Sungwon Kim

Sungwon Kim, Juho Song, Seungmin Shin et al.

Deep learning surrogates for 3D Partial Differential Equations (PDEs) often fail to generalize across geometric transformations because they depend heavily on specific coordinate systems. While equivariant networks offer a solution, they typically rely on local operations in the spatial domain, making the global receptive field, which is essential for PDE dynamics, computationally expensive. Conversely, Fourier Neural Operators (FNOs) efficiently capture global interactions, yet establishing 3D equivariance within them remains impractical due to the prohibitive cost of spectral group convolutions. To bridge this gap, we introduce EqGINO, a geometrically robust framework that enforces isotropy in the spectral domain. By design, EqGINO guarantees exact equivariance to the discrete symmetries inherent to the discretized computational domain. Beyond this discrete guarantee, our structural prior enables effective generalization to arbitrary continuous orientations even with a limited number of SE(3)-transformed training samples. Consequently, our method robustly models coordinate-invariant physical laws on complex irregular 3D geometries. Our code is available at https://github.com/sung-won-kim/EqGINO

Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar et al.

We present Audio Flamingo Next (AF-Next), the next-generation and most capable large audio-language model in the Audio Flamingo series, designed to advance understanding and reasoning over speech, environmental sounds and music. Compared to Audio Flamingo 3, AF-Next introduces: (i) a stronger foundational audio-language model that significantly improves accuracy across diverse audio understanding tasks; (ii) scalable strategies for constructing large-scale audio understanding and reasoning data beyond existing academic benchmarks; (iii) support for long and complex audio inputs up to 30 minutes; and (iv) Temporal Audio Chain-of-Thought, a new reasoning paradigm that explicitly grounds intermediate reasoning steps to timestamps in long audio, enabling fine-grained temporal alignment and improved interpretability. To enable these capabilities, we first conduct a systematic analysis of Audio Flamingo 3 to identify key gaps in audio understanding and reasoning. We then curate and scale new large-scale datasets totaling over 1 million hours to address these limitations and expand the existing AudioSkills-XL, LongAudio-XL, AF-Think and AF-Chat datasets. AF-Next is trained using a curriculum-based strategy spanning pre-training, mid-training and post-training stages. Extensive experiments across 20 audio understanding and reasoning benchmarks, including challenging long-audio tasks, show that AF-Next outperforms similarly sized open models by large margins and remains highly competitive with and sometimes surpasses, much larger open-weight and closed models. Beyond benchmark performance, AF-Next exhibits strong real-world utility and transfers well to unseen tasks, highlighting its robustness and generalization ability. In addition to all data, code and methods, we open-source 3 variants of AF-Next, including AF-Next-Instruct, AF-Next-Think and AF-Next-Captioner.

Namkyeong Lee, Dongmin Hyun, Gyoung S. Na et al.

Molecular relational learning, whose goal is to learn the interaction behavior between molecular pairs, got a surge of interest in molecular sciences due to its wide range of applications. Recently, graph neural networks have recently shown great success in molecular relational learning by modeling a molecule as a graph structure, and considering atom-level interactions between two molecules. Despite their success, existing molecular relational learning methods tend to overlook the nature of chemistry, i.e., a chemical compound is composed of multiple substructures such as functional groups that cause distinctive chemical reactions. In this work, we propose a novel relational learning framework, called CGIB, that predicts the interaction behavior between a pair of graphs by detecting core subgraphs therein. The main idea is, given a pair of graphs, to find a subgraph from a graph that contains the minimal sufficient information regarding the task at hand conditioned on the paired graph based on the principle of conditional graph information bottleneck. We argue that our proposed method mimics the nature of chemical reactions, i.e., the core substructure of a molecule varies depending on which other molecule it interacts with. Extensive experiments on various tasks with real-world datasets demonstrate the superiority of CGIB over state-of-the-art baselines. Our code is available at https://github.com/Namkyeong/CGIB.

Namkyeong Lee, Heewoong Noh, Sungwon Kim et al.

