Singing voice synthesis (SVS) technology has progressed rapidly in recent years. However, vocal ensemble synthesis has not yet been widely explored. In this work, we focus on unison singing, which is to have several singers singing the same melody together. Our goal is to understand what acoustic properties affect the naturalness of the synthesized unison singing. We utilize NNSVS, an SVS toolkit that allows us to manipulate individual acoustic features, including timing, f0, and spectrum features, in a fully data-driven manner to investigate their effect in unison singing synthesis. Through listening tests, it was shown that the fluctuation in timing and f0 is an important factor in synthesizing natural unison singing. Furthermore, we discovered the potential to generate unison singing using an SVS model trained only with a single singer dataset.

We propose a novel description-based controllable text-to-speech (TTS) method with cross-lingual control capability. To address the lack of audio-description paired data in the target language, we combine a TTS model trained on the target language with a description control model trained on another language, which maps input text descriptions to the conditional features of the TTS model. These two models share disentangled timbre and style representations based on self-supervised learning (SSL), allowing for disentangled voice control, such as controlling speaking styles while retaining the original timbre. Furthermore, because the SSL-based timbre and style representations are language-agnostic, combining the TTS and description control models while sharing the same embedding space effectively enables cross-lingual control of voice characteristics. Experiments on English and Japanese TTS demonstrate that our method achieves high naturalness and controllability for both languages, even though no Japanese audio-description pairs are used.

We propose PromptTTS++, a prompt-based text-to-speech (TTS) synthesis system that allows control over speaker identity using natural language descriptions. To control speaker identity within the prompt-based TTS framework, we introduce the concept of speaker prompt, which describes voice characteristics (e.g., gender-neutral, young, old, and muffled) designed to be approximately independent of speaking style. Since there is no large-scale dataset containing speaker prompts, we first construct a dataset based on the LibriTTS-R corpus with manually annotated speaker prompts. We then employ a diffusion-based acoustic model with mixture density networks to model diverse speaker factors in the training data. Unlike previous studies that rely on style prompts describing only a limited aspect of speaker individuality, such as pitch, speaking speed, and energy, our method utilizes an additional speaker prompt to effectively learn the mapping from natural language descriptions to the acoustic features of diverse speakers. Our subjective evaluation results show that the proposed method can better control speaker characteristics than the methods without the speaker prompt. Audio samples are available at https://reppy4620.github.io/demo.promptttspp/.

We propose a novel framework for electrolaryngeal speech intelligibility enhancement through the use of robust linguistic encoders. Pretraining and fine-tuning approaches have proven to work well in this task, but in most cases, various mismatches, such as the speech type mismatch (electrolaryngeal vs. typical) or a speaker mismatch between the datasets used in each stage, can deteriorate the conversion performance of this framework. To resolve this issue, we propose a linguistic encoder robust enough to project both EL and typical speech in the same latent space, while still being able to extract accurate linguistic information, creating a unified representation to reduce the speech type mismatch. Furthermore, we introduce HuBERT output features to the proposed framework for reducing the speaker mismatch, making it possible to effectively use a large-scale parallel dataset during pretraining. We show that compared to the conventional framework using mel-spectrogram input and output features, using the proposed framework enables the model to synthesize more intelligible and naturally sounding speech, as shown by a significant 16% improvement in character error rate and 0.83 improvement in naturalness score.

This paper proposes a multilingual, multi-speaker (MM) TTS system by using a voice conversion (VC)-based data augmentation method. Creating an MM-TTS model is challenging, owing to the difficulties of collecting polyglot data from multiple speakers. To address this problem, we adopt a cross-lingual, multi-speaker VC model trained with multiple speakers’ monolingual databases. As this model effectively transfers acoustic attributes while retaining the content information, it is possible to generate each speaker’s polyglot corpora. Subsequently, we design the MM-TTS model with variational autoencoder (VAE)-based posterior embeddings. It is to be noted that incorporating VC-augmented polyglot corpora into the TTS training process might degrade synthetic quality, since the corpora sometimes contain unwanted artifacts. To mitigate this issue, the VAE is trained to capture the acoustic dissimilarity between the recorded and VC-augmented datasets. Through the selective choice of the posterior embeddings obtained from the original recordings in the training set, the proposed model enables the generation of acoustically clearer voices.

