This study presents an innovative Zero-Shot any-to-any Singing Voice Conversion (SVC) method, leveraging a novel clustering-based phoneme representation to effectively separate content, timbre, and singing style. This approach enables precise voice characteristic manipulation. We discovered that datasets with fewer recordings per artist are more susceptible to timbre leakage. Extensive testing on over 10,000 hours of singing and user feedback revealed our model significantly improves sound quality and timbre accuracy, aligning with our objectives and advancing voice conversion technology. Furthermore, this research advances zero-shot SVC and sets the stage for future work on discrete speech representation, emphasizing the preservation of rhyme.
Speaking rate refers to the average number of phonemes within some unit time, while the rhythmic patterns refer to duration distributions for realizations of different phonemes within different phonetic structures. Both are key components of prosody in speech, which is different for different speakers. Models like cycle-consistent adversarial network (Cycle-GAN) and variational auto-encoder (VAE) have been successfully applied to voice conversion tasks without parallel data. However, due to the neural network architectures and feature vectors chosen for these approaches, the length of the pred…
Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice
Laval University（拉瓦尔大学）；Mila-Québec AI Institute（米拉-魁北克人工智能研究所）；Concordia University（康考迪亚大学）；Université de Montréal（蒙特利尔大学）；Canada CIFAR AI Chair（加拿大 CIFAR 人工智能讲席）
FabasedVC: Enhancing Voice Conversion with Text Modality Fusion and Phoneme-Level SSL Features
School of Software Engineering, Xi'an Jiaotong University（西安交通大学软件工程学院）；AI Platform Department, bilibili（bilibili人工智能平台部）；School of Software Engineering, East China Normal University（华东师范大学软件工程学院）；School of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；Division of Music and Audio, Union Wheatland Culture and Media Ltd.（Union Wheatland Culture and Media Ltd.音乐与音频部）
Human-Computer Communications Laboratory（人机通信实验室）；The Chinese University of Hong Kong（香港中文大学）；SpeechX Limited（SpeechX有限公司）；University of Cambridge（剑桥大学）
Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody while maintaining speaker identity. To address this issue, we propose a VC system with explicit prosodic modelling and deep speaker embedding (DSE) learning. First, a speech-encoder strives to extract robust phoneme embeddings from atypical speech. Second, a prosody corrector takes in phoneme embeddings to infer typical phoneme duration and pitch values. Third, …
Baidu Silicon Valley Artificial Intelligence Lab（百度硅谷人工智能实验室）
We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. Deep Voice lays the groundwork for truly end-to-end neural speech synthesis. The system comprises five major building blocks: a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. For the segmentation model, we propose a novel way of performing phoneme boundary detection with deep neural networks using connectionist temporal classifica…
The Chinese University of Hong Kong（香港中文大学）；Cambridge University（剑桥大学）
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach, which utilizes text supervision during training. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. During the training stage, an encoder-decoder-based hybrid connectionist-temporal-classification-attention (CTC-attention) phoneme recognizer is trained, whose encoder has a bottle-neck layer. A BNE is obtained from the phoneme recognizer and is utilized to extract speaker-independent, dense and rich spoken content represen…
Meiji University（明治大学）；The University of Tokyo（东京大学）
This paper presents a free Japanese singing voice corpus that can be used for highly applicable and reproducible singing voice synthesis research. A singing voice corpus helps develop singing voice synthesis, but existing corpora have two critical problems: data imbalance (singing voice corpora do not guarantee phoneme balance, unlike speaking-voice corpora) and copyright issues (cannot legally share data). As a way to avoid these problems, we constructed a PJS (phoneme-balanced Japanese singing voice) corpus that guarantees phoneme balance and is licensed with CC BY-SA 4.0, and we composed me…
We present a new neural text to speech (TTS) method that is able to transform text to speech in voices that are sampled in the wild. Unlike other systems, our solution is able to deal with unconstrained voice samples and without requiring aligned phonemes or linguistic features. The network architecture is simpler than those in the existing literature and is based on a novel shifting buffer working memory. The same buffer is used for estimating the attention, computing the output audio, and for updating the buffer itself. The input sentence is encoded using a context-free lookup table that con…