The density of states (DOS) is a spectral property of materials, which provides fundamental insights on various characteristics of materials. In this paper, we propose a model to predict the DOS by reflecting the nature of DOS: DOS determines the general distribution of states as a function of energy. Specifically, we integrate the heterogeneous information obtained from the crystal structure and the energies via multi-modal transformer, thereby modeling the complex relationships between the atoms in the crystal structure, and various energy levels. Extensive experiments on two types of DOS, i.e., Phonon DOS and Electron DOS, with various real-world scenarios demonstrate the superiority of DOSTransformer. The source code for DOSTransformer is available at https://github.com/HeewoongNoh/DOSTransformer.

Jooyoung Choi, Jungbeom Lee, Chaehun Shin et al.

Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i.e., denoising score matching loss. In this paper, we show that restoring data corrupted with certain noise levels offers a proper pretext task for the model to learn rich visual concepts. We propose to prioritize such noise levels over other levels during training, by redesigning the weighting scheme of the objective function. We show that our simple redesign of the weighting scheme significantly improves the performance of diffusion models regardless of the datasets, architectures, and sampling strategies.

Namkyeong Lee, Heewoong Noh, Sungwon Kim et al.

The density of states (DOS) is a spectral property of crystalline materials, which provides fundamental insights into various characteristics of the materials. While previous works mainly focus on obtaining high-quality representations of crystalline materials for DOS prediction, we focus on predicting the DOS from the obtained representations by reflecting the nature of DOS: DOS determines the general distribution of states as a function of energy. That is, DOS is not solely determined by the crystalline material but also by the energy levels, which has been neglected in previous works. In this paper, we propose to integrate heterogeneous information obtained from the crystalline materials and the energies via a multi-modal transformer, thereby modeling the complex relationships between the atoms in the crystalline materials and various energy levels for DOS prediction. Moreover, we propose to utilize prompts to guide the model to learn the crystal structural system-specific interactions between crystalline materials and energies. Extensive experiments on two types of DOS, i.e., Phonon DOS and Electron DOS, with various real-world scenarios demonstrate the superiority of DOSTransformer. The source code for DOSTransformer is available at https://github.com/HeewoongNoh/DOSTransformer.

Jihyeong Jung, Sangwoo Seo, Sungwon Kim et al.

We propose Unsupervised Episode Generation method called Neighbors as Queries (NaQ) to solve the Few-Shot Node-Classification (FSNC) task by unsupervised Graph Meta-learning. Doing so enables full utilization of the information of all nodes in a graph, which is not possible in current supervised meta-learning methods for FSNC due to the label-scarcity problem. In addition, unlike unsupervised Graph Contrastive Learning (GCL) methods that overlook the downstream task to be solved at the training phase resulting in vulnerability to class imbalance of a graph, we adopt the episodic learning framework that allows the model to be aware of the downstream task format, i.e., FSNC. The proposed NaQ is a simple but effective unsupervised episode generation method that randomly samples nodes from a graph to make a support set, followed by similarity-based sampling of nodes to make the corresponding query set. Since NaQ is model-agnostic, any existing supervised graph meta-learning methods can be trained in an unsupervised manner, while not sacrificing much of their performance or sometimes even improving them. Extensive experimental results demonstrate the effectiveness of our proposed unsupervised episode generation method for graph meta-learning towards the FSNC task. Our code is available at: https://github.com/JhngJng/NaQ-PyTorch.

Sungwon Kim, Heeseung Kim, Sungroh Yoon

We propose Guided-TTS 2, a diffusion-based generative model for high-quality adaptive TTS using untranscribed data. Guided-TTS 2 combines a speaker-conditional diffusion model with a speaker-dependent phoneme classifier for adaptive text-to-speech. We train the speaker-conditional diffusion model on large-scale untranscribed datasets for a classifier-free guidance method and further fine-tune the diffusion model on the reference speech of the target speaker for adaptation, which only takes 40 seconds. We demonstrate that Guided-TTS 2 shows comparable performance to high-quality single-speaker TTS baselines in terms of speech quality and speaker similarity with only a ten-second untranscribed data. We further show that Guided-TTS 2 outperforms adaptive TTS baselines on multi-speaker datasets even with a zero-shot adaptation setting. Guided-TTS 2 can adapt to a wide range of voices only using untranscribed speech, which enables adaptive TTS with the voice of non-human characters such as Gollum in \textit{"The Lord of the Rings"}.

