# SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation

arXiv: https://arxiv.org/abs/2207.13703 · HTML: https://mlsanity.com/paper/2207.13703/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 27 Jul 2022.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning](https://mlsanity.com/paper/1710.07654/) (2017)
- [Transformer based Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/2004.06338/) (2020)
- [DomainNet: Homograph Detection for Data Lake Disambiguation](https://mlsanity.com/paper/2103.09940/) (2021)
- [Representation Mixing for TTS Synthesis](https://mlsanity.com/paper/1811.07240/) (2018)

## Built on by (most cited first, 14 of 14)

- [Phoneme-aware Encoding for Prefix-tree-based Contextual ASR](https://mlsanity.com/paper/2312.09582/) (2023)
- [Speak While You Think: Streaming Speech Synthesis During Text Generation](https://mlsanity.com/paper/2309.11210/) (2023)
- [Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction](https://mlsanity.com/paper/2507.18863/) (2025)
- [Exploring the Benefits of Tokenization of Discrete Acoustic Units](https://mlsanity.com/paper/2406.05547/) (2024)
- [Train & Constrain: Phonologically Informed Tongue-Twister Generation from Topics and Paraphrases](https://mlsanity.com/paper/2403.13901/) (2024)
- [Multilingual context-based pronunciation learning for Text-to-Speech](https://mlsanity.com/paper/2307.16709/) (2023)
- [Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models](https://mlsanity.com/paper/2411.07563/) (2024)
- [Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning](https://mlsanity.com/paper/2409.09891/) (2024)
- [Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation](https://mlsanity.com/paper/2409.11003/) (2024)
- [Memory as Resonance: A Biomimetic Architecture for Infinite Context Memory on Ergodic Phonetic Manifolds](https://mlsanity.com/paper/2512.20245/) (2025)
- [Automatic Heteronym Resolution Pipeline Using RAD-TTS Aligners](https://mlsanity.com/paper/2302.14523/) (2023)
- [SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces](https://mlsanity.com/paper/2307.12445/) (2023)
- [Head-Pose-Aware Visual Speech Recognition with FiLM Modulation](https://mlsanity.com/paper/2606.00751/) (2026)
- [Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition](https://mlsanity.com/paper/2609.20839/) (2026)

## Abstract (arXiv)

End-to-end speech synthesis models directly convert the input characters into an audio representation (e.g., spectrograms). Despite their impressive performance, such models have difficulty disambiguating the pronunciations of identically spelled words. To mitigate this issue, a separate Grapheme-to-Phoneme (G2P) model can be employed to convert the characters into phonemes before synthesizing the audio. This paper proposes SoundChoice, a novel G2P architecture that processes entire sentences rather than operating at the word level. The proposed architecture takes advantage of a weighted homograph loss (that improves disambiguation), exploits curriculum learning (that gradually switches from word-level to sentence-level G2P), and integrates word embeddings from BERT (for further performance improvement). Moreover, the model inherits the best practices in speech recognition, including multi-task learning with Connectionist Temporal Classification (CTC) and beam search with an embedded language model. As a result, SoundChoice achieves a Phoneme Error Rate (PER) of 2.65% on whole-sentence transcription using data from LibriSpeech and Wikipedia. Index Terms grapheme-to-phoneme, speech synthesis, text-tospeech, phonetics, pronunciation, disambiguation.