mlsanityData to 14 Oct 2026

Text-To-Speech Synthesis In The Wild

arXiv 2409.08711 ↗First posted 13 Sep 2024eess.AS cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Traditional Text-to-Speech (TTS) systems rely on studio-quality speech recorded in controlled settings.a Recently, an effort known as noisy-TTS training has emerged, aiming to utilize in-the-wild data. However, the lack of dedicated datasets has been a significant limitation. We introduce the TTS In the Wild (TITW) dataset, which is publicly available, created through a fully automated pipeline applied to the VoxCeleb1 dataset. It comprises two training sets: TITW-Hard, derived from the transcription, segmentation, and selection of raw VoxCeleb1 data, and TITW-Easy, which incorporates additional enhancement and data selection based on DNSMOS. State-of-the-art TTS models achieve over 3.0 UTMOS score with TITW-Easy, while TITW-Hard remains difficult showing UTMOS below 2.8.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

27 of 43 references.

References · 27

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  3. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  4. 2017VoxCeleb: a large-scale speaker identification datasetcited by 732
  5. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
  6. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  7. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 476
  8. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 447
  9. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 390
  10. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  11. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 340
  12. 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 326
15 more
  1. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 241
  2. 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizerscited by 235
  3. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  4. 2020Real Time Speech Enhancement in the Waveform Domaincited by 186
  5. 2023Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervisioncited by 169
  6. 2023UniAudio: An Audio Foundation Model Toward Universal Audio Generationcited by 127
  7. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 91
  8. 2023SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Modelscited by 87
  9. 2024OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformercited by 74
  10. 2024CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speechcited by 37
  11. 2023A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speechcited by 22
  12. 2023Warning: Humans Cannot Reliably Detect Speech Deepfakescited by 20
  13. 2022SASV 2022: The First Spoofing-Aware Speaker Verification Challengecited by 19
  14. 2020DenoiSpeech: Denoising Text to Speech with Frame-Level Noise Modelingcited by 14
  15. 2024FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocodercited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 3.

6 papers.

  1. 2024SpoofCeleb: Speech Deepfake Detection and SASV In The Wildcited by 22
  2. 2026Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codeccited by 2
  3. 2025WildSpoof Challenge Evaluation Plancited by 1
  4. 2025Training Flow Matching Models with Reliable Labels via Self-Purificationcited by 1
  5. 2026Alethia: A Foundational Encoder for Voice Deepfakescited by 1
  6. 2026Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio Infillingcited by 0