Microsoft Research Asia, Microsoft Azure Speech（微软亚洲研究院，微软 Azure 语音）
Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims to adapt a source TTS model to synthesize personal voice for a target speaker using few speech data. Custom voice presents two unique challenges for TTS adaptation: 1) to support diverse customers, the adaptation model needs to handle diverse acoustic conditions that could be very different from source speech data, and 2) to support a large number of customers, the adaptation parameters need to be small enough for each target speaker to reduce memory usage while maintaining high voice quality. In this wo…
This paper introduces FastVC, an end-to-end model for fast Voice Conversion (VC). The proposed model can convert speech of arbitrary length from multiple source speakers to multiple target speakers. FastVC is based on a conditional AutoEncoder (AE) trained on non-parallel data and requires no annotations at all. This model's latent representation is shown to be speaker-independent and similar to phonemes, which is a desirable feature for VC systems. While the current VC systems primarily focus on achieving the highest overall speech quality, this paper tries to balance the development concerni…
Building a voice conversion system for noisy target speakers, such as users providing noisy samples or Internet found data, is a challenging task since the use of contaminated speech in model training will apparently degrade the conversion performance. In this paper, we leverage the advances of our recently proposed Glow-WaveGAN and propose a noise-independent speech representation learning approach for high-quality voice conversion for noisy target speakers. Specifically, we learn a latent feature space where we ensure that the target distribution modeled by the conversion model is exactly fr…
University of California at Berkeley（加州大学伯克利分校）；Intel AI Lab（英特尔人工智能实验室）
We present a method for converting the voices between a set of speakers. Our method is based on training multiple autoencoder paths, where there is a single speaker-independent encoder and multiple speaker-dependent decoders. The autoencoders are trained with an addition of an adversarial loss which is provided by an auxiliary classifier in order to guide the output of the encoder to be speaker independent. The training of the model is unsupervised in the sense that it does not require collecting the same utterances from the speakers nor does it require time aligning over phonemes. Due to the …
Singing voice conversion is to convert a singer's voice to another one's voice without changing singing content. Recent work shows that unsupervised singing voice conversion can be achieved with an autoencoder-based approach [1]. However, the converted singing voice can be easily out of key, showing that the existing approach cannot model the pitch information precisely. In this paper, we propose to advance the existing unsupervised singing voice conversion method proposed in [1] to achieve more accurate pitch translation and flexible pitch manipulation. Specifically, the proposed PitchNet add…
In this paper, we study the disentanglement of speaker and language representations in non-autoregressive cross-lingual TTS models from various aspects. We propose a phoneme length regulator that solves the length mismatch problem between IPA input sequence and monolingual alignment results. Using the phoneme length regulator, we present a FastPitch-based cross-lingual model with IPA symbols as input representations. Our experiments show that language-independent input representations (e.g. IPA symbols), an increasing number of training speakers, and explicit modeling of speech variance inform…
This paper introduces Taco-VC, a novel architecture for voice conversion based on Tacotron synthesizer, which is a sequence-to-sequence with attention model. The training of multi-speaker voice conversion systems requires a large number of resources, both in training and corpus size. Taco-VC is implemented using a single speaker Tacotron synthesizer based on Phonetic PosteriorGrams (PPGs) and a single speaker WaveNet vocoder conditioned on mel spectrograms. To enhance the converted speech quality, and to overcome over-smoothing, the outputs of Tacotron are passed through a novel speechenhancem…
University of Science and Technology of China（中国科学技术大学）
This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion is achieved by preserving the linguistic representations of source utterances while replacing the speaker representations with the target ones. Our model is built under the framework of encoder-decoder neural networks. A recognition encoder is designed to learn the disentangled linguistic representations with two strategies. First, phoneme transcriptions of…
