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 501–525 of 1249 papers

Title	Date	Tasks	Status	Hype
Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks	Oct 26, 2022	Image CaptioningLanguage Modeling	—Unverified	0
Semi-Supervised Learning Based on Reference Model for Low-resource TTS	Oct 25, 2022	Speech Synthesistext-to-speech	—Unverified	0
A Data-Driven Investigation of Noise-Adaptive Utterance Generation with Linguistic Modification	Oct 19, 2022	Speech SynthesisText Generation	—Unverified	0
Simple and Effective Unsupervised Speech Translation	Oct 18, 2022	Domain AdaptationMachine Translation	—Unverified	0
Empirical Study Incorporating Linguistic Knowledge on Filled Pauses for Personalized Spontaneous Speech Synthesis	Oct 14, 2022	Speech SynthesisVoice Cloning	CodeCode Available	0
Transformer-Based Speech Synthesizer Attribution in an Open Set Scenario	Oct 14, 2022	AttributeMisinformation	—Unverified	0
GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models	Oct 11, 2022	DisentanglementGenerative Adversarial Network	CodeCode Available	1
An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era	Oct 6, 2022	Speech Synthesistext-to-speech	—Unverified	0
Fully Unsupervised Training of Few-shot Keyword Spotting	Oct 6, 2022	Keyword SpottingMetric Learning	—Unverified	0
The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection	Oct 6, 2022	Speech SynthesisSynthetic Speech Detection	CodeCode Available	0
Voice Spoofing Countermeasures: Taxonomy, State-of-the-art, experimental analysis of generalizability, open challenges, and the way forward	Oct 2, 2022	MisinformationSpeaker Verification	CodeCode Available	1
Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis	Oct 1, 2022	Speech Synthesistext-to-speech	—Unverified	0
Detection of Prosodic Boundaries in Speech Using Wav2Vec 2.0	Sep 29, 2022	SentenceSpeech Synthesis	CodeCode Available	1
ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Speed	Sep 23, 2022	Pitch controlSpeech Synthesis	CodeCode Available	1
EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models	Sep 22, 2022	Speech Synthesistext-to-speech	—Unverified	0
MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline	Sep 22, 2022	Speech Synthesistext-to-speech	CodeCode Available	1
Controllable Accented Text-to-Speech Synthesis	Sep 22, 2022	Speech Synthesistext-to-speech	—Unverified	0
An Initial study on Birdsong Re-synthesis Using Neural Vocoders	Sep 21, 2022	ResynthesisSpeech Synthesis	—Unverified	0
AutoLV: Automatic Lecture Video Generator	Sep 19, 2022	Speech SynthesisTalking Head Generation	—Unverified	0
Decoupled Pronunciation and Prosody Modeling in Meta-Learning-Based Multilingual Speech Synthesis	Sep 14, 2022	DecoderMeta-Learning	—Unverified	0
ConvNeXt Based Neural Network for Audio Anti-Spoofing	Sep 14, 2022	image-classificationImage Classification	CodeCode Available	0
Automated detection of pronunciation errors in non-native English speech employing deep learning	Sep 13, 2022	Speech Synthesis	—Unverified	0
Deep Speech Synthesis from Articulatory Representations	Sep 13, 2022	Speech Synthesis	CodeCode Available	1
Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers	Sep 5, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	0
Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild	Sep 1, 2022	Lip to Speech SynthesisSpeech Synthesis	—Unverified	0

Show:10 25 50

← PrevPage 21 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