists of 168 commercial J-POP songs,...

In this paper, we focus on singing techniques within the scope of music information retrieval research. We investigate how singers use singing techniques using real-world recordings of famous solo singers in Japanese popular music songs (J-POP). First, we built a new dataset of singing techniques. The dataset consists of 168 commercial J-POP songs,...

Singing techniques are used for expressive vocal performances by employing temporal fluctuations of the timbre, the pitch, and other components of the voice. Their classification is a challenging task, because of mainly two factors: 1) the fluctuations in singing techniques have a wide variety and are affected by many factors and 2) existing datase...

Lack of large-scale note-level labeled data is the major obstacle to singing transcription from polyphonic music. We address the issue by using pseudo labels from vocal pitch estimation models given unlabeled data. The proposed method first converts the frame-level pseudo labels to note-level through pitch and rhythm quantization steps. Then, it fu...

Recent studies in singing voice synthesis have achieved high-quality results leveraging advances in text-to-speech models based on deep neural networks. One of the main issues in training singing voice synthesis models is that they require melody and lyric labels to be temporally aligned with audio data. The temporal alignment is a time-exhausting...

We propose a machine-translation approach to automatically generate a playlist title from a set of music tracks. We take a sequence of track IDs as input and a sequence of words in a playlist title as output, adapting the sequence-to-sequence framework based on Recurrent Neural Network (RNN) and Transformer to the music data. Considering the orderl...

While there are many music datasets with emotion labels in the literature, they cannot be used for research on symbolic-domain music analysis or generation, as there are usually audio files only. In this paper, we present the EMOPIA (pronounced `yee-m\`{o}-pi-uh') dataset, a shared multi-modal (audio and MIDI) database focusing on perceived emotion...

Creating a good drum track to imitate a skilled performer in digital audio workstations (DAWs) can be a time-consuming process, especially for those unfamiliar with drums. In this work, we introduce PocketVAE, a groove generation system that applies grooves to users' rudimentary MIDI tracks, i.e, templates. Grooves can be either transferred from a...

Quantitative evaluation of piano performance is of interests in many fields, including music education and computational performance rendering. Previous studies utilized features extracted from audio or musical instrument digital interface (MIDI) files but did not address the difference between hands (DBH), which might be an important aspect of hig...

The recent introduction of Deep Learning has led to a vast array of breakthroughs in many fields of science and engineering [...]

Recent advances in the quantitative, computational methodology for the modeling and analysis of heterogeneous large-scale data are leading to new opportunities for understanding human behaviors and faculties, including creativity that drives creative enterprises such as science. While innovation is crucial for novel and influential achievements, qu...

Recent advances in polyphonic piano transcription have been made primarily by a deliberate design of neural network architectures that detect different note states such as onset or sustain and model the temporal evolution of the states. The majority of them, however, use separate neural networks for each note state, thereby optimizing multiple loss...

A DJ mix is a sequence of music tracks concatenated seamlessly, typically rendered for audiences in a live setting by a DJ on stage. As a DJ mix is produced in a studio or the live version is recorded for music streaming services, computational methods to analyze DJ mixes, for example, extracting track information or understanding DJ techniques, ha...

The lack of labeled data is a major obstacle in many music information retrieval tasks such as melody extraction, where labeling is extremely laborious or costly. Semi-supervised learning (SSL) provides a solution to alleviate the issue by leveraging a large amount of unlabeled data. In this paper, we propose an SSL method using teacher-student mod...

Deep representation learning offers a powerful paradigm for mapping input data onto an organized embedding space and is useful for many music information retrieval tasks. Two central methods for representation learning include deep metric learning and classification, both having the same goal of learning a representation that can generalize well ac...

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...

Word embedding pioneered by Mikolov et al. is a staple technique for word representations in natural language processing (NLP) research which has also found popularity in music information retrieval tasks. Depending on the type of text data for word embedding, however, vocabulary size and the degree of musical pertinence can significantly vary. In...

Singing voice is a key sound source in popular music. As recent music streaming and entertainment services call for more intelligent solutions to retrieve songs or evaluate musical characteristics, automatic analysis of popular music targeted to singing voice has been a significant research subject. The majority of studies have focused on quantitat...

Symbolic melodic similarity is based on measuring a pair-wise distance between two songs from diverse perspectives. The distance is usually summarized as a single value for song retrieval. This obscures observing the details of similarity patterns within the two songs. In this paper, we propose a cross-scape plot representation to visualize multi-s...

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 joint embedding space of monophonic and mixed tracks for singing voice. We use a metric learning method, which...

While end-to-end learning has become a trend in deep learning, the model architecture is often designed to incorporate domain knowledge. We propose a novel convolutional recurrent neural network (CRNN) architecture with temporal feedback connections, inspired by the feedback pathways from the brain to ears in the human auditory system. The proposed...

Audio-based music classification and tagging is typically based on categorical supervised learning with a fixed set of labels. This intrinsically cannot handle unseen labels such as newly added music genres or semantic words that users arbitrarily choose for music retrieval. Zero-shot learning can address this problem by leveraging an additional se...

Supervised music representation learning has been performed mainly using semantic labels such as music genres. However, annotating music with semantic labels requires time and cost. In this work, we investigate the use of factual metadata such as artist, album, and track information, which are naturally annotated to songs, for supervised music repr...

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 joint embedding space of monophonic and mixed tracks for singing voice. We use a metric learning method, which...

Music classification and tagging is conducted through categorical supervised learning with a fixed set of labels. In principle, this cannot make predictions on unseen labels. Zero-shot learning is an approach to solve the problem by using side information about the semantic labels. We recently investigated this concept of zero-shot learning in musi...

Recent advances in the quantitative, computational methodology for the modeling and analysis of heterogeneous large-scale data are leading to new opportunities for understanding of human behaviors and faculties, including the manifestation of creativity that drives creative enterprises such as science. While innovation is crucial for novel and infl...

The papers in this special section focus on audio signal processing which is currently undergoing a paradigm change, where data-driven machine learning is replacing hand-crafted feature design. These papers aim to promote progress, systematization, understanding, and convergence of applying machine learning in the area of audio signal processing. S...

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 fi...

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...

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 song...

Artist recognition is a task of modeling the artist's musical style. This problem is challenging because there is no clear standard. We propose a hybrid method of the generative model i-vector and the discriminative model deep convolutional neural network. We show that this approach achieves state-of-the-art performance by complementing each other....

Recently deep learning based recommendation systems have been actively explored to solve the cold-start problem using a hybrid approach. However, the majority of previous studies proposed a hybrid model where collaborative filtering and content-based filtering modules are independently trained. The end-to-end approach that takes different modality...

Since the vocal component plays a crucial role in popular music, singing voice detection has been an active research topic in music information retrieval. Although several proposed algorithms have shown high performances, we argue that there still is a room to improve to build a more robust singing voice detection system. In order to identify the a...

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 capaci...

The musical possibilities of force sensors on touchscreen devices are explored, using Apple’s 3D Touch. Three functions are selected to be controlled by force: (a) excitation, (b) modification (aftertouch), and (c) mode change. Excitation starts a note, modification alters a playing note, and mode change controls binary on/off sound parameters. Fou...

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 proble...

We propose a framework for audio-to-score alignment on piano performance that employs automatic music transcription (AMT) using neural networks. Even though the AMT result may contain some errors, the note prediction output can be regarded as a learned feature representation that is directly comparable to MIDI note or chroma representation. To this...

Singing melody extraction is the task that identifies the melody pitch contour of singing voice from polyphonic music. Most of the traditional melody extraction algorithms are based on calculating salient pitch candidates or separating the melody source from the mixture. Recently, classification-based approach based on deep learning has drawn much...

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 s...

We demonstrate a fully automated system that generates DJ mixes from an arbitrary pool of audio tracks. Our goal is to offer a framework which automatically provides a high-quality endless mix of musical tracks without user supervision , given a seed track. To achieve this, we follow a filter and rank-based approach which selects the best-matching...

Recently, feature representation by learning algorithms has drawn great attention. In the music domain, it is either unsupervised or supervised by semantic labels such as music genre. However, finding discriminative features in an unsupervised way is challenging, and supervised feature learning using semantic labels may involve noisy or expensive a...

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 neur...

We propose a framework for audio-to-score alignment on piano performance that employs automatic music transcription (AMT) using neural networks. Even though the AMT result may contain some errors, the note prediction output can be regarded as a learned feature representation that is directly comparable to MIDI note or chroma representation. To this...

While dynamics is an important characteristic in music performance, it has been rarely researched in automatic music transcription. We propose a method to estimate individual note intensities from a piano recording given pre-aligned score data of the recording. To this end, we use non-negative matrix factorization in a score-informed framework, whe...