With the advancements in singing voice generation and the growing presence of AI singers on media platforms, the inaugural Singing Voice Deepfake Detection (SVDD) Challenge aims to advance research in identifying AI-generated singing voices from authentic singers. This challenge features two tracks: a controlled setting track (CtrSVDD) and an in-the-wild scenario track (WildSVDD). The CtrSVDD track utilizes publicly available singing vocal data to generate deepfakes using state-of-the-art singing voice synthesis and conversion systems. Meanwhile, the WildSVDD track expands upon the existing SingFake dataset, which includes data sourced from popular user-generated content websites. For the CtrSVDD track, we received submissions from 47 teams, with 37 surpassing our baselines and the top team achieving a 1.65% equal error rate. For the WildSVDD track, we benchmarked the baselines. This paper reviews these results, discusses key findings, and outlines future directions for SVDD research.

This paper presents our systems (denoted as T13) for the singing voice conversion challenge (SVCC) 2023. For both in-domain and cross-domain English singing voice conversion (SVC) tasks (Task 1 and Task 2), we adopt a recognition-synthesis approach with self-supervised learning-based representation. To achieve data-efficient SVC with a limited amount of target singer/speaker’s data (150 to 160 utterances for SVCC 2023), we first train a diffusion-based any-to-any voice conversion model using publicly available large-scale 750 hours of speech and singing data. Then, we fine-tune the model for each target singer/speaker of Task 1 and Task 2. Large-scale listening tests conducted by SVCC 2023 show that our T13 system achieves competitive naturalness and speaker similarity for the harder cross-domain SVC (Task 2), which implies the generalization ability of our proposed method. Our objective evaluation results show that using large datasets is particularly beneficial for cross-domain SVC.

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 cascaded components, our method enjoys the full benefits of end-to-end optimization. Experimental results show that our model synthesized speech as natural as that synthesized by VITS, while achieving a real-time factor of 0.066 on an Intel Core i7 CPU, 4.1 times faster than VITS. Moreover, a smaller version of the model significantly outperformed a lightweight baseline model with respect to both naturalness and inference speed. Code and audio samples are available from https://github.com/MasayaKawamura/MB-iSTFT-VITS.

Several fully end-to-end text-to-speech (TTS) models have been proposed that have shown better performance compared to cascade models (i.e., training acoustic and vocoder models separately). However, they often generate unstable pitch contour with audible artifacts when the dataset contains emotional attributes, i.e., large diversity of pronunciation and prosody. To address this problem, we propose Period VITS, a novel end-to-end TTS model that incorporates an explicit periodicity generator. In the proposed method, we introduce a frame pitch predictor that predicts prosodic features, such as pitch and voicing flags, from the input text. From these features, the proposed periodicity generator produces a sample-level sinusoidal source that enables the waveform decoder to accurately reproduce the pitch. Finally, the entire model is jointly optimized in an end-to-end manner with variational inference and adversarial objectives. As a result, the decoder becomes capable of generating more stable, expressive, and natural output waveforms. The experimental results showed that the proposed model significantly outperforms baseline models in terms of naturalness, with improved pitch stability in the generated samples.

This paper describes the design of NNSVS, an open-source soft-ware for neural network-based singing voice synthesis research. NNSVS is inspired by Sinsy, an open-source pioneer in singing voice synthesis research, and provides many additional features such as multi-stream models, autoregressive fundamental frequency models, and neural vocoders. Furthermore, NNSVS provides extensive documentation and numerous scripts to build complete singing voice synthesis systems. Experimental results demonstrate that our best system significantly outperforms our reproduction of Sinsy and other baseline systems. The toolkit is available at https://github.com/nnsvs/nnsvs.

