mlsanityData to 13 Oct 2026

Cross-speaker Emotion Transfer by Manipulating Speech Style Latents

arXiv 2303.08329 ↗First posted 15 Mar 2023cs.SD cs.CL eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

In recent years, emotional text-to-speech has shown considerable progress. However, it requires a large amount of labeled data, which is not easily accessible. Even if it is possible to acquire an emotional speech dataset, there is still a limitation in controlling emotion intensity. In this work, we propose a novel method for cross-speaker emotion transfer and manipulation using vector arithmetic in latent style space. By leveraging only a few labeled samples, we generate emotional speech from reading-style speech without losing the speaker identity. Furthermore, emotion strength is readily controllable using a scalar value, providing an intuitive way for users to manipulate speech. Experimental results show the proposed method affords superior performance in terms of expressiveness, naturalness, and controllability, preserving speaker identity.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 15 Mar 2023.

Builds on

19 of 25 references.

References · 19

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,000
  2. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,148
  3. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  4. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  5. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  6. 2018Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotroncited by 172
  7. 2020Seen and Unseen emotional style transfer for voice conversion with a new emotional speech datasetcited by 120
  8. 2018Neural Voice Cloning with a Few Samplescited by 100
  9. 2021Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generationcited by 93
  10. 2022DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speechcited by 67
  11. 2019Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloningcited by 66
  12. 2018Robust and fine-grained prosody control of end-to-end speech synthesiscited by 48
7 more
  1. 2020Fine-grained Emotion Strength Transfer, Control and Prediction for Emotional Speech Synthesiscited by 29
  2. 2022MsEmoTTS: Multi-scale emotion transfer, prediction, and control for emotional speech synthesiscited by 29
  3. 2021Cross-speaker emotion disentangling and transfer for end-to-end speech synthesiscited by 21
  4. 2019End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Trainingcited by 19
  5. 2020Emotion controllable speech synthesis using emotion-unlabeled dataset with the assistance of cross-domain speech emotion recognitioncited by 19
  6. 2021EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Modelcited by 18
  7. 2022Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTScited by 6

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Controlcited by 13
  2. 2025DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speechcited by 5