mlsanityData to 7 Oct 2026

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

arXiv 2203.10473 ↗First posted 20 Mar 2022cs.SD cs.LG eess.AScited by 5

Not on the map. Why?

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 20 Mar 2022.

Builds on

21 of 35 references.

References · 21

  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  3. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  4. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  5. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  6. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
  7. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 606
  8. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  9. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 280
  10. 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 126
  11. 2018Attentive Statistics Pooling for Deep Speaker Embeddingcited by 108
  12. 2019QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutionscited by 93
9 more
  1. 2017Deep Voice 2: Multi-Speaker Neural Text-to-Speechcited by 75
  2. 2019Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddingscited by 73
  3. 2018The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methodscited by 68
  4. 2017Deep Speaker: an End-to-End Neural Speaker Embedding Systemcited by 56
  5. 2021ECAPA-TDNN Embeddings for Speaker Diarizationcited by 47
  6. 2021MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Networkcited by 37
  7. 2021Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speechcited by 37
  8. 2021Utilizing Self-supervised Representations for MOS Predictioncited by 20
  9. 2020SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verificationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 2; 2026: 1.

5 papers.

  1. 2022Simple and Effective Unsupervised Speech Synthesiscited by 12
  2. 2025Voice Cloning: Comprehensive Surveycited by 4
  3. 2024DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speechcited by 3
  4. 2025LAPS-Diff: A Diffusion-Based Framework for Singing Voice Synthesis With Language Aware Prosody-Style Guided Learningcited by 0
  5. 2026Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversioncited by 0