Hyeongju Kim

June Young Yi, Hyeongju Kim, Juheon Lee

This paper presents a lightweight text-to-speech (TTS) system developed for the WildSpoof Challenge TTS Track. Our approach fine-tunes the recently released open-weight TTS model, \textit{Supertonic}\footnote{\url{https://github.com/supertone-inc/supertonic}}, with Self-Purifying Flow Matching (SPFM) to enable robust adaptation to in-the-wild speech. SPFM mitigates label noise by comparing conditional and unconditional flow matching losses on each sample, routing suspicious text--speech pairs to unconditional training while still leveraging their acoustic information. The resulting model achieves the lowest Word Error Rate (WER) among all participating teams, while ranking second in perceptual metrics such as UTMOS and DNSMOS. These findings demonstrate that efficient, open-weight architectures like Supertonic can be effectively adapted to diverse real-world speech conditions when combined with explicit noise-handling mechanisms such as SPFM.

Jinhyeok Yang, Hyeongju Kim, Yechan Yu et al.

While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment. We propose RobustSpeechFlow, a training strategy that improves alignment robustness by extending contrastive flow matching with length-preserving repeat and skip latent augmentations. Requiring no external aligners or preference data, our method directly penalizes realistic failure modes and readily integrates into existing pipelines. On Seed-TTS-eval, it reduces the word error rate (WER) from 1.44 to 1.38 using only 0.06B parameters. On our ZERO500 benchmark, it delivers consistent intelligibility improvements across diverse speaker and prosody conditions; at NFE=24, it reduces English character error rate (CER) from 0.48\% to 0.35\% and Korean CER from 0.81\% to 0.57\%. Audio samples: https://robustspeechflow.github.io/

Hyeongju Kim, Juheon Lee, Jinhyeok Yang et al.

Many recent text-to-speech (TTS) systems are built on transformer architectures and employ cross-attention mechanisms for text-speech alignment. Within these systems, rotary position embedding (RoPE) is commonly used to encode positional information in text and speech representations. In this work, we introduce length-aware RoPE (LARoPE), a simple yet effective extension of RoPE that improves text-speech alignment. Unlike RoPE, which relies on absolute indices, LARoPE computes relative distances between query and key positions using length-normalized indices. Experimental results show that LARoPE consistently outperforms RoPE, offering faster loss convergence, more accurate text-speech alignment, and higher overall TTS quality. Furthermore, LARoPE demonstrates greater resilience to variations in utterance duration and maintains stable performance in extended speech generation up to 30 seconds, whereas RoPE suffers from notable degradation. Notably, our method achieves a state-of-the-art word error rate on a standard zero-shot TTS benchmark.

Hyeongju Kim, Yechan Yu, June Young Yi et al.

Training datasets are inherently imperfect, often containing mislabeled samples due to human annotation errors, limitations of tagging models, and other sources of noise. Such label contamination can significantly degrade the performance of a trained model. In this work, we introduce Self-Purifying Flow Matching (SPFM), a principled approach to filtering unreliable data within the flow-matching framework. SPFM identifies suspicious data using the model itself during the training process, bypassing the need for pretrained models or additional modules. Our experiments demonstrate that models trained with SPFM generate samples that accurately adhere to the specified conditioning, even when trained on noisy labels. Furthermore, we validate the robustness of SPFM on the TITW dataset, which consists of in-the-wild speech data, achieving performance that surpasses existing baselines.

Hyeongju Kim, Jinhyeok Yang, Yechan Yu et al.

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent module leveraging flow-matching for text-to-latent mapping, and an utterance-level duration predictor. To enable a lightweight architecture, we employ a low-dimensional latent space, temporal compression of latents, and ConvNeXt blocks. The TTS pipeline is further simplified by operating directly on raw character-level text and employing cross-attention for text-speech alignment, thus eliminating the need for grapheme-to-phoneme (G2P) modules and external aligners. In addition, we propose context-sharing batch expansion that accelerates loss convergence and stabilizes text-speech alignment with minimal memory and I/O overhead. Experimental results demonstrate that SupertonicTTS delivers performance comparable to contemporary zero-shot TTS models with only 44M parameters, while significantly reducing architectural complexity and computational cost. Audio samples are available at: https://supertonictts.github.io/.