Any-to-any voice conversion (VC) aims to convert the timbre of utterances from and to any speakers seen or unseen during training. Various any-to-any VC approaches have been proposed like AUTOVC, AdaINVC, and FragmentVC. AUTOVC, and AdaINVC utilize source and target encoders to disentangle the content and speaker information of the features. FragmentVC utilizes two encoders to encode source and target information and adopts cross attention to align the source and target features with similar phonetic content. Moreover, pre-trained features are adopted. AUTOVC used dvector to extract speaker in…
We describe our approach to create and deliver a custom voice for a conversational AI use-case. More specifically, we provide a voice for a Digital Einstein character, to enable human-computer interaction within the digital conversation experience. To create the voice which fits the context well, we first design a voice character and we produce the recordings which correspond to the desired speech attributes. We then model the voice. Our solution utilizes Fastspeech 2 for log-scaled mel-spectrogram prediction from phonemes and Parallel WaveGAN to generate the waveforms. The system supports a c…
In this paper, we tackle the singing voice phoneme segmentation problem in the singing training scenario by using language-independent information -- onset and prior coarse duration. We propose a two-step method. In the first step, we jointly calculate the syllable and phoneme onset detection functions (ODFs) using a convolutional neural network (CNN). In the second step, the syllable and phoneme boundaries and labels are inferred hierarchically by using a duration-informed hidden Markov model (HMM). To achieve the inference, we incorporate the a priori duration model as the transition probabi…
Zero-shot speaker adaptation aims to clone an unseen speaker's voice without any adaptation time and parameters. Previous researches usually use a speaker encoder to extract a global fixed speaker embedding from reference speech, and several attempts have tried variable-length speaker embedding. However, they neglect to transfer the personal pronunciation characteristics related to phoneme content, leading to poor speaker similarity in terms of detailed speaking styles and pronunciation habits. To improve the ability of the speaker encoder to model personal pronunciation characteristics, we pr…
Academia Sinica（中央研究院）；Nagoya University（名古屋大学）；National Cheng Kung University Hospital（国立成功大学医学院附设医院）
Voice conversion (VC) is an effective approach to electrolaryngeal (EL) speech enhancement, a task that aims to improve the quality of the artificial voice from an electrolarynx device. In frame-based VC methods, time alignment needs to be performed prior to model training, and the dynamic time warping (DTW) algorithm is widely adopted to compute the best time alignment between each utterance pair. The validity is based on the assumption that the same phonemes of the speakers have similar features and can be mapped by measuring a pre-defined distance between speech frames of the source and the…
NTT Communication Science Laboratories, NTT Corporation（日本电信电话公司NTT通信科学实验室）
This paper describes a method based on a sequence-to-sequence learning (Seq2Seq) with attention and context preservation mechanism for voice conversion (VC) tasks. Seq2Seq has been outstanding at numerous tasks involving sequence modeling such as speech synthesis and recognition, machine translation, and image captioning. In contrast to current VC techniques, our method 1) stabilizes and accelerates the training procedure by considering guided attention and proposed context preservation losses, 2) allows not only spectral envelopes but also fundamental frequency contours and durations of speec…
Renmin University of China（中国人民大学）；Carnegie Mellon University（卡内基梅隆大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Singing voice synthesis (SVS), as a specific task for generating the vocal singing voice from a music score, has drawn much attention in recent years. SVS faces the challenge that the singing has various pronunciation flexibility conditioned on the same music score. Most of the previous works of SVS can not well handle the misalignment between the music score and actual singing. In this paper, we propose an acoustic feature processing strategy, named PHONEix, with a phoneme distribution predictor, to alleviate the gap between the music score and the singing voice, which can be easily adopted i…
Cognitive Machine Learning (ENS - CNRS - EHESS - INRIA - PSL Research University)（认知机器学习实验室（巴黎高等师范学院 - 法国国家科学研究中心 - 法国高等社会科学研究院 - 法国国家信息与自动化研究所 - PSL研究大学））；Brno Univ. of Technology（布尔诺理工大学）；Carnegie Mellon University（卡内基梅隆大学）；Nara Institute of Science and Technology（奈良科学技术研究所）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；Facebook A.I. Research（脸书人工智能研究部）
