Speech Synthesis

Speech synthesis is the task of generating speech from some other modality like text, lip movements etc.

Please note that the leaderboards here are not really comparable between studies - as they use mean opinion score as a metric and collect different samples from Amazon Mechnical Turk.

( Image credit: WaveNet: A generative model for raw audio )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 26–50 of 1249 papers

Title	Date	Tasks	Status	Hype
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning	Jul 9, 2019	Speech Synthesistext-to-speech	CodeCode Available	3
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation	Jun 15, 2021	Speech Synthesistext-to-speech	CodeCode Available	3
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model	Aug 30, 2024	Audio CompressionAudio Generation	CodeCode Available	3
Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model	May 11, 2022	Packet Loss ConcealmentSpeech Enhancement	CodeCode Available	3
FlashSpeech: Efficient Zero-Shot Speech Synthesis	Apr 23, 2024	RhythmSpeech Synthesis	CodeCode Available	3
Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet	Feb 22, 2022	Speech Synthesis	CodeCode Available	3
PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation	Aug 14, 2024	Speech Synthesistext-to-speech	CodeCode Available	3
End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation	Feb 23, 2022	Speech Synthesis	CodeCode Available	3
Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization	Aug 15, 2024	Speech Synthesis	CodeCode Available	3
ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech	Jul 13, 2022	DenoisingGPU	CodeCode Available	3
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers	Apr 18, 2023	In-Context LearningSpeech Synthesis	CodeCode Available	2
Conditional Diffusion Probabilistic Model for Speech Enhancement	Feb 10, 2022	modelSpeech Enhancement	CodeCode Available	2
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model	May 11, 2023	DenoisingGPU	CodeCode Available	2
CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models	Mar 31, 2024	DenoisingSpeech Synthesis	CodeCode Available	2
PodAgent: A Comprehensive Framework for Podcast Generation	Mar 1, 2025	Audio GenerationSpeech Synthesis	CodeCode Available	2
Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness	Apr 10, 2024	Speech Synthesistext-to-speech	CodeCode Available	2
LPCNet: Improving Neural Speech Synthesis Through Linear Prediction	Oct 28, 2018	PredictionSpeech Synthesis	CodeCode Available	2
BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network	Sep 6, 2023	Generative Adversarial NetworkSpeech Synthesis	CodeCode Available	2
A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech	Feb 8, 2023	Code GenerationDiversity	CodeCode Available	2
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis	Mar 25, 2022	Image GenerationSpeech Synthesis	CodeCode Available	2
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform	Mar 4, 2022	Speech Synthesistext-to-speech	CodeCode Available	2
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT	Oct 7, 2023	Audio captioningAutomatic Speech Recognition	CodeCode Available	2
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis	Oct 12, 2020	CPUGPU	CodeCode Available	2
HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform	Sep 18, 2023	Speech Synthesis	CodeCode Available	2
Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows	Mar 3, 2022	Speech Synthesistext-to-speech	CodeCode Available	2

Show:10 25 50

← PrevPage 2 of 50Next →

All datasets LibriTTS North American English LJSpeech Mandarin Chinese Blizzard Challenge 2013

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	PeriodWave-Turbo-L	PESQ	4.45	—	Unverified
2	BigVGAN-v2	PESQ	4.36	—	Unverified
3	EVA-GAN-big	PESQ	4.35	—	Unverified
4	PeriodWave + FreeU	PESQ	4.25	—	Unverified
5	RFWave	PESQ	4.23	—	Unverified
6	BigVSAN (w/ snakebeta)	PESQ	4.12	—	Unverified
7	BigVSAN	PESQ	4.12	—	Unverified
8	EVA-GAN-base	PESQ	4.03	—	Unverified
9	BigVGAN	PESQ	4.03	—	Unverified
10	Vocos	PESQ	3.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Tacotron 2	Mean Opinion Score	4.53	—	Unverified
2	WaveNet (Linguistic)	Mean Opinion Score	4.34	—	Unverified
3	WaveNet (L+F)	Mean Opinion Score	4.21	—	Unverified
4	Tacotron	Mean Opinion Score	4	—	Unverified
5	HMM-driven concatenative	Mean Opinion Score	3.86	—	Unverified
6	LSTM-RNN parametric	Mean Opinion Score	3.67	—	Unverified
7	means	Mean Opinion Score	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BDDM vocoder	Mean Opinion Score	4.48	—	Unverified
2	DiffWave LARGE	Mean Opinion Score	4.44	—	Unverified
3	Neural HMM	Mean Opinion Score	3.24	—	Unverified
4	Neural HMM Ablation with 1 state per phone	Mean Opinion Score	2.68	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	WaveNet (L+F)	Mean Opinion Score	4.08	—	Unverified
2	LSTM-RNN parametric	Mean Opinion Score	3.79	—	Unverified
3	HMM-driven concatenative	Mean Opinion Score	3.47	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SampleRNN (2-tier)	NLL	1.39	—	Unverified
2	SampleRNN (3-tier)	NLL	1.39	—	Unverified