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 176–200 of 1249 papers

Title	Date	Tasks	Status	Hype
Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis	Jun 8, 2019	Expressive Speech SynthesisSpeech Synthesis	CodeCode Available	1
KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset	Apr 17, 2021	Speech Synthesistext-to-speech	CodeCode Available	1
Dynamical Variational Autoencoders: A Comprehensive Review	Aug 28, 2020	3D Human DynamicsResynthesis	CodeCode Available	1
dMel: Speech Tokenization made Simple	Jul 22, 2024	DecoderLanguage Modeling	CodeCode Available	1
EdiTTS: Score-based Editing for Controllable Text-to-Speech	Oct 6, 2021	Speech SynthesisSpeech-to-Text	CodeCode Available	1
Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm	Oct 21, 2020	speaker-diarizationSpeaker Diarization	CodeCode Available	1
Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis	May 17, 2020	Lip ReadingLip to Speech Synthesis	CodeCode Available	1
Digital Voicing of Silent Speech	Oct 6, 2020	Electromyography (EMG)Speech Synthesis	CodeCode Available	1
Disentanglement in a GAN for Unconditional Speech Synthesis	Jul 4, 2023	DisentanglementGenerative Adversarial Network	CodeCode Available	1
Effective Deep Learning Models for Automatic Diacritization of Arabic Text	Nov 1, 2020	Arabic Text DiacritizationDecoder	CodeCode Available	1
EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech	Jun 28, 2023	Emotion RecognitionSpeech Synthesis	CodeCode Available	1
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech	Jun 8, 2020	Knowledge DistillationSpeech Synthesis	CodeCode Available	1
DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training	Jul 31, 2023	DenoisingExpressive Speech Synthesis	CodeCode Available	1
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis	Oct 8, 2019	CPUGPU	CodeCode Available	1
Bts-e: Audio deepfake detection using breathing-talking-silence encoder	May 5, 2023	Audio Deepfake DetectionDeepFake Detection	CodeCode Available	1
Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data	May 18, 2023	Speech EnhancementSpeech Synthesis	CodeCode Available	1
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models	May 21, 2025	Bayesian OptimizationSpeech Synthesis	CodeCode Available	1
Detection of Prosodic Boundaries in Speech Using Wav2Vec 2.0	Sep 29, 2022	SentenceSpeech Synthesis	CodeCode Available	1
Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet	Feb 4, 2025	Speech Synthesistext-to-speech	CodeCode Available	1
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme	Sep 28, 2021	Speech SynthesisVoice Conversion	CodeCode Available	1
Deep Learning Enabled Semantic Communications with Speech Recognition and Synthesis	May 9, 2022	Deep LearningSemantic Communication	CodeCode Available	1
Deep Learning Based Assessment of Synthetic Speech Naturalness	Apr 23, 2021	Deep LearningPrediction	CodeCode Available	1
Deep Speech Synthesis from Articulatory Representations	Sep 13, 2022	Speech Synthesis	CodeCode Available	1
ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation	May 29, 2023	Speech Synthesistext-to-speech	CodeCode Available	1
Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding	Aug 12, 2020	Speech Synthesistext-to-speech	CodeCode Available	1

Show:10 25 50

← PrevPage 8 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