Junhyeok Lee

Junhyeok Lee, Seungu Han, Hyunjae Cho et al.

Previous generative adversarial network (GAN)-based neural vocoders are trained to reconstruct the exact ground truth waveform from the paired mel-spectrogram and do not consider the one-to-many relationship of speech synthesis. This conventional training causes overfitting for both the discriminators and the generator, leading to the periodicity artifacts in the generated audio signal. In this work, we present PhaseAug, the first differentiable augmentation for speech synthesis that rotates the phase of each frequency bin to simulate one-to-many mapping. With our proposed method, we outperform baselines without any architecture modification. Code and audio samples will be available at https://github.com/mindslab-ai/phaseaug.

Junhyeok Lee, Wonbin Jung, Hyunjae Cho et al.

Previous pitch-controllable text-to-speech (TTS) models rely on directly modeling fundamental frequency, leading to low variance in synthesized speech. To address this issue, we propose PITS, an end-to-end pitch-controllable TTS model that utilizes variational inference to model pitch. Based on VITS, PITS incorporates the Yingram encoder, the Yingram decoder, and adversarial training of pitch-shifted synthesis to achieve pitch-controllability. Experiments demonstrate that PITS generates high-quality speech that is indistinguishable from ground truth speech and has high pitch-controllability without quality degradation. Code, audio samples, and demo are available at https://github.com/anonymous-pits/pits.

Hyunjae Cho, Wonbin Jung, Junhyeok Lee et al.

In this paper, we present SANE-TTS, a stable and natural end-to-end multilingual TTS model. By the difficulty of obtaining multilingual corpus for given speaker, training multilingual TTS model with monolingual corpora is unavoidable. We introduce speaker regularization loss that improves speech naturalness during cross-lingual synthesis as well as domain adversarial training, which is applied in other multilingual TTS models. Furthermore, by adding speaker regularization loss, replacing speaker embedding with zero vector in duration predictor stabilizes cross-lingual inference. With this replacement, our model generates speeches with moderate rhythm regardless of source speaker in cross-lingual synthesis. In MOS evaluation, SANE-TTS achieves naturalness score above 3.80 both in cross-lingual and intralingual synthesis, where the ground truth score is 3.99. Also, SANE-TTS maintains speaker similarity close to that of ground truth even in cross-lingual inference. Audio samples are available on our web page.

Hyoung-Kyu Song, Sang Hoon Woo, Junhyeok Lee et al.

In this work, we propose a joint system combining a talking face generation system with a text-to-speech system that can generate multilingual talking face videos from only the text input. Our system can synthesize natural multilingual speeches while maintaining the vocal identity of the speaker, as well as lip movements synchronized to the synthesized speech. We demonstrate the generalization capabilities of our system by selecting four languages (Korean, English, Japanese, and Chinese) each from a different language family. We also compare the outputs of our talking face generation model to outputs of a prior work that claims multilingual support. For our demo, we add a translation API to the preprocessing stage and present it in the form of a neural dubber so that users can utilize the multilingual property of our system more easily.

Seungu Han, Junhyeok Lee

Conventionally, audio super-resolution models fixed the initial and the target sampling rates, which necessitate the model to be trained for each pair of sampling rates. We introduce NU-Wave 2, a diffusion model for neural audio upsampling that enables the generation of 48 kHz audio signals from inputs of various sampling rates with a single model. Based on the architecture of NU-Wave, NU-Wave 2 uses short-time Fourier convolution (STFC) to generate harmonics to resolve the main failure modes of NU-Wave, and incorporates bandwidth spectral feature transform (BSFT) to condition the bandwidths of inputs in the frequency domain. We experimentally demonstrate that NU-Wave 2 produces high-resolution audio regardless of the sampling rate of input while requiring fewer parameters than other models. The official code and the audio samples are available at https://mindslab-ai.github.io/nuwave2.

