A Comparative Analysis of Pretrained Language Models for Text-to-Speech
Not on the map. Why?
Abstract (arXiv)
State-of-the-art text-to-speech (TTS) systems have utilized pretrained language models (PLMs) to enhance prosody and create more natural-sounding speech. However, while PLMs have been extensively researched for natural language understanding (NLU), their impact on TTS has been overlooked. In this study, we aim to address this gap by conducting a comparative analysis of different PLMs for two TTS tasks: prosody prediction and pause prediction. Firstly, we trained a prosody prediction model using 15 different PLMs. Our findings revealed a logarithmic relationship between model size and quality, as well as significant performance differences between neutral and expressive prosody. Secondly, we employed PLMs for pause prediction and found that the task was less sensitive to small models. We also identified a strong correlation between our empirical results and the GLUE scores obtained for these language models. To the best of our knowledge, this is the first study of its kind to investigate the impact of different PLMs on TTS.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 4 Sep 2023.
Builds on
21 of 32 references.
References · 21
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
- 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,043
- 2020A Primer in BERTology: What we know about how BERT workscited by 815
- 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
- 2020Pre-trained Models for Natural Language Processing: A Surveycited by 505
- 2020MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devicescited by 482
- 2021Pre-Trained Models: Past, Present and Futurecited by 319
- 2020Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processingcited by 162
9 more
- 2020SqueezeBERT: What can computer vision teach NLP about efficient neural networks?cited by 50
- 2020A Survey on Contextual Embeddingscited by 48
- 2020Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesiscited by 27
- 2019Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Modelscited by 10
- 2022CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfercited by 7
- 2022Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosodycited by 5
- 2022ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Modelscited by 4
- 2022Life after BERT: What do Other Muppets Understand about Language?cited by 4
- 2023eCat: An End-to-End Model for Multi-Speaker TTS & Many-to-Many Fine-Grained Prosody Transfercited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.