mlsanityData to 7 Oct 2026

Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise Distillation

arXiv 2203.15643 ↗First posted 29 Mar 2022cs.SD cs.CL cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Several solutions for lightweight TTS have shown promising results. Still, they either rely on a hand-crafted design that reaches non-optimum size or use a neural architecture search but often suffer training costs. We present Nix-TTS, a lightweight TTS achieved via knowledge distillation to a high-quality yet large-sized, non-autoregressive, and end-to-end (vocoder-free) TTS teacher model. Specifically, we offer module-wise distillation, enabling flexible and independent distillation to the encoder and decoder module. The resulting Nix-TTS inherited the advantageous properties of being non-autoregressive and end-to-end from the teacher, yet significantly smaller in size, with only 5.23M parameters or up to 89.34% reduction of the teacher model; it also achieves over 3.04x and 8.36x inference speedup on Intel-i7 CPU and Raspberry Pi 3B respectively and still retains a fair voice naturalness and intelligibility compared to the teacher model. We provide pretrained models and audio samples of Nix-TTS.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 29 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

22 of 29 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  4. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  5. 2016Density estimation using Real NVPcited by 2,029
  6. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  7. 2016Least Squares Generative Adversarial Networkscited by 1,000
  8. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  9. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  10. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  11. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  12. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
10 more
  1. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  2. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  3. 2020DDSP: Differentiable Digital Signal Processingcited by 177
  4. 2020End-to-End Adversarial Text-to-Speechcited by 77
  5. 2018ClariNet: Parallel Wave Generation in End-to-End Text-to-Speechcited by 70
  6. 2020A Spectral Energy Distance for Parallel Speech Synthesiscited by 42
  7. 2021LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Searchcited by 27
  8. 2020SpeedySpeech: Efficient Neural Speech Synthesiscited by 15
  9. 2021TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Predictioncited by 7
  10. 2021On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesiscited by 2

Built on by

Cited by year

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

3 papers.

  1. 2022Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transformcited by 8
  2. 2024ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigramscited by 2
  3. 2025BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexingcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
  2. 2026CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
  3. 2026Distill Locally, Schedule Globally: Flow Maps for Few-Step Text-to-Speech
  4. 2026TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech
  5. 2025DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration
  6. 2026COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning
  7. 2026End-to-End Training for Discrete Token LLM based TTS System
  8. 2025SyncSpeech: Efficient and Low-Latency Text-to-Speech based on Temporal Masked Transformer