Recently, GAN based speech synthesis methods, such as MelGAN, have become very popular. Compared to conventional autoregressive based methods, parallel structures based generators make waveform generation process fast and stable. However, the quality of generated speech by autoregressive based neural vocoders, such as WaveRNN, is still higher than GAN. To address this issue, we propose a novel vocoder model: TFGAN, which is adversarially learned both in time and frequency domain. On one hand, we propose to discriminate ground-truth waveform from synthetic one in frequency domain for offering more consistency guarantees instead of only in time domain. On the other hand, in contrast to the conventionally frequency-domain STFT loss approach or feature map loss by discriminator to learn waveform, we propose a set of time-domain loss that encourage the generator to capture the waveform directly. TFGAN has nearly same synthesis speed as MelGAN, but the fidelity is significantly improved by our novel learning method. In our experiments, TFGAN shows the ability to achieve comparable mean opinion score (MOS) than autoregressive vocoder under speech synthesis context.
While generative adversarial networks (GANs) based neural text-to-speech (TTS) systems have shown significant improvement in neural speech synthesis, there is no TTS system to learn to synthesize speech from text sequences with only adversarial feedback. Because adversarial feedback alone is not sufficient to train the generator, current models still require the reconstruction loss compared with the ground-truth and the generated mel-spectrogram directly. In this paper, we present Multi-SpectroGAN (MSG), which can train the multi-speaker model with only the adversarial feedback by conditioning…
Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the intermediate representation. Although the intermediate representation is served as a bridge, there still exists critical mismatch between the acoustic model and the vocoder as they are commonly separately learned and work on different distributions of representation, leading to inevitable artifacts in the synthesized speech. In this work, different from using pre-desig…
Speech enhancement has seen great improvement in recent years mainly through contributions in denoising, speaker separation, and dereverberation methods that mostly deal with environmental effects on vocal audio. To enhance speech beyond the limitations of the original signal, we take a regeneration approach, in which we recreate the speech from its essence, including the semi-recognized speech, prosody features, and identity. We propose a wav-to-wav generative model for speech that can generate 24khz speech in a real-time manner and which utilizes a compact speech representation, composed of …
Denoising diffusion probabilistic models (DDPMs) are expressive generative models that have been used to solve a variety of speech synthesis problems. However, because of their high sampling costs, DDPMs are difficult to use in real-time speech processing applications. In this paper, we introduce DiffGAN-TTS, a novel DDPM-based text-to-speech (TTS) model achieving high-fidelity and efficient speech synthesis. DiffGAN-TTS is based on denoising diffusion generative adversarial networks (GANs), which adopt an adversarially-trained expressive model to approximate the denoising distribution. We sho…
STSR: High-Fidelity Speech Super-Resolution via Spectral-Transient Context Modeling
National Engineering Research Center for Multimedia Software, School of Computer Science（多媒体软件国家工程研究中心，计算机科学学院）；School of Artificial Intelligence（人工智能学院）
DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers
INRS-EMT, Université du Québec, Montréal, Canada（INRS-EMT，魁北克大学，蒙特利尔，加拿大）；Adobe Research, San Francisco, California, United States（Adobe研究，旧金山，加利福尼亚，美国）
In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recently proposed neural vocoder which utilized the linear predictive characteristic of speech signal in the WaveRNN architecture, can generate high quality speech with a speed faster than real-time on a single CPU core. However, LPCNet is still not efficient enough for online speech generation tasks. To address this issue, we adopt the multi-band linear predictive coding for WaveRNN vocoder. The multi-band method enables t…
Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. Although such methods improve the sampling efficiency and memory usage, their sample quality has not yet reached that of autoregressive and flow-based generative models. In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. As speech audio consists of sinusoidal signals with various periods, we demonstrate that modeling periodic patterns of an audio is crucial for enhancing sample quality. A subjective human evaluation (mean opini…
Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a studio. We use an end-to-end feed-forward WaveNet architecture, trained with multi-scale adversarial discriminators in both the time domain and the time-frequency domain. It relies on the deep feature matching losses of the discriminators to improve the perceptual quality of enhanced speech. The proposed model generalizes well to new speakers, new spee…
Recent advances in neural multi-speaker text-to-speech (TTS) models have enabled the generation of reasonably good speech quality with a single model and made it possible to synthesize the speech of a speaker with limited training data. Fine-tuning to the target speaker data with the multi-speaker model can achieve better quality, however, there still exists a gap compared to the real speech sample and the model depends on the speaker. In this work, we propose GANSpeech, which is a high-fidelity multi-speaker TTS model that adopts the adversarial training method to a non-autoregressive multi-s…
In recent years, neural vocoders have surpassed classical speech generation approaches in naturalness and perceptual quality of the synthesized speech. Computationally heavy models like WaveNet and WaveGlow achieve best results, while lightweight GAN models, e.g. MelGAN and Parallel WaveGAN, remain inferior in terms of perceptual quality. We therefore propose StyleMelGAN, a lightweight neural vocoder allowing synthesis of high-fidelity speech with low computational complexity. StyleMelGAN employs temporal adaptive normalization to style a low-dimensional noise vector with the acoustic features…