We present the Zero Resource Speech Challenge 2019, which proposes to build a speech synthesizer without any text or phonetic labels: hence, TTS without T (text-to-speech without text). We provide raw audio for a target voice in an unknown language (the Voice dataset), but no alignment, text or labels. Participants must discover subword units in an unsupervised way (using the Unit Discovery dataset) and align them to the voice recordings in a way that works best for the purpose of synthesizing novel utterances from novel speakers, similar to the target speaker's voice. We describe the metrics …
Graduate School of Culture Technology, KAIST（韩国科学技术院文化技术研究生院）
Singing voice separation (SVS) is a task that separates singing voice audio from its mixture with instrumental audio. Previous SVS studies have mainly employed the spectrogram masking method which requires a large dimensionality in predicting the binary masks. In addition, they focused on extracting a vocal stem that retains the wet sound with the reverberation effect. This result may hinder the reusability of the isolated singing voice. This paper addresses the issues by predicting mel-spectrogram of dry singing voices from the mixed audio as neural vocoder features and synthesizing the singi…
Singing voice conversion is converting the timbre in the source singing to the target speaker's voice while keeping singing content the same. However, singing data for target speaker is much more difficult to collect compared with normal speech data.In this paper, we introduce a singing voice conversion algorithm that is capable of generating high quality target speaker's singing using only his/her normal speech data. First, we manage to integrate the training and conversion process of speech and singing into one framework by unifying the features used in standard speech synthesis system and s…
Disentangling content and speaking style information is essential for zero-shot non-parallel voice conversion (VC). Our previous study investigated a novel framework with disentangled sequential variational autoencoder (DSVAE) as the backbone for information decomposition. We have demonstrated that simultaneous disentangling content embedding and speaker embedding from one utterance is feasible for zero-shot VC. In this study, we continue the direction by raising one concern about the prior distribution of content branch in the DSVAE baseline. We find the random initialized prior distribution …
STMS UMR9912, Ircam/CNRS/SU（STMS UMR9912，Ircam/CNRS/SU）；LTCI, Institut Polytechnique de Paris（巴黎理工学院 LTCI）
Informed source separation has recently gained renewed interest with the introduction of neural networks and the availability of large multitrack datasets containing both the mixture and the separated sources. These approaches use prior information about the target source to improve separation. Historically, Music Information Retrieval researchers have focused primarily on score-informed source separation, but more recent approaches explore lyrics-informed source separation. However, because of the lack of multitrack datasets with time-aligned lyrics, models use weak conditioning with non-alig…
College of Geophysics, Chengdu University of Technology（成都理工大学地球物理学院）；Changhong AI Lab (CHAIR), Sichuan Changhong Electronics Holding Group Co., Ltd.（四川长虹电子控股集团有限公司长虹人工智能实验室）
Suffering from limited singing voice corpus, existing singing voice synthesis (SVS) methods that build encoder-decoder neural networks to directly generate spectrogram could lead to out-of-tune issues during the inference phase. To attenuate these issues, this paper presents a novel acoustic model with independent pitch encoder and phoneme encoder, which disentangles the phoneme and pitch information from music score to fully utilize the corpus. Specifically, according to equal temperament theory, the pitch encoder is constrained by a pitch metric loss that maps distances between adjacent inpu…
Amazon Research（亚马逊研究院）；Warsaw University of Technology（华沙理工大学）
This work focuses on modelling a speaker's accent that does not have a dedicated text-to-speech (TTS) frontend, including a grapheme-to-phoneme (G2P) module. Prior work on modelling accents assumes a phonetic transcription is available for the target accent, which might not be the case for low-resource, regional accents. In our work, we propose an approach whereby we first augment the target accent data to sound like the donor voice via voice conversion, then train a multi-speaker multi-accent TTS model on the combination of recordings and synthetic data, to generate the donor's voice speaking…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure Speech（微软Azure语音）
