# ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis

arXiv: https://arxiv.org/abs/2203.10473 · HTML: https://mlsanity.com/paper/2203.10473/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [Deep Voice 2: Multi-Speaker Neural Text-to-Speech](https://mlsanity.com/paper/1705.08947/) (2017)
- [Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings](https://mlsanity.com/paper/1910.10838/) (2019)
- [The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods](https://mlsanity.com/paper/1804.04262/) (2018)
- [Deep Speaker: an End-to-End Neural Speaker Embedding System](https://mlsanity.com/paper/1705.02304/) (2017)
- [ECAPA-TDNN Embeddings for Speaker Diarization](https://mlsanity.com/paper/2104.01466/) (2021)
- [MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network](https://mlsanity.com/paper/2103.00110/) (2021)
- [Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech](https://mlsanity.com/paper/2103.04088/) (2021)
- [Utilizing Self-supervised Representations for MOS Prediction](https://mlsanity.com/paper/2104.03017/) (2021)
- [SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification](https://mlsanity.com/paper/2010.12653/) (2020)

## Built on by (most cited first, 5 of 5)

- [Simple and Effective Unsupervised Speech Synthesis](https://mlsanity.com/paper/2204.02524/) (2022)
- [Voice Cloning: Comprehensive Survey](https://mlsanity.com/paper/2505.00579/) (2025)
- [DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech](https://mlsanity.com/paper/2410.13342/) (2024)
- [LAPS-Diff: A Diffusion-Based Framework for Singing Voice Synthesis With Language Aware Prosody-Style Guided Learning](https://mlsanity.com/paper/2507.04966/) (2025)
- [Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion](https://mlsanity.com/paper/2609.24688/) (2026)

## Abstract (arXiv)

In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in these methods still cannot capture enough speaker information. In this paper, we focus on accurate speaker encoder modeling and propose an end-to-end method that can generate high-quality speech and better similarity for both seen and unseen speakers. The proposed architecture consists of three separately trained components: a speaker encoder based on the state-of-the-art ECAPA-TDNN model which is derived from speaker verification task, a FastSpeech2 based synthesizer, and a HiFi-GAN vocoder. The comparison among different speaker encoder models shows our proposed method can achieve better naturalness and similarity. To efficiently evaluate our synthesized speech, we are the first to adopt deep learning based automatic MOS evaluation methods to assess our results, and these methods show great potential in automatic speech quality assessment.