Sangwoo Seo, Sungwon Kim, Chanyoung Park

The success of Graph Neural Networks (GNNs) has led to a need for understanding their decision-making process and providing explanations for their predictions, which has given rise to explainable AI (XAI) that offers transparent explanations for black-box models. Recently, the use of prototypes has successfully improved the explainability of models by learning prototypes to imply training graphs that affect the prediction. However, these approaches tend to provide prototypes with excessive information from the entire graph, leading to the exclusion of key substructures or the inclusion of irrelevant substructures, which can limit both the interpretability and the performance of the model in downstream tasks. In this work, we propose a novel framework of explainable GNNs, called interpretable Prototype-based Graph Information Bottleneck (PGIB) that incorporates prototype learning within the information bottleneck framework to provide prototypes with the key subgraph from the input graph that is important for the model prediction. This is the first work that incorporates prototype learning into the process of identifying the key subgraphs that have a critical impact on the prediction performance. Extensive experiments, including qualitative analysis, demonstrate that PGIB outperforms state-of-the-art methods in terms of both prediction performance and explainability.

Seungyoon Choi, Wonjoong Kim, Sungwon Kim et al.

We investigate the replay buffer in rehearsal-based approaches for graph continual learning (GCL) methods. Existing rehearsal-based GCL methods select the most representative nodes for each class and store them in a replay buffer for later use in training subsequent tasks. However, we discovered that considering only the class representativeness of each replayed node makes the replayed nodes to be concentrated around the center of each class, incurring a potential risk of overfitting to nodes residing in those regions, which aggravates catastrophic forgetting. Moreover, as the rehearsal-based approach heavily relies on a few replayed nodes to retain knowledge obtained from previous tasks, involving the replayed nodes that have irrelevant neighbors in the model training may have a significant detrimental impact on model performance. In this paper, we propose a GCL model named DSLR, specifically, we devise a coverage-based diversity (CD) approach to consider both the class representativeness and the diversity within each class of the replayed nodes. Moreover, we adopt graph structure learning (GSL) to ensure that the replayed nodes are connected to truly informative neighbors. Extensive experimental results demonstrate the effectiveness and efficiency of DSLR. Our source code is available at https://github.com/seungyoon-Choi/DSLR_official.

Sungwon Kim, Yoonho Lee, Yunhak Oh et al.

Federated Learning (FL) on graphs enables collaborative model training to enhance performance without compromising the privacy of each client. However, existing methods often overlook the mutable nature of graph data, which frequently introduces new nodes and leads to shifts in label distribution. Since they focus solely on performing well on each client's local data, they are prone to overfitting to their local distributions (i.e., local overfitting), which hinders their ability to generalize to unseen data with diverse label distributions. In contrast, our proposed method, FedLoG, effectively tackles this issue by mitigating local overfitting. Our model generates global synthetic data by condensing the reliable information from each class representation and its structural information across clients. Using these synthetic data as a training set, we alleviate the local overfitting problem by adaptively generalizing the absent knowledge within each local dataset. This enhances the generalization capabilities of local models, enabling them to handle unseen data effectively. Our model outperforms baselines in our proposed experimental settings, which are designed to measure generalization power to unseen data in practical scenarios. Our code is available at https://github.com/sung-won-kim/FedLoG

Mathew J. Koretsky, Maya Willey, Adi Asija et al.

Biomedical researchers increasingly rely on large-scale structured databases for complex analytical tasks. However, current text-to-SQL systems often struggle to map qualitative scientific questions into executable SQL, particularly when implicit domain reasoning is required. We introduce BiomedSQL, the first benchmark explicitly designed to evaluate scientific reasoning in text-to-SQL generation over a real-world biomedical knowledge base. BiomedSQL comprises 68,000 question/SQL query/answer triples generated from templates and grounded in a harmonized BigQuery knowledge base that integrates gene-disease associations, causal inference from omics data, and drug approval records. Each question requires models to infer domain-specific criteria, such as genome-wide significance thresholds, effect directionality, or trial phase filtering, rather than rely on syntactic translation alone. We evaluate a range of open- and closed-source LLMs across prompting strategies and interaction paradigms. Our results reveal a substantial performance gap: GPT-o3-mini achieves 59.0% execution accuracy, while our custom multi-step agent, BMSQL, reaches 62.6%, both well below the expert baseline of 90.0%. BiomedSQL provides a new foundation for advancing text-to-SQL systems capable of supporting scientific discovery through robust reasoning over structured biomedical knowledge bases. Our dataset is publicly available at https://huggingface.co/datasets/NIH-CARD/BiomedSQL, and our code is open-source at https://github.com/NIH-CARD/biomedsql.

