mlsanityData to 14 Oct 2026

Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings

arXiv 1910.10838 ↗First posted 23 Oct 2019eess.AScited by 73

Not on the map. Why?

Abstract (arXiv)

While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zero-shot adaptation to unseen speakers. We investigate multi-speaker modeling for end-to-end text-to-speech synthesis and study the effects of different types of state-of-the-art neural speaker embeddings on speaker similarity for unseen speakers. Learnable dictionary encoding-based speaker embeddings with angular softmax loss can improve equal error rates over x-vectors in a speaker verification task; these embeddings also improve speaker similarity and naturalness for unseen speakers when used for zero-shot adaptation to new speakers in end-to-end speech synthesis.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 14; 2023: 15; 2024: 16; 2025: 6; 2026: 3.

73 papers.

Sort:

By area:

  1. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 278
  2. 2021A Survey on Neural Speech Synthesiscited by 184
  3. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  4. 2021AdaSpeech: Adaptive Text to Speech for Custom Voicecited by 98
  5. 2023SpeechX: Neural Codec Language Model as a Versatile Speech Transformercited by 64
  6. 2022AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarioscited by 41
  7. 2024VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignmentcited by 38
  8. 2021Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speechcited by 37
  9. 2022Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Datacited by 35
  10. 2021fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkitcited by 24
  11. 2024Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveycited by 23
  12. 2021Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speechcited by 22
38 more
  1. 2023StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesiscited by 21
  2. 2024TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Controlcited by 20
  3. 2023PolyVoice: Language Models for Speech to Speech Translationcited by 19
  4. 2021GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesiscited by 18
  5. 2021AdaSpeech 2: Adaptive Text to Speech with Untranscribed Datacited by 17
  6. 2021AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Personcited by 17
  7. 2022Low-Resource Multilingual and Zero-Shot Multispeaker TTScited by 15
  8. 2023UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Datacited by 15
  9. 2021Speaker Generationcited by 14
  10. 2021VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Overcited by 13
  11. 2022Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speechcited by 13
  12. 2021Adapting TTS models For New Speakers using Transfer Learningcited by 12
  13. 2022Simple and Effective Unsupervised Speech Synthesiscited by 12
  14. 2021Expressive Neural Voice Cloningcited by 11
  15. 2023Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translationcited by 11
  16. 2024Where are we in audio deepfake detection? A systematic analysis over generative and detection modelscited by 11
  17. 2022Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpuscited by 10
  18. 2022Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptationcited by 10
  19. 2023Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation modelcited by 10
  20. 2023ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptationcited by 7
  21. 2021Whispered and Lombard Neural Speech Synthesiscited by 6
  22. 2021Review of end-to-end speech synthesis technology based on deep learningcited by 6
  23. 2024USAT: A Universal Speaker-Adaptive Text-to-Speech Approachcited by 6
  24. 2022ECAPA-TDNN for Multi-speaker Text-to-speech Synthesiscited by 5
  25. 2022A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesiscited by 5
  26. 2022Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosodycited by 5
  27. 2023Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representationscited by 5
  28. 2024Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapterscited by 4
  29. 2025Voice Cloning: Comprehensive Surveycited by 4
  30. 2021Combining speakers of multiple languages to improve quality of neural voicescited by 3
  31. 2024Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Modelcited by 3
  32. 2024Towards Zero-Shot Text-To-Speech for Arabic Dialectscited by 3
  33. 2025Zero-Shot Text-to-Speech for Vietnamesecited by 3
  34. 2025Voice Impression Control in Zero-Shot TTScited by 3
  35. 2025Analyzing and Improving Speaker Similarity Assessment for Speech Synthesiscited by 3
  36. 2022Zero-Shot Long-Form Voice Cloning with Dynamic Convolution Attentioncited by 2
  37. 2023Residual Information in Deep Speaker Embedding Architecturescited by 2
  38. 2023ELF: Encoding Speaker-Specific Latent Speech Feature for Speech Synthesiscited by 2

50 most cited of 73 All 73 (JSON)