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 926–950 of 1249 papers

Title	Date	Tasks	Status	Hype
Replay Spoofing Countermeasure Using Autoencoder and Siamese Network on ASVspoof 2019 Challenge	Oct 29, 2019	Speaker VerificationSpeech Synthesis	—Unverified	0
Spoofing Speaker Verification Systems with Deep Multi-speaker Text-to-speech Synthesis	Oct 29, 2019	Speaker VerificationSpeech Synthesis	CodeCode Available	0
Effect of choice of probability distribution, randomness, and search methods for alignment modeling in sequence-to-sequence text-to-speech synthesis using hard alignment	Oct 28, 2019	Hard AttentionSpeech Synthesis	—Unverified	0
Transferring neural speech waveform synthesizers to musical instrument sounds generation	Oct 27, 2019	Audio GenerationAudio Synthesis	—Unverified	0
Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram	Oct 25, 2019	Generative Adversarial NetworkGPU	CodeCode Available	2
Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis	Oct 23, 2019	FormSpeech Synthesis	CodeCode Available	0
Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models	Oct 21, 2019	Data AugmentationNatural Language Understanding	CodeCode Available	2
The Theory behind Controllable Expressive Speech Synthesis: a Cross-disciplinary Approach	Oct 14, 2019	Expressive Speech SynthesisSociology	—Unverified	0
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis	Oct 8, 2019	CPUGPU	CodeCode Available	1
Semi-Supervised Generative Modeling for Controllable Speech Synthesis	Oct 3, 2019	Speech Synthesistext-to-speech	—Unverified	0
即時中文語音合成系統(Real-Time Mandarin Speech Synthesis System)	Oct 1, 2019	Speech Synthesis	—Unverified	0
應用文脈分析於中英夾雜語音合成系統(Linguistic Analysis for English/Mandarin Speech Synthesis System)	Oct 1, 2019	Speech Synthesis	—Unverified	0
Using NLG for speech synthesis of mathematical sentences	Oct 1, 2019	SentenceSpeech Synthesis	—Unverified	0
Attention Forcing for Sequence-to-sequence Model Training	Sep 26, 2019	Machine Translationmodel	—Unverified	0
High Fidelity Speech Synthesis with Adversarial Networks	Sep 25, 2019	Generative Adversarial NetworkSpeech Synthesis	CodeCode Available	0
Disentangling Speech and Non-Speech Components for Building Robust Acoustic Models from Found Data	Sep 25, 2019	speech-recognitionSpeech Recognition	CodeCode Available	0
Speech Recognition with Augmented Synthesized Speech	Sep 25, 2019	Data AugmentationDiversity	—Unverified	0
Modular Meta-Learning with Shrinkage	Sep 12, 2019	Image ClassificationMeta-Learning	—Unverified	0
Evaluating Long-form Text-to-Speech: Comparing the Ratings of Sentences and Paragraphs	Sep 9, 2019	FormSpeech Synthesis	—Unverified	0
DurIAN: Duration Informed Attention Network For Multimodal Synthesis	Sep 4, 2019	CPUSpeech Synthesis	CodeCode Available	0
Maximizing Mutual Information for Tacotron	Aug 30, 2019	AttributeSpeech Synthesis	CodeCode Available	0
Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis	Aug 27, 2019	Speech Synthesistext-to-speech	—Unverified	0
Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck	Aug 19, 2019	Image GenerationSpeech Synthesis	CodeCode Available	0
DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis	Jul 19, 2019	Speech Synthesis	—Unverified	0
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

Show:10 25 50

← PrevPage 38 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