Sungwon Kim, Junseok Lee, Namkyeong Lee et al.

Although Graph Neural Networks (GNNs) have been successful in node classification tasks, their performance heavily relies on the availability of a sufficient number of labeled nodes per class. In real-world situations, not all classes have many labeled nodes and there may be instances where the model needs to classify new classes, making manual labeling difficult. To solve this problem, it is important for GNNs to be able to classify nodes with a limited number of labeled nodes, known as few-shot node classification. Previous episodic meta-learning based methods have demonstrated success in few-shot node classification, but our findings suggest that optimal performance can only be achieved with a substantial amount of diverse training meta-tasks. To address this challenge of meta-learning based few-shot learning (FSL), we propose a new approach, the Task-Equivariant Graph few-shot learning (TEG) framework. Our TEG framework enables the model to learn transferable task-adaptation strategies using a limited number of training meta-tasks, allowing it to acquire meta-knowledge for a wide range of meta-tasks. By incorporating equivariant neural networks, TEG can utilize their strong generalization abilities to learn highly adaptable task-specific strategies. As a result, TEG achieves state-of-the-art performance with limited training meta-tasks. Our experiments on various benchmark datasets demonstrate TEG's superiority in terms of accuracy and generalization ability, even when using minimal meta-training data, highlighting the effectiveness of our proposed approach in addressing the challenges of meta-learning based few-shot node classification. Our code is available at the following link: https://github.com/sung-won-kim/TEG

Sang-gil Lee, Zhifeng Kong, Arushi Goel et al.

Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks are not well understood. With the purpose of providing a holistic understanding of the design space of TTA models, we set up a large-scale empirical experiment focused on diffusion and flow matching models. Our contributions include: 1) AF-Synthetic, a large dataset of high quality synthetic captions obtained from an audio understanding model; 2) a systematic comparison of different architectural, training, and inference design choices for TTA models; 3) an analysis of sampling methods and their Pareto curves with respect to generation quality and inference speed. We leverage the knowledge obtained from this extensive analysis to propose our best model dubbed Elucidated Text-To-Audio (ETTA). When evaluated on AudioCaps and MusicCaps, ETTA provides improvements over the baselines trained on publicly available data, while being competitive with models trained on proprietary data. Finally, we show ETTA's improved ability to generate creative audio following complex and imaginative captions -- a task that is more challenging than current benchmarks.

Yoonho Lee, Junseok Lee, Sangwoo Seo et al.

Despite the promising results of disentangled representation learning in discovering latent patterns in graph-structured data, few studies have explored disentanglement for hypergraph-structured data. Integrating hyperedge disentanglement into hypergraph neural networks enables models to leverage hidden hyperedge semantics, such as unannotated relations between nodes, that are associated with labels. This paper presents an analysis of hyperedge disentanglement from a category-theoretical perspective and proposes a novel criterion for disentanglement derived from the naturality condition. Our proof-of-concept model experimentally showed the potential of the proposed criterion by successfully capturing functional relations of genes (nodes) in genetic pathways (hyperedges).

Sungwon Kim, Daniel Khashabi

Large Language Models (LLMs) often exhibit sycophancy, distorting responses to align with user beliefs, notably by readily agreeing with user counterarguments. Paradoxically, LLMs are increasingly adopted as successful evaluative agents for tasks such as grading and adjudicating claims. This research investigates that tension: why do LLMs show sycophancy when challenged in subsequent conversational turns, yet perform well when evaluating conflicting arguments presented simultaneously? We empirically tested these contrasting scenarios by varying key interaction patterns. We find that state-of-the-art models: (1) are more likely to endorse a user's counterargument when framed as a follow-up from a user, rather than when both responses are presented simultaneously for evaluation; (2) show increased susceptibility to persuasion when the user's rebuttal includes detailed reasoning, even when the conclusion of the reasoning is incorrect; and (3) are more readily swayed by casually phrased feedback than by formal critiques, even when the casual input lacks justification. Our results highlight the risk of relying on LLMs for judgment tasks without accounting for conversational framing.