Neural audio super-resolution models are typically trained on low- and high-resolution audio signal pairs. Although these methods achieve highly accurate super-resolution if the acoustic characteristics of the input data are similar to those of the training data, challenges remain: the models suffer from quality degradation for out-of-domain data, and paired data are required for training. To address these problems, we propose Dual-CycleGAN, a high-quality audio super-resolution method that can utilize unpaired data based on two connected cycle consistent generative adversarial networks (CycleGAN). Our method decomposes the super-resolution method into domain adaptation and resampling processes to handle acoustic mismatch in the unpaired low- and high-resolution signals. The two processes are then jointly optimized within the CycleGAN framework. Experimental results verify that the proposed method significantly outperforms conventional methods when paired data are not available. Code and audio samples are available from https://chomeyama.github.io/DualCycleGAN-Demo/.

Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection.To solve this problem, existing noise-robust TTS methods are intended to use noisy speech corpora as training data.However, they only address either timeinvariant or time-variant noises.We propose a degradationrobust TTS method, which can be trained on speech corpora that contain both additive noises and environmental distortions.It jointly represents the time-variant additive noises with a framelevel encoder and the time-invariant environmental distortions with an utterance-level encoder.We also propose a regularization method to attain clean environmental embedding that is disentangled from the utterance-dependent information such as linguistic contents and speaker characteristics.Evaluation results show that our method achieved significantly higher-quality synthetic speech than previous methods in the condition including both additive noise and reverberation.

Recent advances in synthetic speech quality have enabled us to train text-to-speech (TTS) systems by using synthetic corpora. However, merely increasing the amount of synthetic data is not always advantageous for improving training efficiency. Our aim in this study is to selectively choose synthetic data that are beneficial to the training process. In the proposed method, we first adopt a variational autoencoder whose posterior distribution is utilized to extract latent features representing acoustic similarity between the recorded and synthetic corpora. By using those learned features, we then train a ranking support vector machine (RankSVM) that is well known for effectively ranking relative attributes among binary classes. By setting the recorded and synthetic ones as two opposite classes, RankSVM is used to determine how the synthesized speech is acoustically similar to the recorded data. Then, synthetic TTS data, whose distribution is close to the recorded data, are selected from large-scale synthetic corpora. By using these data for retraining the TTS model, the synthetic quality can be significantly improved. Objective and subjective evaluation results show the superiority of the proposed method over the conventional methods.

Data augmentation via voice conversion (VC) has been successfully applied to low-resource expressive text-to-speech (TTS) when only neutral data for the target speaker are available. Although the quality of VC is crucial for this approach, it is challenging to learn a stable VC model because the amount of data is limited in low-resource scenarios, and highly expressive speech has large acoustic variety. To address this issue, we propose a novel data augmentation method that combines pitch-shifting and VC techniques. Because pitch-shift data augmentation enables the coverage of a variety of pitch dynamics, it greatly stabilizes training for both VC and TTS models, even when only 1,000 utterances of the target speaker's neutral data are available. Subjective test results showed that a FastSpeech 2-based emotional TTS system with the proposed method improved naturalness and emotional similarity compared with conventional methods.

This paper proposes an effective emotional text-to-speech (TTS) system with a pre-trained language model (LM)-based emotion prediction method.Unlike conventional systems that require auxiliary inputs such as manually defined emotion classes, our system directly estimates emotion-related attributes from the input text.Specifically, we utilize generative pre-trained transformer (GPT)-3 to jointly predict both an emotion class and its strength in representing emotions' coarse and fine properties, respectively.Then, these attributes are combined in the emotional embedding space and used as conditional features of the TTS model for generating output speech signals.Consequently, the proposed system can produce emotional speech only from text without any auxiliary inputs.Furthermore, because the GPT-3 enables to capture emotional context among the consecutive sentences, the proposed method can effectively handle the paragraph-level generation of emotional speech.

