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 a self-supervised hidden representation of the generator to a conditional discriminator. This leads to better guidance for generator training. Moreover, we also propose adversarial style combination (ASC) for better generalization in the unseen speaking style and transcript, which can learn latent representations of the combined style embedding from multiple mel-spectrograms. Trained with ASC and feature matching, the MSG synthesizes a high-diversity mel-spectrogram by controlling and mixing the individual speaking styles (e.g., duration, pitch, and energy). The result shows that the MSG synthesizes a high-fidelity mel-spectrogram, which has almost the same naturalness MOS score as the ground-truth mel-spectrogram.
We describe our approach for the generative emotional vocal burst task (ExVo Generate) of the ICML Expressive Vocalizations Competition. We train a conditional StyleGAN2 architecture on mel-spectrograms of preprocessed versions of the audio samples. The mel-spectrograms generated by the model are then inverted back to the audio domain. As a result, our generated samples substantially improve upon the baseline provided by the competition from a qualitative and quantitative perspective for all emotions. More precisely, even for our worst-performing emotion (awe), we obtain an FAD of 1.76 compare…
Traditional voice conversion methods rely on parallel recordings of multiple speakers pronouncing the same sentences. For real-world applications however, parallel data is rarely available. We propose MelGAN-VC, a voice conversion method that relies on non-parallel speech data and is able to convert audio signals of arbitrary length from a source voice to a target voice. We firstly compute spectrograms from waveform data and then perform a domain translation using a Generative Adversarial Network (GAN) architecture. An additional siamese network helps preserving speech information in the trans…
We present a system for generating song lyrics lines conditioned on the style of a specified artist. The system uses a variational autoencoder with artist embeddings. We propose the pre-training of artist embeddings with the representations learned by a CNN classifier, which is trained to predict artists based on MEL spectrograms of their song clips. This work is the first step towards combining audio and text modalities of songs for generating lyrics conditioned on the artist's style. Our preliminary results suggest that there is a benefit in initializing artists' embeddings with the represen…
Style transfer is a technique for combining two images based on the activations and feature statistics in a deep learning neural network architecture. This paper studies the analogous task in the audio domain and takes a critical look at the problems that arise when adapting the original vision-based framework to handle spectrogram representations. We conclude that CNN architectures with features based on 2D representations and convolutions are better suited for visual images than for time-frequency representations of audio. Despite the awkward fit, experiments show that the Gram matrix determ…
This paper presents a novel design of neural network system for fine-grained style modeling, transfer and prediction in expressive text-to-speech (TTS) synthesis. Fine-grained modeling is realized by extracting style embeddings from the mel-spectrograms of phone-level speech segments. Collaborative learning and adversarial learning strategies are applied in order to achieve effective disentanglement of content and style factors in speech and alleviate the "content leakage" problem in style modeling. The proposed system can be used for varying-content speech style transfer in the single-speaker…
One-shot voice conversion (VC) aims to convert speech from any source speaker to an arbitrary target speaker with only a few seconds of reference speech from the target speaker. This relies heavily on disentangling the speaker's identity and speech content, a task that still remains challenging. Here, we propose a novel approach to learning disentangled speech representation by transfer learning from style-based text-to-speech (TTS) models. With cycle consistent and adversarial training, the style-based TTS models can perform transcription-guided one-shot VC with high fidelity and similarity. …
This paper adapts a StyleGAN model for speech generation with minimal or no conditioning on text. StyleGAN is a multi-scale convolutional GAN capable of hierarchically capturing data structure and latent variation on multiple spatial (or temporal) levels. The model has previously achieved impressive results on facial image generation, and it is appealing to audio applications due to similar multi-level structures present in the data. In this paper, we train a StyleGAN to generate mel-frequency spectrograms on the Speech Commands dataset, which contains spoken digits uttered by multiple speaker…
Along with the evolution of music technology, a large number of styles, or "subgenres," of Electronic Dance Music(EDM) have emerged in recent years. While the classification task of distinguishing between EDM and non-EDM has been often studied in the context of music genre classification, little work has been done on the more challenging EDM subgenre classification. The state-of-art model is based on extremely randomized trees and could be improved by deep learning methods. In this paper, we extend the state-of-art music auto-tagging model "short-chunkCNN+Resnet" to EDM subgenre classification…
In multi-speaker speech synthesis, data from a number of speakers usually tend to have great diversity due to the fact that the speakers may differ largely in ages, speaking styles, emotions, and so on. It is important but challenging to improve the modeling capabilities for multi-speaker speech synthesis. To address the issue, this paper proposes a high-capability speech synthesis system, called Msdtron, in which 1) a representation of the harmonic structure of speech, called excitation spectrogram, is designed to directly guide the learning of harmonics in mel-spectrogram. 2) conditional gat…
StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis
The Chinese University of Hong Kong（香港中文大学）；Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems（清华-香港中文大学媒体科学、技术与系统联合研究中心）；Tsinghua University（清华大学）；Microsoft（微软）
National Tsing-Hua University（国立清华大学）；Academia Sinica（中央研究院）
