Image de couverture de livre

Evaluation of preprocessing pipelines in the creation of in-the-wild TTS datasets

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Di Bernardo, Matías, Misley, Emmanuel, Correa, Ignacio, Iacovelli, Mateo García, Mellino, Simón, Barrios, Gala Lucía Gonzalez
Format:	Preprint
Publié:	2025
Sujets:	Audio and Speech Processing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ManaTTS Persian: a recipe for creating TTS datasets for lower resource languages
par: Qharabagh, Mahta Fetrat, et autres
Publié: (2024)

How Open is Open TTS? A Practical Evaluation of Open Source TTS Tools
par: Răgman, Teodora, et autres
Publié: (2026)

An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR
par: Ogun, Sewade, et autres
Publié: (2025)

Traceable TTS: Toward Watermark-Free TTS with Strong Traceability
par: Zhao, Yuxiang, et autres
Publié: (2025)

Scalable Controllable Accented TTS
par: Xinyuan, Henry Li, et autres
Publié: (2025)

Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech
par: Li, Zirui, et autres
Publié: (2025)

SponTTS: modeling and transferring spontaneous style for TTS
par: Li, Hanzhao, et autres
Publié: (2023)

Zero-Shot TTS With Enhanced Audio Prompts: Bsc Submission For The 2026 Wildspoof Challenge TTS Track
par: Giraldo, Jose, et autres
Publié: (2026)

E1 TTS: Simple and Fast Non-Autoregressive TTS
par: Liu, Zhijun, et autres
Publié: (2024)

T5Gemma-TTS Technical Report
par: Arata, Chihiro, et autres
Publié: (2026)

Low-Resource Self-Supervised Learning with SSL-Enhanced TTS
par: Hsu, Po-chun, et autres
Publié: (2023)

WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark
par: Ma, Linhan, et autres
Publié: (2024)

E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
par: Eskimez, Sefik Emre, et autres
Publié: (2024)

Reconstructing the Charlie Parker Omnibook using an audio-to-score automatic transcription pipeline
par: Riley, Xavier, et autres
Publié: (2024)

Natural Yet Challenging to Detect: Robust In-the-Wild TTS through EMA and Dual-Scoring Prompt Selection -- Submission for WildSpoof 2026 TTS Track
par: Sun, Renhe, et autres
Publié: (2026)

TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch
par: Song, Xingchen, et autres
Publié: (2024)

MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts
par: Xue, Heyang, et autres
Publié: (2025)

Towards Prosodically Informed Mizo TTS without Explicit Tone Markings
par: Mohanta, Abhijit, et autres
Publié: (2026)

Towards Flow-Matching-based TTS without Classifier-Free Guidance
par: Liang, Yuzhe, et autres
Publié: (2025)

Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech
par: Kim, Semin, et autres
Publié: (2026)

Spatio-temporal Latent Representations for the Analysis of Acoustic Scenes in-the-wild
par: Montero-Ramírez, Claudia, et autres
Publié: (2024)

KazEmoTTS: A Dataset for Kazakh Emotional Text-to-Speech Synthesis
par: Abilbekov, Adal, et autres
Publié: (2024)

Arabic TTS with FastPitch: Reproducible Baselines, Adversarial Training, and Oversmoothing Analysis
par: Nippert, Lars
Publié: (2025)

Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning
par: Ouyang, Zhicheng, et autres
Publié: (2026)

FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis
par: Meng, Qingliang, et autres
Publié: (2025)

T-Mimi: A Transformer-based Mimi Decoder for Real-Time On-Phone TTS
par: Wu, Haibin, et autres
Publié: (2026)

MELA-TTS: Joint transformer-diffusion model with representation alignment for speech synthesis
par: An, Keyu, et autres
Publié: (2025)

EE-TTS: Emphatic Expressive TTS with Linguistic Information
par: Zhong, Yi, et autres
Publié: (2023)

EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge
par: Manku, Ruskin Raj, et autres
Publié: (2025)

HiFiTTS-2: A Large-Scale High Bandwidth Speech Dataset
par: Langman, Ryan, et autres
Publié: (2025)

Measuring Prosody Diversity in Zero-Shot TTS: A New Metric, Benchmark, and Exploration
par: Yang, Yifan, et autres
Publié: (2025)

Accent-VITS:accent transfer for end-to-end TTS
par: Ma, Linhan, et autres
Publié: (2023)

A Dataset for Automatic Assessment of TTS Quality in Spanish
par: Welford, Alejandro Sosa, et autres
Publié: (2025)

Intelli-Z: Toward Intelligible Zero-Shot TTS
par: Jung, Sunghee, et autres
Publié: (2024)

Zero-shot Cross-lingual Voice Transfer for TTS
par: Biadsy, Fadi, et autres
Publié: (2024)

SelfTTS: cross-speaker style transfer through explicit embedding disentanglement and self-refinement using self-augmentation
par: Ueda, Lucas H., et autres
Publié: (2026)

Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump Diffusion
par: Ai, Jiabao, et autres
Publié: (2026)

Time-Layer Adaptive Alignment for Speaker Similarity in Flow-Matching Based Zero-Shot TTS
par: Li, Haoyu, et autres
Publié: (2025)

Exploring an Inter-Pausal Unit (IPU) based Approach for Indic End-to-End TTS Systems
par: Prakash, Anusha, et autres
Publié: (2024)

SP-MCQA: Evaluating Intelligibility of TTS Beyond the Word Level
par: Tee, Hitomi Jin Ling, et autres
Publié: (2025)