In this paper, we propose a text-to-speech (TTS)-driven data augmentation method for improving the quality of a non-autoregressive (AR) TTS system. Recently proposed non-AR models, such as FastSpeech 2, have successfully achieved fast speech synthesis system. However, their quality is not satisfactory, especially when the amount of training data is insufficient. To address this problem, we propose an effective data augmentation method using a well-designed AR TTS system. In this method, large-scale synthetic corpora including text-waveform pairs with phoneme duration are generated by the AR TTS system, and then used to train the target non-AR model. Perceptual listening test results showed that the proposed method significantly improved the quality of the non-AR TTS system. In particular, we augmented five hours of a training database to 179 hours of a synthetic one. Using these databases, our TTS system consisting of a FastSpeech 2 acoustic model with a Parallel WaveGAN vocoder achieved a mean opinion score of 3.74, which is 40% higher than that achieved by the conventional method.

This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning method that can significantly improve the discriminator’s performance. Furthermore, the conventional discriminator is separated into two waveform discriminators for modeling voiced and unvoiced speech. As each discriminator learns the distinctive characteristics of the harmonic and noise components, respectively, the adversarial training process becomes more efficient, allowing the generator to produce more realistic speech waveforms. Subjective test results demonstrate the superiority of the proposed method over the conventional Parallel WaveGAN and WaveNet systems. In particular, our speaker-independently trained model within a FastSpeech 2 based text-to-speech framework achieves the mean opinion scores of 4.20, 4.18, 4.21, and 4.31 for four Japanese speakers, respectively.

We propose a novel phrase break prediction method that combines implicit features extracted from a pre-trained large language model, a.k.a BERT, and explicit features extracted from BiLSTM with linguistic features. In conventional BiLSTM based methods, word representations and/or sentence representations are used as independent components. The proposed method takes account of both representations to extract the latent semantics, which cannot be captured by previous methods. The objective evaluation results show that the proposed method obtains an absolute improvement of 3.2 points for the F1 score compared with BiLSTM-based conventional methods using linguistic features. Moreover, the perceptual listening test results verify that a TTS system that applied our proposed method achieved a mean opinion score of 4.39 in prosody naturalness, which is highly competitive with the score of 4.37 for synthesized speech with ground-truth phrase breaks.

This paper proposes a spectral-domain perceptual weighting technique for Parallel WaveGAN-based text-to-speech (TTS) systems. The recently proposed Parallel WaveGAN vocoder successfully generates waveform sequences using a fast non-autoregressive WaveNet model. By employing multi-resolution short-time Fourier transform (MR-STFT) criteria with a generative adversarial network, the light-weight convolutional networks can be effectively trained without any distillation process. To further improve the vocoding performance, we propose the application of frequency-dependent weighting to the MR-STFT loss function. The proposed method penalizes perceptually-sensitive errors in the frequency domain; thus, the model is optimized toward reducing auditory noise in the synthesized speech. Subjective listening test results demonstrate that our proposed method achieves 4.21 and 4.26 TTS mean opinion scores for female and male Korean speakers, respectively.

This paper introduces a new end-to-end text-to-speech (E2E-TTS) toolkit named ESPnet-TTS, which is an extension of the open-source speech processing toolkit ESPnet. The toolkit supports state-of- the-art E2E-TTS models, including Tacotron 2, Transformer TTS, and FastSpeech, and also provides recipes inspired by the Kaldi automatic speech recognition (ASR) toolkit. The recipes are based on the design unified with the ESPnet ASR recipe, providing high reproducibility. The toolkit also provides pre-trained models and samples of all of the recipes so that users can use it as a baseline. Furthermore, the unified design enables the integration of ASR functions with TTS, e.g., ASR-based objective evaluation and semi- supervised learning with both ASR and TTS models. This paper describes the design of the toolkit and experimental evaluation in comparison with other toolkits. The experimental results show that our models can achieve state-of-the-art performance comparable to the other latest toolkits, resulting in a mean opinion score (MOS) of 4.25 on the LJSpeech dataset. The toolkit is publicly available at https://github.com/espnet/espnet.

