# Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

arXiv: https://arxiv.org/abs/1806.04558 · HTML: https://mlsanity.com/paper/1806.04558/

## Key facts

- Cited by 282 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2018.

## Built on by (most cited first, 30 of 282)

- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme](https://mlsanity.com/paper/2109.13821/) (2021)
- [AdaSpeech: Adaptive Text to Speech for Custom Voice](https://mlsanity.com/paper/2103.00993/) (2021)
- [Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation](https://mlsanity.com/paper/2106.03153/) (2021)
- [Self-Supervised Video Forensics by Audio-Visual Anomaly Detection](https://mlsanity.com/paper/2301.01767/) (2023)
- [Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance](https://mlsanity.com/paper/2111.11755/) (2021)
- [Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward](https://mlsanity.com/paper/2103.00484/) (2021)
- [Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations](https://mlsanity.com/paper/2110.14513/) (2021)
- [AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset](https://mlsanity.com/paper/2311.15308/) (2023)
- [Detecting Multimedia Generated by Large AI Models: A Survey](https://mlsanity.com/paper/2402.00045/) (2024)
- [Translatotron 2: High-quality direct speech-to-speech translation with voice preservation](https://mlsanity.com/paper/2107.08661/) (2021)
- [CVSS Corpus and Massively Multilingual Speech-to-Speech Translation](https://mlsanity.com/paper/2201.03713/) (2022)
- [SpeechX: Neural Codec Language Model as a Versatile Speech Transformer](https://mlsanity.com/paper/2308.06873/) (2023)
- [AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection](https://mlsanity.com/paper/2406.02951/) (2024)
- [Generative Pre-training for Speech with Flow Matching](https://mlsanity.com/paper/2310.16338/) (2023)
- [PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS](https://mlsanity.com/paper/2103.15060/) (2021)
- [Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias](https://mlsanity.com/paper/2306.03509/) (2023)
- [Audio-Visual Person-of-Interest DeepFake Detection](https://mlsanity.com/paper/2204.03083/) (2022)
- [Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization](https://mlsanity.com/paper/2305.01979/) (2023)
- [Lip to Speech Synthesis with Visual Context Attentional GAN](https://mlsanity.com/paper/2204.01726/) (2022)
- [Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation](https://mlsanity.com/paper/2406.07867/) (2024)
- [MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2502.18924/) (2025)
- [A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing](https://mlsanity.com/paper/2203.09690/) (2022)

## Abstract (arXiv)

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which generates a mel spectrogram from text, conditioned on the speaker embedding; (3) an auto-regressive WaveNet-based vocoder that converts the mel spectrogram into a sequence of time domain waveform samples. We demonstrate that the proposed model is able to transfer the knowledge of speaker variability learned by the discriminatively-trained speaker encoder to the new task, and is able to synthesize natural speech from speakers that were not seen during training. We quantify the importance of training the speaker encoder on a large and diverse speaker set in order to obtain the best generalization performance. Finally, we show that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation.