# Multi-Scale Spectrogram Modelling for Neural Text-to-Speech

arXiv: https://arxiv.org/abs/2106.15649 · HTML: https://mlsanity.com/paper/2106.15649/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 29 Jun 2021.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron](https://mlsanity.com/paper/1803.09047/) (2018)
- [Hierarchical Generative Modeling for Controllable Speech Synthesis](https://mlsanity.com/paper/1810.07217/) (2018)
- [MelNet: A Generative Model for Audio in the Frequency Domain](https://mlsanity.com/paper/1906.01083/) (2019)
- [Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS](https://mlsanity.com/paper/1906.00672/) (2019)
- [DurIAN: Duration Informed Attention Network For Multimodal Synthesis](https://mlsanity.com/paper/1909.01700/) (2019)
- [Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior](https://mlsanity.com/paper/2002.03788/) (2020)
- [CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network](https://mlsanity.com/paper/1905.07195/) (2019)
- [Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder](https://mlsanity.com/paper/1804.02135/) (2018)
- [AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment](https://mlsanity.com/paper/2003.01950/) (2020)
- [Controllable neural text-to-speech synthesis using intuitive prosodic features](https://mlsanity.com/paper/2009.06775/) (2020)
- [Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis](https://mlsanity.com/paper/2011.06465/) (2020)
- [CAMP: a Two-Stage Approach to Modelling Prosody in Context](https://mlsanity.com/paper/2011.01175/) (2020)
- [Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection](https://mlsanity.com/paper/1912.00955/) (2019)
- [Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech](https://mlsanity.com/paper/2011.02252/) (2020)
- [Traditional Machine Learning for Pitch Detection](https://mlsanity.com/paper/1903.01290/) (2019)

## Abstract (arXiv)

We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrogram prediction mechanism where the system first predicts coarser scale mel-spectrograms that capture the suprasegmental information in speech, and later uses these coarser scale mel-spectrograms to predict finer scale mel-spectrograms capturing fine-grained prosody. We present details for two specific versions of MSS called Word-level MSS and Sentence-level MSS where the scales in our system are motivated by the linguistic units. The Word-level MSS models word, phoneme, and frame-level spectrograms while Sentence-level MSS models sentence-level spectrogram in addition. Subjective evaluations show that Word-level MSS performs statistically significantly better compared to the baseline on two voices.