SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 451–500 of 1249 papers

TitleStatusHype
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?—0
Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data—0
Enhancing Multilingual Speech Generation and Recognition Abilities in LLMs with Constructed Code-switched Data—0
Enhancing audio quality for expressive Neural Text-to-Speech—0
A Preliminary Study on Mandarin-Hakka neural machine translation using small-sized data—0
Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping—0
Facial Expression-Enhanced TTS: Combining Face Representation and Emotion Intensity for Adaptive Speech—0
FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning—0
FA-GAN: Artifacts-free and Phase-aware High-fidelity GAN-based Vocoder—0
A Flow-Based Neural Network for Time Domain Speech Enhancement—0
fairseq Sˆ2: A Scalable and Integrable Speech Synthesis Toolkit—0
Fast and Accurate Decision Trees for Natural Language Processing Tasks—0
A comparison of Vietnamese Statistical Parametric Speech Synthesis Systems—0
Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages—0
Fast Bootstrapping of Grapheme to Phoneme System for Under-resourced Languages - Application to the Iban Language—0
Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices—0
A Bengali Speech Synthesizer on Android OS—0
Energy-Based Models For Speech Synthesis—0
Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?—0
End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks—0
End-to-End Text-to-Speech using Latent Duration based on VQ-VAE—0
Fast Spectrogram Inversion using Multi-head Convolutional Neural Networks—0
A Preliminary Study on Deep Learning-based Chinese Text to Taiwanese Speech Synthesis System—0
CALLS: Japanese Empathetic Dialogue Speech Corpus of Complaint Handling and Attentive Listening in Customer Center—0
End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator—0
End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training—0
Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes—0
A Practical Guide to Logical Access Voice Presentation Attack Detection—0
Fine-grained Noise Control for Multispeaker Speech Synthesis—0
AffectEcho: Speaker Independent and Language-Agnostic Emotion and Affect Transfer for Speech Synthesis—0
Fine-grained Style Modeling, Transfer and Prediction in Text-to-Speech Synthesis via Phone-Level Content-Style Disentanglement—0
Fitting New Speakers Based on a Short Untranscribed Sample—0
End-to-End Binaural Speech Synthesis—0
Flavored Tacotron: Conditional Learning for Prosodic-linguistic Features—0
FleSpeech: Flexibly Controllable Speech Generation with Various Prompts—0
ELF: Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis—0
EM-TTS: Efficiently Trained Low-Resource Mongolian Lightweight Text-to-Speech—0
FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis—0
BU-TTS: An Open-Source, Bilingual Welsh-English, Text-to-Speech Corpus—0
Applying Syntaxx2013Prosody Mapping Hypothesis and Prosodic Well-Formedness Constraints to Neural Sequence-to-Sequence Speech Synthesis—0
Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesis—0
Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis—0
FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model—0
From `Solved Problems' to New Challenges: A Report on LDC Activities—0
Building Text-To-Speech Voices in the Cloud—0
From Flat to Feeling: A Feasibility and Impact Study on Dynamic Facial Emotions in AI-Generated Avatars—0
From Speaker Identification to Affective Analysis: A Multi-Step System for Analyzing Children's Stories—0
Empirical Analysis of Oral and Nasal Vowels of Konkani—0
Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement—0
Emphasized Accent Phrase Prediction from Text for Advertisement Text-To-Speech Synthesis—0
Show:102550
← PrevPage 10 of 25Next →
All datasetsLibriTTSNorth American EnglishLJSpeechMandarin ChineseBlizzard Challenge 2013

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PeriodWave-Turbo-LPESQ4.45—Unverified
2BigVGAN-v2PESQ4.36—Unverified
3EVA-GAN-bigPESQ4.35—Unverified
4PeriodWave + FreeUPESQ4.25—Unverified
5RFWavePESQ4.23—Unverified
6BigVSAN (w/ snakebeta)PESQ4.12—Unverified
7BigVSANPESQ4.12—Unverified
8EVA-GAN-basePESQ4.03—Unverified
9BigVGANPESQ4.03—Unverified
10VocosPESQ3.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Tacotron 2Mean Opinion Score4.53—Unverified
2WaveNet (Linguistic)Mean Opinion Score4.34—Unverified
3WaveNet (L+F)Mean Opinion Score4.21—Unverified
4TacotronMean Opinion Score4—Unverified
5HMM-driven concatenativeMean Opinion Score3.86—Unverified
6LSTM-RNN parametricMean Opinion Score3.67—Unverified
7meansMean Opinion Score0—Unverified
#ModelMetricClaimedVerifiedStatus
1BDDM vocoderMean Opinion Score4.48—Unverified
2DiffWave LARGEMean Opinion Score4.44—Unverified
3Neural HMMMean Opinion Score3.24—Unverified
4Neural HMM Ablation with 1 state per phoneMean Opinion Score2.68—Unverified
#ModelMetricClaimedVerifiedStatus
1WaveNet (L+F)Mean Opinion Score4.08—Unverified
2LSTM-RNN parametricMean Opinion Score3.79—Unverified
3HMM-driven concatenativeMean Opinion Score3.47—Unverified
#ModelMetricClaimedVerifiedStatus
1SampleRNN (2-tier)NLL1.39—Unverified
2SampleRNN (3-tier)NLL1.39—Unverified