Representation Mixing for TTS Synthesis
Not on the map. Why?
Abstract (arXiv)
Recent character and phoneme-based parametric TTS systems using deep learning have shown strong performance in natural speech generation. However, the choice between character or phoneme input can create serious limitations for practical deployment, as direct control of pronunciation is crucial in certain cases. We demonstrate a simple method for combining multiple types of linguistic information in a single encoder, named representation mixing, enabling flexible choice between character, phoneme, or mixed representations during inference. Experiments and user studies on a public audiobook corpus show the efficacy of our approach.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Nov 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 4.
7 papers.
- 2021A Survey on Neural Speech Synthesiscited by 184
- 2021PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTScited by 52
- 2022SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguationcited by 14
- 2022Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speechcited by 13
- 2021Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesiscited by 12
- 2022Zero-Shot Long-Form Voice Cloning with Dynamic Convolution Attentioncited by 2
- 2022R-MelNet: Reduced Mel-Spectral Modeling for Neural TTScited by 0
- 2022SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation27 Jul 2022
- 2022R-MelNet: Reduced Mel-Spectral Modeling for Neural TTS30 Jun 2022
- 2022Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech31 Mar 2022
- 2022Zero-Shot Long-Form Voice Cloning with Dynamic Convolution Attention25 Jan 2022
- 2021A Survey on Neural Speech Synthesis29 Jun 2021
- 2021Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis26 Apr 2021
- 2021PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS28 Mar 2021