Junhyeok Lee, Hyeonuk Nam, Yong-Hwa Park

The goal of DCASE 2023 Challenge Task 7 is to generate various sound clips for Foley sound synthesis (FSS) by "category-to-sound" approach. "Category" is expressed by a single index while corresponding "sound" covers diverse and different sound examples. To generate diverse sounds for a given category, we adopt VITS, a text-to-speech (TTS) model with variational inference. In addition, we apply various techniques from speech synthesis including PhaseAug and Avocodo. Different from TTS models which generate short pronunciation from phonemes and speaker identity, the category-to-sound problem requires generating diverse sounds just from a category index. To compensate for the difference while maintaining consistency within each audio clip, we heavily modified the prior encoder to enhance consistency with posterior latent variables. This introduced additional Gaussian on the prior encoder which promotes variance within the category. With these modifications, we propose VIFS, variational inference for end-to-end Foley sound synthesis, which generates diverse high-quality sounds.

Changho Choi, Minho Kim, Junhyeok Lee et al.

We propose LatentSwap, a simple face swapping framework generating a face swap latent code of a given generator. Utilizing randomly sampled latent codes, our framework is light and does not require datasets besides employing the pre-trained models, with the training procedure also being fast and straightforward. The loss objective consists of only three terms, and can effectively control the face swap results between source and target images. By attaching a pre-trained GAN inversion model independent to the model and using the StyleGAN2 generator, our model produces photorealistic and high-resolution images comparable to other competitive face swap models. We show that our framework is applicable to other generators such as StyleNeRF, paving a way to 3D-aware face swapping and is also compatible with other downstream StyleGAN2 generator tasks. The source code and models can be found at \url{https://github.com/usingcolor/LatentSwap}.

Kang-wook Kim, Seung-won Park, Junhyeok Lee et al.

Recent works on voice conversion (VC) focus on preserving the rhythm and the intonation as well as the linguistic content. To preserve these features from the source, we decompose current non-parallel VC systems into two encoders and one decoder. We analyze each module with several experiments and reassemble the best components to propose Assem-VC, a new state-of-the-art any-to-many non-parallel VC system. We also examine that PPG and Cotatron features are speaker-dependent, and attempt to remove speaker identity with adversarial training. Code and audio samples are available at https://github.com/mindslab-ai/assem-vc.

Junhyeok Lee, Helin Wang, Yaohan Guan et al.

We introduce MaskVCT, a zero-shot voice conversion (VC) model that offers multi-factor controllability through multiple classifier-free guidances (CFGs). While previous VC models rely on a fixed conditioning scheme, MaskVCT integrates diverse conditions in a single model. To further enhance robustness and control, the model can leverage continuous or quantized linguistic features to enhance intellgibility and speaker similarity, and can use or omit pitch contour to control prosody. These choices allow users to seamlessly balance speaker identity, linguistic content, and prosodic factors in a zero-shot VC setting. Extensive experiments demonstrate that MaskVCT achieves the best target speaker and accent similarities while obtaining competitive word and character error rates compared to existing baselines. Audio samples are available at https://maskvct.github.io/.

Hyunjae Cho, Junhyeok Lee, Wonbin Jung

Non-autoregressive GAN-based neural vocoders are widely used due to their fast inference speed and high perceptual quality. However, they often suffer from audible artifacts such as tonal artifacts in their generated results. Therefore, we propose JenGAN, a new training strategy that involves stacking shifted low-pass filters to ensure the shift-equivariant property. This method helps prevent aliasing and reduce artifacts while preserving the model structure used during inference. In our experimental evaluation, JenGAN consistently enhances the performance of vocoder models, yielding significantly superior scores across the majority of evaluation metrics.

Junhyeok Lee, Seungu Han

In this work, we introduce NU-Wave, the first neural audio upsampling model to produce waveforms of sampling rate 48kHz from coarse 16kHz or 24kHz inputs, while prior works could generate only up to 16kHz. NU-Wave is the first diffusion probabilistic model for audio super-resolution which is engineered based on neural vocoders. NU-Wave generates high-quality audio that achieves high performance in terms of signal-to-noise ratio (SNR), log-spectral distance (LSD), and accuracy of the ABX test. In all cases, NU-Wave outperforms the baseline models despite the substantially smaller model capacity (3.0M parameters) than baselines (5.4-21%). The audio samples of our model are available at https://mindslab-ai.github.io/nuwave, and the code will be made available soon.