Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining

• URL: http://arxiv.org/abs/2301.12596v3
• Date: Sat, 27 May 2023 15:15:39 GMT
• Title: Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining
• Authors: Takaaki Saeki, Soumi Maiti, Xinjian Li, Shinji Watanabe, Shinnosuke Takamichi, Hiroshi Saruwatari
• Abstract summary: This paper proposes a method for zero-shot multilingual TTS using text-only data for the target language. The use of text-only data allows the development of TTS systems for low-resource languages. Evaluation results demonstrate highly intelligible zero-shot TTS with a character error rate of less than 12% for an unseen language.
• Score: 65.30528567491984
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method for zero-shot multilingual TTS using text-only data for the target language. The use of text-only data allows the development of TTS systems for low-resource languages for which only textual resources are available, making TTS accessible to thousands of languages. Inspired by the strong cross-lingual transferability of multilingual language models, our framework first performs masked language model pretraining with multilingual text-only data. Then we train this model with a paired data in a supervised manner, while freezing a language-aware embedding layer. This allows inference even for languages not included in the paired data but present in the text-only data. Evaluation results demonstrate highly intelligible zero-shot TTS with a character error rate of less than 12% for an unseen language.

Related papers

• A multilingual training strategy for low resource Text to Speech [5.109810774427171]
  We investigate whether data from social media can be used for a small TTS dataset construction, and whether cross lingual transfer learning can work with this type of data. To do so, we explore how data from foreign languages may be selected and pooled to train a TTS model for a target low resource language. Our findings show that multilingual pre-training is better than monolingual pre-training at increasing the intelligibility and naturalness of the generated speech.
  arXiv  Detail & Related papers  (2024-09-02T12:53:01Z)
• Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model [13.730152819942445]
  Cross-lingual transfer learning can be particularly effective for improving performance in low-resource languages. This suggests that cross-lingual transfer can be inexpensive and effective for developing TTS front-end in resource-poor languages.
  arXiv  Detail & Related papers  (2023-06-05T04:10:04Z)
• Scaling Speech Technology to 1,000+ Languages [66.31120979098483]
  The Massively Multilingual Speech (MMS) project increases the number of supported languages by 10-40x, depending on the task. Main ingredients are a new dataset based on readings of publicly available religious texts. We built pre-trained wav2vec 2.0 models covering 1,406 languages, a single multilingual automatic speech recognition model for 1,107 languages, speech synthesis models for the same number of languages, and a language identification model for 4,017 languages.
  arXiv  Detail & Related papers  (2023-05-22T22:09:41Z)
• Speech-to-Speech Translation For A Real-world Unwritten Language [62.414304258701804]
  We study speech-to-speech translation (S2ST) that translates speech from one language into another language. We present an end-to-end solution from training data collection, modeling choices to benchmark dataset release.
  arXiv  Detail & Related papers  (2022-11-11T20:21:38Z)
• Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech [37.942466944970704]
  This paper proposes Virtuoso, a massively multilingual speech-text joint semi-supervised learning framework for text-to-speech synthesis (TTS) models. To train a TTS model from various types of speech and text data, different training schemes are designed to handle supervised (TTS and ASR data) and unsupervised (untranscribed speech and unspoken text) datasets. Experimental evaluation shows that multilingual TTS models trained on Virtuoso can achieve significantly better naturalness and intelligibility than baseline ones in seen languages.
  arXiv  Detail & Related papers  (2022-10-27T14:09:48Z)
• Low-Resource Multilingual and Zero-Shot Multispeaker TTS [25.707717591185386]
  We show that it is possible for a system to learn speaking a new language using just 5 minutes of training data. We show the success of our proposed approach in terms of intelligibility, naturalness and similarity to target speaker.
  arXiv  Detail & Related papers  (2022-10-21T20:03:37Z)
• When Is TTS Augmentation Through a Pivot Language Useful? [26.084140117526488]
  We propose to produce synthetic audio by running text from the target language through a trained TTS system for a higher-resource pivot language. Using several thousand synthetic TTS text-speech pairs and duplicating authentic data to balance yields optimal results. Application of these findings improves ASR by 64.5% and 45.0% character error reduction rate (CERR) respectively for two low-resource languages.
  arXiv  Detail & Related papers  (2022-07-20T13:33:41Z)
• Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding [55.989376102986654]
  This paper studies a transferable phoneme embedding framework that aims to deal with the cross-lingual text-to-speech problem under the few-shot setting. We propose a framework that consists of a phoneme-based TTS model and a codebook module to project phonemes from different languages into a learned latent space.
  arXiv  Detail & Related papers  (2022-06-27T11:24:40Z)
• Textless Speech-to-Speech Translation on Real Data [49.134208897722246]
  We present a textless speech-to-speech translation (S2ST) system that can translate speech from one language into another language. We tackle the challenge in modeling multi-speaker target speech and train the systems with real-world S2ST data.
  arXiv  Detail & Related papers  (2021-12-15T18:56:35Z)
• CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus [57.641761472372814]
  CoVoST is a multilingual speech-to-text translation corpus from 11 languages into English. It diversified with over 11,000 speakers and over 60 accents. CoVoST is released under CC0 license and free to use.
  arXiv  Detail & Related papers  (2020-02-04T14:35:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.