No article text was recorded for this version.
non-autoregressive speech synthesis
Version 1 of 1270 papers326 conceptsfrozen 2026-10-04
Papers in this version
- Blog: FPETS : Fully Parallel End-to-End Text-to-Speech System
- Blog: Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
- Blog: End-to-end Adversarial Text-to-Speech
- Blog: High Fidelity Speech Synthesis with Adversarial Networks
- Blog: E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition
- Blog: SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet
- Blog: FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
- Blog: ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations
- Blog: FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation
- Blog: FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation
- Blog: Tell What You Hear From What You See -- Video to Audio Generation Through Text
- Blog: End-to-End Adversarial Text-to-Speech
- Blog: MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline
- Blog: Misclassification-driven Fingerprinting for DNNs Using Frequency-aware GANs
- Blog: OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning
- Blog: SING: Symbol-to-Instrument Neural Generator
- Blog: N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement
- Blog: Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
- Blog: High Fidelity Speech Synthesis with Adversarial Networks
- Blog: Transformer-S2A: Robust and Efficient Speech-to-Animation
- Blog: Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition
- Blog: fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
- Blog: TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation
- Blog: SpecMaskGIT: Masked Generative Modeling of Audio Spectrograms for Efficient Audio Synthesis and Beyond
- Blog: TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation
- Blog: Real-Time End-to-End Monaural Multi-Speaker Speech Recognition
- Blog: TalkNet: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis
- Blog: VoiceNoNG: Robust High-Quality Speech Editing Model without Hallucinations
- Blog: Joint Modeling of Multi-Sample and Subband Signals for Fast Neural Vocoding on CPU
- Blog: Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs
- Blog: MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
- Blog: Efficient Non-Autoregressive GAN Voice Conversion using VQWav2vec Features and Dynamic Convolution
- Blog: Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters
- Blog: Fast Spectrogram Inversion Using Multi-Head Convolutional Neural Networks
- Blog: OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis
- Blog: A Survey on Neural Speech Synthesis
- Blog: Lip to Speech Synthesis with Visual Context Attentional GAN
- Blog: Adversarial Auto-Encoding for Packet Loss Concealment
- Blog: FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis
- Blog: FloWaveNet : A Generative Flow for Raw Audio
- Blog: From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation
- Blog: MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech
- Blog: ControlSpeech: Towards Simultaneous Zero-shot Speaker Cloning and Zero-shot Language Style Control With Decoupled Codec
- Blog: DelightfulTTS 2: End-to-End Speech Synthesis with Adversarial Vector-Quantized Auto-Encoders
- Blog: OpenVoice: Versatile Instant Voice Cloning
- Blog: Fast Spectrogram Inversion using Multi-head Convolutional Neural Networks
- Blog: Integrating Discrete Word-Level Style Variations into Non-Autoregressive Acoustic Models for Speech Synthesis
- Blog: SC-GlowTTS: An Efficient Zero-Shot Multi-Speaker Text-To-Speech Model
- Blog: A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation
- Blog: Review of end-to-end speech synthesis technology based on deep learning
- Blog: Preserving Speaker Information in Direct Speech-to-Speech Translation with Non-Autoregressive Generation and Pretraining
- Blog: Non-Autoregressive End-to-End TTS with Coarse-to-Fine Decoding
- Blog: Self-Attention Linguistic-Acoustic Decoder
- Blog: EdenTTS: A Simple and Efficient Parallel Text-to-speech Architecture with Collaborative Duration-alignment Learning
- Blog: Sa-Paraformer: Non-Autoregressive End-To-End Speaker-Attributed ASR
- Blog: DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognition
- Blog: CTC-based Non-autoregressive Textless Speech-to-Speech Translation
- Blog: Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition
- Blog: Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings
- Blog: Mobile PresenTra: NICT fast neural text-to-speech system on smartphones with incremental inference of MS-FC-HiFi-GAN for law-latency synthesis
Showing 60 of 270 papers.
History & citation
Current · Permanent link
- Parallel Speech Generation for Real-Time Applications merged into this direction (75% overlap)
- Bidirectional Context for Efficient Non-Autoregressive Audio Synthesis merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_non_autoregressive_speech_synthesis_10cfb2af,
title = {non-autoregressive speech synthesis},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-autoregressive-speech-synthesis/rdr_10cfb2afaa5c4d3897fd27f85e155f1b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_non_autoregressive_speech_synthesis_10cfb2af_v1,
title = {non-autoregressive speech synthesis},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-autoregressive-speech-synthesis/rdr_10cfb2afaa5c4d3897fd27f85e155f1b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}