Speech Synthesis

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

22 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

15 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 366 papers with code (1,249 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• WaveNet: A Generative Model for Raw Audio
  12 Sep 2016 62 repositories listed Syntology ran 41 of 103 samples · 62 unverified · 25 pointer-only (licence)
  This paper introduces WaveNet, a deep neural network for generating raw audio waveforms.
• FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
  8 Jun 2020 37 repositories listed Syntology ran 73 of 119 samples · 46 unverified · 33 pointer-only (licence)
  In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the…
• Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
  16 Dec 2017 33 repositories listed Syntology ran 7 of 7 samples · 0 unverified · 2 pointer-only (licence)
  This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text.
• Tacotron: Towards End-to-End Speech Synthesis
  29 Mar 2017 30 repositories listed Syntology ran 7 of 25 samples · 18 unverified · 6 pointer-only (licence)
  A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module.
• FastSpeech: Fast, Robust and Controllable Text to Speech
  22 May 2019 22 repositories listed Syntology ran 3 of 11 samples · 8 unverified · 3 pointer-only (licence)
  In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS.
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
  8 Oct 2019 21 repositories listed Syntology ran 5 of 7 samples · 2 unverified · 1 pointer-only (licence)
  In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques.
• Efficient Neural Audio Synthesis
  23 Feb 2018 16 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 1 pointer-only (licence)
  The small number of weights in a Sparse WaveRNN makes it possible to sample high-fidelity audio on a mobile CPU in real time.
• Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
  25 Oct 2019 12 repositories listed Syntology ran 0 of 20 samples · 20 unverified · 1 pointer-only (licence)
  We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network.
• HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
  12 Oct 2020 11 repositories listed Syntology ran 17 of 25 samples · 8 unverified · 3 pointer-only (licence)
  Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms.
• DiffWave: A Versatile Diffusion Model for Audio Synthesis
  21 Sep 2020 11 repositories listed Syntology ran 20 of 33 samples · 13 unverified
  In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation.
• Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
  12 Jun 2018 11 repositories listed
  Clone a voice in 5 seconds to generate arbitrary speech in real-time
• Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
  23 Mar 2018 11 repositories listed Syntology ran 6 of 21 samples · 15 unverified · 7 pointer-only (licence)
  In this work, we propose "global style tokens" (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system.
• UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
  15 Jun 2021 9 repositories listed Syntology ran 8 of 12 samples · 4 unverified · 1 pointer-only (licence)
  Using full-band mel-spectrograms as input, we expect to generate high-resolution signals by adding a discriminator that employs spectrograms of multiple resolutions as the input.
• Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
  5 Jan 2023 7 repositories listed Syntology ran 6 of 6 samples · 0 unverified
  In addition, we find Vall-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis.
• WaveGrad: Estimating Gradients for Waveform Generation
  2 Sep 2020 7 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 1 pointer-only (licence)
  This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density.
• Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
  20 Oct 2017 7 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system.
• SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
  14 Oct 2021 6 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for…
• Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
  13 May 2021 6 repositories listed Syntology ran 9 of 18 samples · 9 unverified · 1 pointer-only (licence)
  Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these…
• DurIAN: Duration Informed Attention Network For Multimodal Synthesis
  4 Sep 2019 6 repositories listed
  In this paper, we present a generic and robust multimodal synthesis system that produces highly natural speech and facial expression simultaneously.
• Neural Speech Synthesis with Transformer Network
  19 Sep 2018 6 repositories listed
  Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2)…
• Neural Autoregressive Flows
  3 Apr 2018 6 repositories listed Syntology ran 3 of 8 samples · 5 unverified · 2 pointer-only (licence)
  Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art…
• BigVGAN: A Universal Neural Vocoder with Large-Scale Training
  9 Jun 2022 5 repositories listed Syntology ran 8 of 17 samples · 9 unverified · 1 pointer-only (licence)
  Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous…
• MelNet: A Generative Model for Audio in the Frequency Domain
  4 Jun 2019 5 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps.
• Exploring Transfer Learning for Low Resource Emotional TTS
  14 Jan 2019 5 repositories listed
  During the last few years, spoken language technologies have known a big improvement thanks to Deep Learning.
• ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
  19 Jul 2018 5 repositories listed Syntology ran 1 of 13 samples · 12 unverified
  In this work, we propose a new solution for parallel wave generation by WaveNet.
• Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks
  23 Sep 2017 5 repositories listed
  In the proposed framework incorporating the GANs, the discriminator is trained to distinguish natural and generated speech parameters, while the acoustic models are trained to minimize the weighted sum of the…
• Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis
  13 Jul 2024 4 repositories listed
  It is too early to conclude that Mamba is a better alternative to transformers for speech before comparing Mamba with transformers in terms of both performance and efficiency in multiple speech-related tasks.
• Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
  1 Jun 2023 4 repositories listed Syntology ran 5 of 16 samples · 11 unverified
  Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain.
• Scaling Speech Technology to 1,000+ Languages
  22 May 2023 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  Expanding the language coverage of speech technology has the potential to improve access to information for many more people.
• ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech
  13 Jul 2022 4 repositories listed Syntology ran 2 of 6 samples · 4 unverified
  Through the preliminary study on diffusion model parameterization, we find that previous gradient-based TTS models require hundreds or thousands of iterations to guarantee high sample quality, which poses a challenge…

Syntology lines on 24 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.