In this paper, we propose an improved LPCNet vocoder using a linear prediction (LP)-structured mixture density network (MDN). The recently proposed LPCNet vocoder has successfully achieved high-quality and lightweight speech synthesis systems by combining a vocal tract LP filter with a WaveRNN-based vocal source (i.e., excitation) generator. However, the quality of synthesized speech is often unstable because the vocal source component is insufficiently represented by the μ-law quantization method, and the model is trained without considering the entire speech production mechanism. To address this problem, we first introduce LP-MDN, which enables the autoregressive neural vocoder to structurally represent the interactions between the vocal tract and vocal source components. Then, we propose to incorporate the LP-MDN to the LPCNet vocoder by replacing the conventional discretized output with continuous density distribution. The experimental results verify that the proposed system provides high quality synthetic speech by achieving a mean opinion score of 4.41 within a text-to-speech framework.

Recently, end-to-end text-to-speech (TTS) models have achieved a remarkable performance, however, requiring a large amount of paired text and speech data for training. On the other hand, we can easily collect unpaired dozen minutes of speech recordings for a target speaker without corresponding text data. To make use of such accessible data, the proposed method leverages the recent great success of state-of-the-art end-to-end automatic speech recognition (ASR) systems and obtains corresponding transcriptions from pretrained ASR models. Although these models could only provide text output instead of intermediate linguistic features like phonemes, end-to-end TTS can be well trained with such raw text data directly. Thus, the proposed method can greatly simplify a speaker adaptation pipeline by consistently employing end-to-end ASR/TTS ecosystems. The experimental results show that our proposed method achieved comparable performance to a paired data adaptation method in terms of subjective speaker similarity and objective cepstral distance measures.

We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network. In the proposed method, a non-autoregressive WaveNet is trained by jointly optimizing multi-resolution spectrogram and adversarial loss functions, which can effectively capture the time-frequency distribution of the realistic speech waveform. As our method does not require density distillation used in the conventional teacher-student framework, the entire model can be easily trained. Furthermore, our model is able to generate high-fidelity speech even with its compact architecture. In particular, the proposed Parallel WaveGAN has only 1.44 M parameters and can generate 24 kHz speech waveform 28.68 times faster than real-time on a single GPU environment. Perceptual listening test results verify that our proposed method achieves 4.16 mean opinion score within a Transformer-based text-to-speech framework, which is comparative to the best distillation-based Parallel WaveNet system.

This paper proposes a modeling-by-generation (MbG) excitation vocoder for a neural text-to-speech (TTS) system. Recently proposed neural excitation vocoders can realize qualified waveform generation by combining a vocal tract filter with a WaveNet-based glottal excitation generator. However, when these vocoders are used in a TTS system, the quality of synthesized speech is often degraded owing to a mismatch between training and synthesis steps. Specifically, the vocoder is separately trained from an acoustic model front-end. Therefore, estimation errors of the acoustic model are inevitably boosted throughout the synthesis process of the vocoder back-end. To address this problem, we propose to incorporate an MbG structure into the vocoder's training process. In the proposed method, the excitation signal is extracted by the acoustic model's generated spectral parameters, and the neural vocoder is then optimized not only to learn the target excitation's distribution but also to compensate for the estimation errors occurring from the acoustic model. Furthermore, as the generated spectral parameters are shared in the training and synthesis steps, their mismatch conditions can be reduced effectively. The experimental results verify that the proposed system provides high-quality synthetic speech by achieving a mean opinion score of 4.57 within the TTS framework.

Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence model called Transformer, which achieves state-of-the-art performance in neural machine translation and other natural language processing applications. We undertook intensive studies in which we experimentally compared and analyzed Transformer and conventional recurrent neural networks (RNN) in a total of 15 ASR, one multilingual ASR, one ST, and two TTS benchmarks. Our experiments revealed various training tips and significant performance benefits obtained with Transformer for each task including the surprising superiority of Transformer in 13/15 ASR benchmarks in comparison with RNN. We are preparing to release Kaldi-style reproducible recipes using open source and publicly available datasets for all the ASR, ST, and TTS tasks for the community to succeed our exciting outcomes.

This paper proposes an effective probability density distillation (PDD) algorithm for WaveNet-based parallel waveform generation (PWG) systems.Recently proposed teacher-student frameworks in the PWG system have successfully achieved a realtime generation of speech signals.However, the difficulties optimizing the PDD criteria without auxiliary losses result in quality degradation of synthesized speech.To generate more natural speech signals within the teacher-student framework, we propose a novel optimization criterion based on generative adversarial networks (GANs).In the proposed method, the inverse autoregressive flow-based student model is incorporated as a generator in the GAN framework, and jointly optimized by the PDD mechanism with the proposed adversarial learning method.As this process encourages the student to model the distribution of realistic speech waveform, the perceptual quality of the synthesized speech becomes much more natural.Our experimental results verify that the PWG systems with the proposed method outperform both those using conventional approaches, and also autoregressive generation systems with a well-trained teacher WaveNet.

In this paper, we present a robust on-line algorithm for real-time audio-to-score alignment based on a delayed decision and anticipation framework. We employ Segmental Conditional Random Fields and Linear Dynamical System to model musical performance. The combination of these models allows an efficient iterative decoding of score position and tempo. The combined advantages of our approach are the delayed-decision Viterbi algorithm which utilizes future information to determine past score position with high reliability, thus improving alignment accuracy, and the fact that the future position can be anticipated using an adaptively estimated tempo. Experiments using classical music and jazz databases demonstrate the validity of our approach.

Modern medicine generates huge amounts of sensitive data. Data mining and knowledge discovery systems can be used to extract useful information/knowledge in order to to improve future diagnoses and reduce costs. On the other hand, when analysing data, the most recent methods, that extract the most accurate knowledge and decision models, should be used. This can be established with a service enabling quick access to newly developed methods. In this paper, a service for doing this, named IFSIMS (Internet Framework Service for Intelligent Medical Systems), is presented.

Dynamic evidence-based medicine (DEBM) is defined as the process of finding evidence about the care of individual patients automatically and dynamically in those cases when we cannot rely on any literature or guidelines. In this paper, we develop a framework for DEBM using data mining technologies that make it possible to automatically analyze huge clinical databases and to discover patterns behind them. We define the requirements of a data mining system for DEBM. The following functions are required of the system: (1) support for clinical decision making, and (2) discovery of rare patterns which human beings can hardly find. In order to support clinical decision making, rule discovery methods such as association rule mining are applied to this framework. We adopt a post-analysis approach using a rule base and queries. The discovered rules are collected into a rule base for further analysis. By submitting queries to the rule base, users can obtain keys to evidence for making decisions about clinical care. We preliminarily implement a prototype of a rule base and a post-analysis tool based on our framework. This tool can assist users in analyzing the discovered rules.

Searching for new rules and new knowledge in problem areas, where very little or almost none previous knowledge is present, can be a very long and demanding process. In our research we addressed the problem of finding new knowledge in the form of rules in the diabetes database using a combination of decision trees and association rules. The first question we wanted to answer was, if there are significant differences in sets of rules both approaches produce, and how rules, produced by decision trees behave, after being a subject of filtering and reduction, normally used in association rule approaches. In order to accomplish that, we had to make some modifications to both the decision tree approach and association rule approach. From the first results we can conclude, that the sets of rules, built by decision trees are much smaller than the sets created by association rules. We could also establish, that filtering and reduction did not effect the rules derived from decision trees in the same scale as association rules.