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 76–100 of 1249 papers

Title	Date	Tasks	Status	Hype	Score
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis	Mar 25, 2022	Image GenerationSpeech Synthesis	CodeCode Available	2	5
A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet	Mar 28, 2019	Speech Synthesis	CodeCode Available	2	5
Generative Adversarial Training for Text-to-Speech Synthesis Based on Raw Phonetic Input and Explicit Prosody Modelling	Oct 14, 2023	Speech Synthesistext-to-speech	CodeCode Available	2	5
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis	Oct 12, 2020	CPUGPU	CodeCode Available	2	5
Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness	Apr 10, 2024	Speech Synthesistext-to-speech	CodeCode Available	2	5
Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis	Jun 8, 2019	Expressive Speech SynthesisSpeech Synthesis	CodeCode Available	1	5
EfficientNet-Absolute Zero for Continuous Speech Keyword Spotting	Dec 31, 2020	Keyword SpottingKeyword Spotting CSS	CodeCode Available	1	5
FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection	Oct 18, 2021	Speech SynthesisSynthetic Speech Detection	CodeCode Available	1	5
Effective Deep Learning Models for Automatic Diacritization of Arabic Text	Nov 1, 2020	Arabic Text DiacritizationDecoder	CodeCode Available	1	5
EdiTTS: Score-based Editing for Controllable Text-to-Speech	Oct 6, 2021	Speech SynthesisSpeech-to-Text	CodeCode Available	1	5
FonBund: A Library for Combining Cross-lingual Phonological Segment Data	May 1, 2018	Language ModelingLanguage Modelling	CodeCode Available	1	5
Dynamical Variational Autoencoders: A Comprehensive Review	Aug 28, 2020	3D Human DynamicsResynthesis	CodeCode Available	1	5
dMel: Speech Tokenization made Simple	Jul 22, 2024	DecoderLanguage Modeling	CodeCode Available	1	5
Generative Expressive Conversational Speech Synthesis	Jul 31, 2024	Speech Synthesis	CodeCode Available	1	5
Fine-grained style control in Transformer-based Text-to-speech Synthesis	Oct 12, 2021	Inductive BiasSpeech Synthesis	CodeCode Available	1	5
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis	May 12, 2020	Speech SynthesisStyle Transfer	CodeCode Available	1	5
From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint	May 10, 2020	Speaker VerificationSpeech Synthesis	CodeCode Available	1	5
Digital Voicing of Silent Speech	Oct 6, 2020	Electromyography (EMG)Speech Synthesis	CodeCode Available	1	5
DiffWave: A Versatile Diffusion Model for Audio Synthesis	Sep 21, 2020	Audio SynthesisDiversity	CodeCode Available	1	5
Disentanglement in a GAN for Unconditional Speech Synthesis	Jul 4, 2023	DisentanglementGenerative Adversarial Network	CodeCode Available	1	5
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme	Sep 28, 2021	Speech SynthesisVoice Conversion	CodeCode Available	1	5
Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data	May 18, 2023	Speech EnhancementSpeech Synthesis	CodeCode Available	1	5
DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding	Aug 15, 2023	Speech Synthesis	CodeCode Available	1	5
FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis	Oct 27, 2022	Speech Synthesistext-to-speech	CodeCode Available	1	5
Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet	Feb 4, 2025	Speech Synthesistext-to-speech	CodeCode Available	1	5

Show:10 25 50

← PrevPage 4 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