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 1226–1249 of 1249 papers

Title	Date	Tasks	Status
Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks	Sep 23, 2017	Speech Synthesistext-to-speech	CodeCode Available
Deep Voice 2: Multi-Speaker Neural Text-to-Speech	May 24, 2017	Speech Synthesistext-to-speech	CodeCode Available
STC Antispoofing Systems for the ASVspoof2019 Challenge	Apr 11, 2019	Speech SynthesisVoice Conversion	CodeCode Available
DeepTalk: Vocal Style Encoding for Speaker Recognition and Speech Synthesis	Dec 9, 2020	Speaker RecognitionSpeech Synthesis	CodeCode Available
Hierarchical Generative Modeling for Controllable Speech Synthesis	Oct 16, 2018	AttributeSpeech Synthesis	CodeCode Available
Learning pronunciation from a foreign language in speech synthesis networks	Oct 22, 2018	Speech Synthesis	CodeCode Available
Learning latent representations for style control and transfer in end-to-end speech synthesis	Dec 11, 2018	Speech SynthesisStyle Transfer	CodeCode Available
Deep Voice: Real-time Neural Text-to-Speech	Feb 25, 2017	Audio SynthesisBoundary Detection	CodeCode Available
Half-Truth: A Partially Fake Audio Detection Dataset	Apr 8, 2021	Speech Synthesis	CodeCode Available
Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition	Aug 17, 2024	Language ModelingLanguage Modelling	CodeCode Available
Language Technology Programme for Icelandic 2019-2023	Mar 20, 2020	Machine Translationspeech-recognition	CodeCode Available
WavLM model ensemble for audio deepfake detection	Aug 14, 2024	Audio Deepfake DetectionData Augmentation	CodeCode Available
The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection	Oct 6, 2022	Speech SynthesisSynthetic Speech Detection	CodeCode Available
Direct speech-to-speech translation with a sequence-to-sequence model	Apr 12, 2019	Speech SynthesisSpeech-to-Speech Translation	CodeCode Available
Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously	Jun 3, 2023	Speech Synthesis	CodeCode Available
Deep Residual Neural Networks for Audio Spoofing Detection	Jun 30, 2019	Speaker VerificationSpeech Synthesis	CodeCode Available
GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-spectrogram	Apr 8, 2019	Speech Synthesistext-to-speech	CodeCode Available
FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis	Jul 8, 2022	Lip to Speech SynthesisSpeech Synthesis	CodeCode Available
fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit	Sep 14, 2021	Speech Synthesistext-to-speech	CodeCode Available
DeepGesture: A conversational gesture synthesis system based on emotions and semantics	Jul 3, 2025	Gesture GenerationMotion Synthesis	CodeCode Available
A Critical Review of Recurrent Neural Networks for Sequence Learning	May 29, 2015	Handwriting RecognitionImage Captioning	CodeCode Available
Time out of Mind: Generating Rate of Speech conditioned on emotion and speaker	Jan 29, 2023	Speech Synthesistext-to-speech	CodeCode Available
JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis	Oct 28, 2017	BIG-bench Machine LearningSpeech Synthesis	CodeCode Available
JSSS: free Japanese speech corpus for summarization and simplification	Oct 5, 2020	FormSpeech Synthesis	CodeCode Available

Show:10 25 50

← PrevPage 50 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