We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that can be trained with minimal supervision. By combining two types of discrete speech representations, we cast TTS as a composition of two sequence-to-sequence tasks: from text to high-level semantic tokens (akin to "reading") and from semantic tokens to low-level acoustic tokens ("speaking"). Decoupling these two tasks enables training of the "speaking" module using abundant audio-only data, and unlocks the highly efficient combination of pretraining and backtranslation to reduce the need for parallel data when training the…
Source-Filter-Based Generative Adversarial Neural Vocoder for High Fidelity Speech Synthesis
National Engineering Research Center of Speech and Language Information Processing（语音与语言信息处理国家工程研究中心）；University of Science and Technology of China（中国科学技术大学）
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and autoregressive models, such as WaveNet, remain the state of the art in generative modelling of audio signals such as human speech. To address this paucity, we introduce GAN-TTS, a Generative Adversarial Network for Text-to-Speech. Our architecture is composed of a conditional feed-forward generator producing raw speech audio, and an ensemble of discriminators whic…
In this paper, we propose WG-WaveNet, a fast, lightweight, and high-quality waveform generation model. WG-WaveNet is composed of a compact flow-based model and a post-filter. The two components are jointly trained by maximizing the likelihood of the training data and optimizing loss functions on the frequency domains. As we design a flow-based model that is heavily compressed, the proposed model requires much less computational resources compared to other waveform generation models during both training and inference time; even though the model is highly compressed, the post-filter maintains th…
NeuroIncept Decoder for High-Fidelity Speech Reconstruction from Neural Activity
CITIC-UGR University of Granada（CITIC-UGR格拉纳达大学）；Epilepsy Centre, Dept. Clinical Sciences Lund University Hospital（癫痫中心，临床科学系隆德大学医院）；School of Computing Science and Engineering VIT Bhopal University（计算科学与工程学院VIT博帕尔大学）
We propose a lightweight end-to-end text-to-speech model using multi-band generation and inverse short-time Fourier transform. Our model is based on VITS, a high-quality end-to-end text-to-speech model, but adopts two changes for more efficient inference: 1) the most computationally expensive component is partially replaced with a simple inverse short-time Fourier transform, and 2) multi-band generation, with fixed or trainable synthesis filters, is used to generate waveforms. Unlike conventional lightweight models, which employ optimization or knowledge distillation separately to train two ca…
Masakhane NLP（Masakhane自然语言处理社区）；Coqui（Coqui公司）；Saarland University（萨尔大学）；CLEAR Global（全球清晰语言组织）；Col·lectivaT（Col·lectivaT机构）；SIL International（国际暑期语言学院）；Leibniz Universität Hannover（汉诺威莱布尼茨大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Niger-Volta LTI（尼日尔-沃尔特语言技术倡议）；Carnegie Mellon University（卡内基梅隆大学）；Technical University of Munich（慕尼黑工业大学）；Makerere University（马凯雷雷大学）；Ewegbe Akademi（埃韦格贝学院）；Kwame Nkrumah University of Science and Technology（夸梅·恩克鲁玛科技大学）
BibleTTS is a large, high-quality, open speech dataset for ten languages spoken in Sub-Saharan Africa. The corpus contains up to 86 hours of aligned, studio quality 48kHz single speaker recordings per language, enabling the development of high-quality text-to-speech models. The ten languages represented are: Akuapem Twi, Asante Twi, Chichewa, Ewe, Hausa, Kikuyu, Lingala, Luganda, Luo, and Yoruba. This corpus is a derivative work of Bible recordings made and released by the Open.Bible project from Biblica. We have aligned, cleaned, and filtered the original recordings, and additionally hand-che…
Neural-based text-to-speech (TTS) systems achieve very high-fidelity speech generation because of the rapid neural network developments. However, the huge labeled corpus and high computation cost requirements limit the possibility of developing a high-fidelity TTS system by small companies or individuals. On the other hand, a neural vocoder, which has been widely adopted for the speech generation in neural-based TTS systems, can be trained with a relatively small unlabeled corpus. Therefore, in this paper, we explore a general framework to develop a neural post-filter (NPF) for low-cost TTS sy…
HiFi-Glot: High-Fidelity Neural Formant Synthesis with Differentiable Resonant Filters
Acoustic Lab, Department of Information Communications Engineering, Aalto University（声学实验室，信息与通信工程系，艾尔沃大学）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（数据科学学院，香港中文大学（深圳））；Department of Speech, Music and Hearing, KTH Royal Institute of Technology（语音、音乐与听觉系，皇家理工学院）
In this work, we propose a new mathematical vocoder algorithm(modified spectral inversion) that generates a waveform from acoustic features without phase estimation. The main benefit of using our proposed method is that it excludes the training stage of the neural vocoder from the end-to-end speech synthesis model. Our implementation can synthesize high fidelity speech at approximately 20 Mhz on CPU and 59.6MHz on GPU. This is 909 and 2,702 times faster compared to real-time. Since the proposed methodology is not a data-driven method, it is applicable to unseen voices and multiple languages wi…
DeepASMR: LLM-Based Zero-Shot ASMR Speech Generation for Anyone of Any Voice
Auditory Cognition and Computational Acoustics Lab, School of Computer Science& MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（计算机学院听力认知与计算声学实验室、教育部人工智能关键实验室、人工智能研究院，上海交通大学）
We propose Universal MelGAN, a vocoder that synthesizes high-fidelity speech in multiple domains. To preserve sound quality when the MelGAN-based structure is trained with a dataset of hundreds of speakers, we added multi-resolution spectrogram discriminators to sharpen the spectral resolution of the generated waveforms. This enables the model to generate realistic waveforms of multi-speakers, by alleviating the over-smoothing problem in the high frequency band of the large footprint model. Our structure generates signals close to ground-truth data without reducing the inference speed, by disc…