Style transfer of polyphonic music recordings is a challenging task when considering the modeling of diverse, imaginative, and reasonable music pieces in the style different from their original one. To achieve this, learning stable multi-modal representations for both domain-variant (i.e., style) and domain-invariant (i.e., content) information of music in an unsupervised manner is critical. In this paper, we propose an unsupervised music style transfer method without the need for parallel data. Besides, to characterize the multi-modal distribution of music pieces, we employ the Multi-modal Un…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Hidden-Markov-model (HMM) based text-to-speech (HTS) offers flexibility in speaking styles along with fast training and synthesis while being computationally less intense. HTS performs well even in low-resource scenarios. The primary drawback is that the voice quality is poor compared to that of E2E systems. A hybrid approach combining HMM-based feature generation and neural-network-based HiFi-GAN vocoder to improve HTS synthesis quality is proposed. HTS is trained on high-resolution mel-spectrograms instead of conventional mel generalized coefficients (MGC), and the output mel-spectrogram cor…
Voice impersonation is not the same as voice transformation, although the latter is an essential element of it. In voice impersonation, the resultant voice must convincingly convey the impression of having been naturally produced by the target speaker, mimicking not only the pitch and other perceivable signal qualities, but also the style of the target speaker. In this paper, we propose a novel neural network based speech quality- and style- mimicry framework for the synthesis of impersonated voices. The framework is built upon a fast and accurate generative adversarial network model. Given sp…
Generalized Multilingual Text-to-Speech Generation with Language-Aware Style Adaptation
School of Computer Science and Engineering, UNSW Sydney（新南威尔士大学悉尼分校计算机科学与工程学院）；School of Engineering, Institute of Science Tokyo（东京科学大学工程学院）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织数据61部门）
DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech
Institute of Automation, Chinese Academy of Science（中国科学院自动化研究所）；Beijing National Research Center for Information Science and Technology, Tsinghua University（清华大学北京信息科学与技术国家研究中心）；AI Lab, Tencent（腾讯AI实验室）
In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to provide high-quality and expressive mel-spectrogram synthesis. Flowtron is optimized by maximizing the likelihood of the training data, which makes training simple and stable. Flowtron learns an invertible mapping of data to a latent space that can be manipulated to control many aspects of speech synthesis (pitch, tone, speech rate, cadence, accent). Our mean opi…
In this work, we pose and address the following "cover song analogies" problem: given a song A by artist 1 and a cover song A' of this song by artist 2, and given a different song B by artist 1, synthesize a song B' which is a cover of B in the style of artist 2. Normally, such a polyphonic style transfer problem would be quite challenging, but we show how the cover songs example constrains the problem, making it easier to solve. First, we extract the longest common beat-synchronous subsequence between A and A', and we time stretch the corresponding beat intervals in A' so that they align with…
Southern University of Science and Technology（南方科技大学）；University of Technology Sydney（悉尼科技大学）；National University of Singapore（新加坡国立大学）；Zhejiang University（浙江大学）
Voice conversion is to generate a new speech with the source content and a target voice style. In this paper, we focus on one general setting, i.e., non-parallel many-to-many voice conversion, which is close to the real-world scenario. As the name implies, non-parallel many-to-many voice conversion does not require the paired source and reference speeches and can be applied to arbitrary voice transfer. In recent years, Generative Adversarial Networks (GANs) and other techniques such as Conditional Variational Autoencoders (CVAEs) have made considerable progress in this field. However, due to t…
This paper investigates the use of generative adversarial network (GAN)-based models for converting the spectrogram of a speech signal into that of a singing one, without reference to the phoneme sequence underlying the speech. This is achieved by viewing speech-to-singing conversion as a style transfer problem. Specifically, given a speech input, and optionally the F0 contour of the target singing, the proposed model generates as the output a singing signal with a progressive-growing encoder/decoder architecture and boundary equilibrium GAN loss functions. Our quantitative and qualitative ana…
Institut de Recherche et Coordination Acoustique-Musique (IRCAM)（声学与音乐研究协作研究所（IRCAM））；CNRS（法国国家科学研究中心）；UPMC - Sorbonne Universite（巴黎第六大学-索邦大学）
Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including semantic controls that can be adapted to different sound libraries and specific tags. These generative variables should allow expressive modulations of target musical qualities and continuously mix into new styles. To this extent we train AEs on an orchestral database of individual note samples, along with their intrinsic attributes: note class, timbre domain…
Recently the state-of-the-art text-to-speech synthesis systems have shifted to a two-model approach: a sequence-to-sequence model to predict a representation of speech (typically mel-spectrograms), followed by a 'neural vocoder' model which produces the time-domain speech waveform from this intermediate speech representation. This approach is capable of synthesizing speech that is confusable with natural speech recordings. However, the inference speed of neural vocoder approaches represents a major obstacle for deploying this technology for commercial applications. Parallel WaveNet is one appr…
Soochow University（苏州大学）；ByteDance AI Lab（字节跳动人工智能实验室）
Recently, phonetic posteriorgrams (PPGs) based methods have been quite popular in non-parallel singing voice conversion systems. However, due to the lack of acoustic information in PPGs, style and naturalness of the converted singing voices are still limited. To solve these problems, in this paper, we utilize an acoustic reference encoder to implicitly model singing characteristics. We experiment with different auxiliary features, including mel spectrograms, HuBERT, and the middle hidden feature (PPG-Mid) of pretrained automatic speech recognition (ASR) model, as the input of the reference enc…
The capability of generating speech with specific type of emotion is desired for many applications of human-computer interaction. Cross-speaker emotion transfer is a common approach to generating emotional speech when speech with emotion labels from target speakers is not available for model training. This paper presents a novel cross-speaker emotion transfer system, named iEmoTTS. The system is composed of an emotion encoder, a prosody predictor, and a timbre encoder. The emotion encoder extracts the identity of emotion type as well as the respective emotion intensity from the mel-spectrogram…