Sungwon Kim, Namkyeong Lee, Yunyoung Doh et al.

Mesh-based 3D static analysis methods have recently emerged as efficient alternatives to traditional computational numerical solvers, significantly reducing computational costs and runtime for various physics-based analyses. However, these methods primarily focus on surface topology and geometry, often overlooking the inherent thickness of real-world 3D objects, which exhibits high correlations and similar behavior between opposing surfaces. This limitation arises from the disconnected nature of these surfaces and the absence of internal edge connections within the mesh. In this work, we propose a novel framework, the Thickness-aware E(3)-Equivariant 3D Mesh Neural Network (T-EMNN), that effectively integrates the thickness of 3D objects while maintaining the computational efficiency of surface meshes. Additionally, we introduce data-driven coordinates that encode spatial information while preserving E(3)-equivariance or invariance properties, ensuring consistent and robust analysis. Evaluations on a real-world industrial dataset demonstrate the superior performance of T-EMNN in accurately predicting node-level 3D deformations, effectively capturing thickness effects while maintaining computational efficiency.

Sangwoo Seo, Sungwon Kim, Jihyeong Jung et al.

Temporal Graph Neural Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGNN models due to the difficulty in identifying how past events influence their predictions. Since the explanation model for a static graph cannot be readily applied to temporal graphs due to its inability to capture temporal dependencies, recent studies proposed explanation models for temporal graphs. However, existing explanation models for temporal graphs rely on post-hoc explanations, requiring separate models for prediction and explanation, which is limited in two aspects: efficiency and accuracy of explanation. In this work, we propose a novel built-in explanation framework for temporal graphs, called Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck (TGIB). TGIB provides explanations for event occurrences by introducing stochasticity in each temporal event based on the Information Bottleneck theory. Experimental results demonstrate the superiority of TGIB in terms of both the link prediction performance and explainability compared to state-of-the-art methods. This is the first work that simultaneously performs prediction and explanation for temporal graphs in an end-to-end manner.

Akshit Arora, Rohan Badlani, Sungwon Kim et al.

In this paper, we describe the TTS models developed by NVIDIA for the MMITS-VC (Multi-speaker, Multi-lingual Indic TTS with Voice Cloning) 2024 Challenge. In Tracks 1 and 2, we utilize RAD-MMM to perform few-shot TTS by training additionally on 5 minutes of target speaker data. In Track 3, we utilize P-Flow to perform zero-shot TTS by training on the challenge dataset as well as external datasets. We use HiFi-GAN vocoders for all submissions. RAD-MMM performs competitively on Tracks 1 and 2, while P-Flow ranks first on Track 3, with mean opinion score (MOS) 4.4 and speaker similarity score (SMOS) of 3.62.

Heeseung Kim, Sungwon Kim, Sungroh Yoon

We propose Guided-TTS, a high-quality text-to-speech (TTS) model that does not require any transcript of target speaker using classifier guidance. Guided-TTS combines an unconditional diffusion probabilistic model with a separately trained phoneme classifier for classifier guidance. Our unconditional diffusion model learns to generate speech without any context from untranscribed speech data. For TTS synthesis, we guide the generative process of the diffusion model with a phoneme classifier trained on a large-scale speech recognition dataset. We present a norm-based scaling method that reduces the pronunciation errors of classifier guidance in Guided-TTS. We show that Guided-TTS achieves a performance comparable to that of the state-of-the-art TTS model, Grad-TTS, without any transcript for LJSpeech. We further demonstrate that Guided-TTS performs well on diverse datasets including a long-form untranscribed dataset.

Yonghyun Jeong, Jooyoung Choi, Sungwon Kim et al.

In this work, we present Facial Identity Controllable GAN (FICGAN) for not only generating high-quality de-identified face images with ensured privacy protection, but also detailed controllability on attribute preservation for enhanced data utility. We tackle the less-explored yet desired functionality in face de-identification based on the two factors. First, we focus on the challenging issue to obtain a high level of privacy protection in the de-identification task while uncompromising the image quality. Second, we analyze the facial attributes related to identity and non-identity and explore the trade-off between the degree of face de-identification and preservation of the source attributes for enhanced data utility. Based on the analysis, we develop Facial Identity Controllable GAN (FICGAN), an autoencoder-based conditional generative model that learns to disentangle the identity attributes from non-identity attributes on a face image. By applying the manifold k-same algorithm to satisfy k-anonymity for strengthened security, our method achieves enhanced privacy protection in de-identified face images. Numerous experiments demonstrate that our model outperforms others in various scenarios of face de-identification.

