mlsanityData to 14 Oct 2026

Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment

arXiv 2605.00861 ↗First posted 21 Apr 2026eess.AS cs.AI eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

This study investigates voice mapping as an evaluation framework for text-to-speech (TTS) synthesis quality. The study analyzes six TTS models, including historical and recent ones. The metrics are crest factor, spectrum balance, and cepstral peak prominence (CPPs). We investigated 6 influential TTS models: Merlin, Tacotron 2, Transformer TTS, FastSpeech 2, Glow-TTS, and VITS. The results demonstrate that voice range serves as a primary indicator of model capability, with VITS showing the largest range among tested models. Glow-TTS exhibited superior performance in soft phonation, indicated by higher spectrum balance, despite limited voice range. The results showed that the CPPs values between 7-8 dB indicate natural voice quality, while with CPPs exceeding 10 dB, the speech tends to sound robotic. These findings underscore the need for voice mapping to evaluate vocal effort, and capture how TTS systems handle voice dynamic and expressiveness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 53 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

21 of 53 references.

References · 21

  1. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  2. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  3. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  4. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  5. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 490
  6. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  7. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 226
  8. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 192
  9. 2021A Survey on Neural Speech Synthesiscited by 184
  10. 2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 152
  11. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 151
  12. 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 127
9 more
  1. 2021UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generationcited by 74
  2. 2024Natural language guidance of high-fidelity text-to-speech with synthetic annotationscited by 67
  3. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  4. 2022The VoiceMOS Challenge 2022cited by 57
  5. 2021ESPnet2-TTS: Extending the Edge of TTS Researchcited by 22
  6. 2023Investigating Range-Equalizing Bias in Mean Opinion Score Ratings of Synthesized Speechcited by 13
  7. 2023Why We Should Report the Details in Subjective Evaluation of TTS More Rigorouslycited by 10
  8. 2020Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modelingcited by 4
  9. 2021Analysis and Assessment of Controllability of an Expressive Deep Learning-based TTS systemcited by 4

Built on by

Not cited yet.