Jaesung Tae, Hyeongju Kim, Taesu Kim

We present EdiTTS, an off-the-shelf speech editing methodology based on score-based generative modeling for text-to-speech synthesis. EdiTTS allows for targeted, granular editing of audio, both in terms of content and pitch, without the need for any additional training, task-specific optimization, or architectural modifications to the score-based model backbone. Specifically, we apply coarse yet deliberate perturbations in the Gaussian prior space to induce desired behavior from the diffusion model while applying masks and softening kernels to ensure that iterative edits are applied only to the target region. Through listening tests and speech-to-text back transcription, we show that EdiTTS outperforms existing baselines and produces robust samples that satisfy user-imposed requirements.

Jaesung Tae, Hyeongju Kim, Younggun Lee

Recent developments in deep learning have significantly improved the quality of synthesized singing voice audio. However, prominent neural singing voice synthesis systems suffer from slow inference speed due to their autoregressive design. Inspired by MLP-Mixer, a novel architecture introduced in the vision literature for attention-free image classification, we propose MLP Singer, a parallel Korean singing voice synthesis system. To the best of our knowledge, this is the first work that uses an entirely MLP-based architecture for voice synthesis. Listening tests demonstrate that MLP Singer outperforms a larger autoregressive GAN-based system, both in terms of audio quality and synthesis speed. In particular, MLP Singer achieves a real-time factor of up to 200 and 3400 on CPUs and GPUs respectively, enabling order of magnitude faster generation on both environments.

Myeonghun Jeong, Hyeongju Kim, Sung Jun Cheon et al.

Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness and architectural efficiency. In this work, we propose a novel non-autoregressive TTS model, namely Diff-TTS, which achieves highly natural and efficient speech synthesis. Given the text, Diff-TTS exploits a denoising diffusion framework to transform the noise signal into a mel-spectrogram via diffusion time steps. In order to learn the mel-spectrogram distribution conditioned on the text, we present a likelihood-based optimization method for TTS. Furthermore, to boost up the inference speed, we leverage the accelerated sampling method that allows Diff-TTS to generate raw waveforms much faster without significantly degrading perceptual quality. Through experiments, we verified that Diff-TTS generates 28 times faster than the real-time with a single NVIDIA 2080Ti GPU.

Hyeonseung Lee, Woo Hyun Kang, Sung Jun Cheon et al.

Recently, attention-based encoder-decoder (AED) models have shown state-of-the-art performance in automatic speech recognition (ASR). As the original AED models with global attentions are not capable of online inference, various online attention schemes have been developed to reduce ASR latency for better user experience. However, a common limitation of the conventional softmax-based online attention approaches is that they introduce an additional hyperparameter related to the length of the attention window, requiring multiple trials of model training for tuning the hyperparameter. In order to deal with this problem, we propose a novel softmax-free attention method and its modified formulation for online attention, which does not need any additional hyperparameter at the training phase. Through a number of ASR experiments, we demonstrate the tradeoff between the latency and performance of the proposed online attention technique can be controlled by merely adjusting a threshold at the test phase. Furthermore, the proposed methods showed competitive performance to the conventional global and online attentions in terms of word-error-rates (WERs).

Hyeongju Kim, Hyeonseung Lee, Woo Hyun Kang et al.

In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time. However, these models require either a well-trained teacher network or a number of flow steps making them memory-inefficient. In this paper, we propose a novel generative model called WaveNODE which exploits a continuous normalizing flow for speech synthesis. Unlike the conventional models, WaveNODE places no constraint on the function used for flow operation, thus allowing the usage of more flexible and complex functions. Moreover, WaveNODE can be optimized to maximize the likelihood without requiring any teacher network or auxiliary loss terms. We experimentally show that WaveNODE achieves comparable performance with fewer parameters compared to the conventional flow-based vocoders.