Jongyoon Song, Sungwon Kim, Sungroh Yoon

Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition. Most recent approaches have attempted to solve this problem by implicitly modeling dependencies between outputs. In this paper, we introduce AligNART, which leverages full alignment information to explicitly reduce the modality of the target distribution. AligNART divides the machine translation task into $(i)$ alignment estimation and $(ii)$ translation with aligned decoder inputs, guiding the decoder to focus on simplified one-to-one translation. To alleviate the alignment estimation problem, we further propose a novel alignment decomposition method. Our experiments show that AligNART outperforms previous non-iterative NART models that focus on explicit modality reduction on WMT14 En$\leftrightarrow$De and WMT16 Ro$\rightarrow$En. Furthermore, AligNART achieves BLEU scores comparable to those of the state-of-the-art connectionist temporal classification based models on WMT14 En$\leftrightarrow$De. We also observe that AligNART effectively addresses the token repetition problem even without sequence-level knowledge distillation.

Jooyoung Choi, Sungwon Kim, Yonghyun Jeong et al.

Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in DDPM, it is challenging to generate images with the desired semantics. In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image. Here, the refinement of the generative process in DDPM enables a single DDPM to sample images from various sets directed by the reference image. The proposed ILVR method generates high-quality images while controlling the generation. The controllability of our method allows adaptation of a single DDPM without any additional learning in various image generation tasks, such as generation from various downsampling factors, multi-domain image translation, paint-to-image, and editing with scribbles.

Sang-gil Lee, Sungwon Kim, Sungroh Yoon

Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. However, a flow-based network is considered to be inefficient in parameter complexity because of reduced expressiveness of bijective mapping, which renders the models unfeasibly expensive in terms of parameters. We present an alternative parameterization scheme called NanoFlow, which uses a single neural density estimator to model multiple transformation stages. Hence, we propose an efficient parameter decomposition method and the concept of flow indication embedding, which are key missing components that enable density estimation from a single neural network. Experiments performed on audio and image models confirm that our method provides a new parameter-efficient solution for scalable NFs with significant sublinear parameter complexity.

Jaehyeon Kim, Sungwon Kim, Jungil Kong et al.

Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet have been proposed to generate mel-spectrograms from text in parallel. Despite the advantage, the parallel TTS models cannot be trained without guidance from autoregressive TTS models as their external aligners. In this work, we propose Glow-TTS, a flow-based generative model for parallel TTS that does not require any external aligner. By combining the properties of flows and dynamic programming, the proposed model searches for the most probable monotonic alignment between text and the latent representation of speech on its own. We demonstrate that enforcing hard monotonic alignments enables robust TTS, which generalizes to long utterances, and employing generative flows enables fast, diverse, and controllable speech synthesis. Glow-TTS obtains an order-of-magnitude speed-up over the autoregressive model, Tacotron 2, at synthesis with comparable speech quality. We further show that our model can be easily extended to a multi-speaker setting.

Sungwon Kim, Sang-gil Lee, Jongyoon Song et al.

Most modern text-to-speech architectures use a WaveNet vocoder for synthesizing high-fidelity waveform audio, but there have been limitations, such as high inference time, in its practical application due to its ancestral sampling scheme. The recently suggested Parallel WaveNet and ClariNet have achieved real-time audio synthesis capability by incorporating inverse autoregressive flow for parallel sampling. However, these approaches require a two-stage training pipeline with a well-trained teacher network and can only produce natural sound by using probability distillation along with auxiliary loss terms. We propose FloWaveNet, a flow-based generative model for raw audio synthesis. FloWaveNet requires only a single-stage training procedure and a single maximum likelihood loss, without any additional auxiliary terms, and it is inherently parallel due to the characteristics of generative flow. The model can efficiently sample raw audio in real-time, with clarity comparable to previous two-stage parallel models. The code and samples for all models, including our FloWaveNet, are publicly available.