Text to speech (TTS) is widely used to synthesize personal voice for a target speaker, where a well-trained source TTS model is fine-tuned with few paired adaptation data (speech and its transcripts) on this target speaker. However, in many scenarios, only untranscribed speech data is available for adaptation, which brings challenges to the previous TTS adaptation pipelines (e.g., AdaSpeech). In this paper, we develop AdaSpeech 2, an adaptive TTS system that only leverages untranscribed speech data for adaptation. Specifically, we introduce a mel-spectrogram encoder to a well-trained TTS model…
This paper proposes singing voice synthesis (SVS) based on frame-level sequence-to-sequence models considering vocal timing deviation. In SVS, it is essential to synchronize the timing of singing with temporal structures represented by scores, taking into account that there are differences between actual vocal timing and note start timing. In many SVS systems including our previous work, phoneme-level score features are converted into frame-level ones on the basis of phoneme boundaries obtained by external aligners to take into account vocal timing deviations. Therefore, the sound quality is a…
Macquarie University（麦考瑞大学）；Islamic Azad University（伊斯兰阿扎德大学）
In this paper, we propose a neural-based coding scheme in which an artificial neural network is exploited to automatically compress and decompress speech signals by a trainable approach. Having a two-stage training phase, the system can be fully specified to each speech frame and have robust performance across different speakers and wide range of spoken utterances. Indeed, Frame-based nonlinear predictive coding (FNPC) would code a frame in the procedure of training to predict the frame samples. The motivating objective is to analyze the system behavior in regenerating not only the envelope of…
Though significant progress has been made for speaker-dependent Video-to-Speech (VTS) synthesis, little attention is devoted to multi-speaker VTS that can map silent video to speech, while allowing flexible control of speaker identity, all in a single system. This paper proposes a novel multi-speaker VTS system based on cross-modal knowledge transfer from voice conversion (VC), where vector quantization with contrastive predictive coding (VQCPC) is used for the content encoder of VC to derive discrete phoneme-like acoustic units, which are transferred to a Lip-to-Index (Lip2Ind) network to inf…
In this paper, a text-to-rapping/singing system is introduced, which can be adapted to any speaker's voice. It utilizes a Tacotron-based multispeaker acoustic model trained on read-only speech data and which provides prosody control at the phoneme level. Dataset augmentation and additional prosody manipulation based on traditional DSP algorithms are also investigated. The neural TTS model is fine-tuned to an unseen speaker's limited recordings, allowing rapping/singing synthesis with the target's speaker voice. The detailed pipeline of the system is described, which includes the extraction of …
National University of Singapore（新加坡国立大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Singing voice conversion aims to convert singer's voice from source to target without changing singing content. Parallel training data is typically required for the training of singing voice conversion system, that is however not practical in real-life applications. Recent encoder-decoder structures, such as variational autoencoding Wasserstein generative adversarial network (VAW-GAN), provide an effective way to learn a mapping through non-parallel training data. In this paper, we propose a singing voice conversion framework that is based on VAW-GAN. We train an encoder to disentangle singer …
Snap Research, Snap Inc.（Snap公司Snap研究院）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Singing voice conversion is a task to convert a song sang by a source singer to the voice of a target singer. In this paper, we propose using a parallel data free, many-to-one voice conversion technique on singing voices. A phonetic posterior feature is first generated by decoding singing voices through a robust Automatic Speech Recognition Engine (ASR). Then, a trained Recurrent Neural Network (RNN) with a Deep Bidirectional Long Short Term Memory (DBLSTM) structure is used to model the mapping from person-independent content to the acoustic features of the target person. F0 and aperiodic are…
This paper presents a method for phoneme-level prosody control of F0 and duration on a multispeaker text-to-speech setup, which is based on prosodic clustering. An autoregressive attention-based model is used, incorporating multispeaker architecture modules in parallel to a prosody encoder. Several improvements over the basic single-speaker method are proposed that increase the prosodic control range and coverage. More specifically we employ data augmentation, F0 normalization, balanced clustering for duration, and speaker-independent prosodic clustering. These modifications enable fine-graine…
