Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS. Specifically, we extract attention alignments from an encoder-decoder based teacher model for phoneme duration prediction, which is used by a length regulator to expand the source phoneme sequence to match the length of the target mel-spectrogram sequence for parallel mel-spectrogram generation. Experiments on the LJSpeech dataset show that our parallel model matches autoregressive models in terms of speech quality, nearly eliminates the problem of word skipping and repeating in particularly hard cases, and can adjust voice speed smoothly. Most importantly, compared with autoregressive Transformer TTS, our model speeds up mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x. Therefore, we call our model FastSpeech.

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which generates a mel spectrogram from text, conditioned on the speaker embedding; (3) an auto-regressive WaveNet-based vocoder that converts the mel spectrogram into a sequence of time domain waveform samples. We demonstrate that the proposed model is able to transfer the knowledge of speaker variability learned by the discriminatively-trained speaker encoder to the new task, and is able to synthesize natural speech from speakers that were not seen during training. We quantify the importance of training the speaker encoder on a large and diverse speaker set in order to obtain the best generalization performance. Finally, we show that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation.

In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its predecessor by modeling styles as a latent random variable through diffusion models to generate the most suitable style for the text without requiring reference speech, achieving efficient latent diffusion while benefiting from the diverse speech synthesis offered by diffusion models. Furthermore, we employ large pre-trained SLMs, such as WavLM, as discriminators with our novel differentiable duration modeling for end-to-end training, resulting in improved speech naturalness. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. Moreover, when trained on the LibriTTS dataset, our model outperforms previous publicly available models for zero-shot speaker adaptation. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs. The audio demos and source code are available at https://styletts2.github.io/.

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 opinion score, MOS) of a single speaker dataset indicates that our proposed method demonstrates similarity to human quality while generating 22.05 kHz high-fidelity audio 167.9 times faster than real-time on a single V100 GPU.

This paper presents HierSpeech, a high-quality end-to-end text-to-speech (TTS) system based on a hierarchical conditional variational autoencoder (VAE) utilizing self-supervised speech representations. Recently, single-stage TTS systems, which directly generate raw speech waveform from text, have been getting interest thanks to their ability in generating high-quality audio within a fully end-to-end training pipeline. However, there is still a room for improvement in the conventional TTS systems. Since it is challenging to infer both the linguistic and acoustic attributes from the text directly, missing the details of attributes, specifically linguistic information, is inevitable, which results in mispronunciation and over-smoothing problem in their synthetic speech. To address the aforementioned problem, we leverage self-supervised speech representations as additional linguistic representations to bridge an information gap between text and speech.

Style transfer for out-of-domain (OOD) speech synthesis aims to generate speech samples with unseen style (e.g., speaker identity, emotion, and prosody) derived from an acoustic reference, while facing the following challenges: 1) The highly dynamic style features in expressive voice are difficult to model and transfer; and 2) the TTS models should be robust enough to handle diverse OOD conditions that differ from the source data. This paper proposes GenerSpeech, a text-to-speech model towards high-fidelity zero-shot style transfer of OOD custom voice. GenerSpeech decomposes the speech variation into the style-agnostic and style-specific parts by introducing two components: 1) a multi-level style adaptor to efficiently model a large range of style conditions, including global speaker and emotion characteristics, and the local (utterance, phoneme, and word-level) fine-grained prosodic representations; and 2) a generalizable content adaptor with Mix-Style Layer Normalization to eliminate style information in the linguistic content representation and thus improve model generalization. Our evaluations on zero-shot style transfer demonstrate that GenerSpeech surpasses the state-of-the-art models in terms of audio quality and style similarity. The extension studies to adaptive style transfer further show that GenerSpeech performs robustly in the few-shot data setting. Audio samples are available at \url{https://GenerSpeech.github.io/}.

Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet have been proposed to generate mel-spectrograms from text in parallel. Despite the advantage, the parallel TTS models cannot be trained without guidance from autoregressive TTS models as their external aligners. In this work, we propose Glow-TTS, a flow-based generative model for parallel TTS that does not require any external aligner. By combining the properties of flows and dynamic programming, the proposed model searches for the most probable monotonic alignment between text and the latent representation of speech on its own. We demonstrate that enforcing hard monotonic alignments enables robust TTS, which generalizes to long utterances, and employing generative flows enables fast, diverse, and controllable speech synthesis.

Many real-world problems, including multi-speaker text-to-speech synthesis, can greatly benefit from the ability to meta-learn large models with only a few task-specific components. Updating only these task-specific modules then allows the model to be adapted to low-data tasks for as many steps as necessary without risking overfitting. Unfortunately, existing meta-learning methods either do not scale to long adaptation or else rely on handcrafted task-specific architectures. Here, we propose a meta-learning approach that obviates the need for this often sub-optimal hand-selection. In particular, we develop general techniques based on Bayesian shrinkage to automatically discover and learn both task-specific and general reusable modules. Empirically, we demonstrate that our method discovers a small set of meaningful task-specific modules and outperforms existing meta-learning approaches in domains like few-shot text-to-speech that have little task data and long adaptation horizons. We also show that existing meta-learning methods including MAML, iMAML, and Reptile emerge as special cases of our method.

Video dubbing aims to generate high-fidelity speech that is precisely temporally aligned with the visual content. Existing methods still suffer from limitations in speech naturalness and audio-visual synchronization, and are limited to monolingual settings. To address these challenges, we propose SyncVoice, a vision-augmented video dubbing framework built upon a pretrained text-to-speech (TTS) model. By fine-tuning the TTS model on audio-visual data, we achieve strong audiovisual consistency. We propose a Dual Speaker Encoder to effectively mitigate inter-language interference in cross-lingual speech synthesis and explore the application of video dubbing in video translation scenarios. Experimental results show that SyncVoice achieves high-fidelity speech generation with strong synchronization performance, demonstrating its potential in video dubbing tasks.

Synthesizing expressive Japanese character speech poses unique challenges due to pitch-accent sensitivity and stylistic variability. This paper empirically evaluates two open-source text-to-speech models--VITS and Style-BERT-VITS2 JP Extra (SBV2JE)--on in-domain, character-driven Japanese speech. Using three character-specific datasets, we evaluate models across naturalness (mean opinion and comparative mean opinion score), intelligibility (word error rate), and speaker consistency. SBV2JE matches human ground truth in naturalness (MOS 4.37 vs. 4.38), achieves lower WER, and shows slight preference in CMOS. Enhanced by pitch-accent controls and a WavLM-based discriminator, SBV2JE proves effective for applications like language learning and character dialogue generation, despite higher computational demands.