Meta Learning Text-to-Speech Synthesis in over 7000 Languages

• URL: http://arxiv.org/abs/2406.06403v1
• Date: Mon, 10 Jun 2024 15:56:52 GMT
• Title: Meta Learning Text-to-Speech Synthesis in over 7000 Languages
• Authors: Florian Lux, Sarina Meyer, Lyonel Behringer, Frank Zalkow, Phat Do, Matt Coler, Emanuël A. P. Habets, Ngoc Thang Vu,
• Abstract summary: In this work, we take on the challenging task of building a single text-to-speech synthesis system capable of generating speech in over 7000 languages. By leveraging a novel integration of massively multilingual pretraining and meta learning, our approach enables zero-shot speech synthesis in languages without any available data. We aim to empower communities with limited linguistic resources and foster further innovation in the field of speech technology.
• Score: 29.17020696379219
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this work, we take on the challenging task of building a single text-to-speech synthesis system that is capable of generating speech in over 7000 languages, many of which lack sufficient data for traditional TTS development. By leveraging a novel integration of massively multilingual pretraining and meta learning to approximate language representations, our approach enables zero-shot speech synthesis in languages without any available data. We validate our system's performance through objective measures and human evaluation across a diverse linguistic landscape. By releasing our code and models publicly, we aim to empower communities with limited linguistic resources and foster further innovation in the field of speech technology.

Related papers

• ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language [53.8622516025736]
  We propose a novel end-to-end zero-shot dialogue generation model ChatZero based on cross-lingual code-switching method. Experiments on the multilingual DailyDialog and DSTC7-AVSD datasets demonstrate that ChatZero can achieve more than 90% of the original performance.
  arXiv  Detail & Related papers  (2024-08-16T13:11:53Z)
• Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training [29.47243668154796]
  BLOOMZMMS is a novel model that integrates a multilingual LLM with a multilingual speech encoder. We demonstrate the transferability of linguistic knowledge from the text to the speech modality. Our zero-shot evaluation results confirm the robustness of our approach across multiple tasks.
  arXiv  Detail & Related papers  (2024-04-16T21:45:59Z)
• ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation [79.66359274050885]
  We present ComSL, a speech-language model built atop a composite architecture of public pretrained speech-only and language-only models. Our approach has demonstrated effectiveness in end-to-end speech-to-text translation tasks.
  arXiv  Detail & Related papers  (2023-05-24T07:42:15Z)
• 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)
• Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining [65.30528567491984]
  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.
  arXiv  Detail & Related papers  (2023-01-30T00:53:50Z)
• 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)
• Building African Voices [125.92214914982753]
  This paper focuses on speech synthesis for low-resourced African languages. We create a set of general-purpose instructions on building speech synthesis systems with minimum technological resources. We release the speech data, code, and trained voices for 12 African languages to support researchers and developers.
  arXiv  Detail & Related papers  (2022-07-01T23:28:16Z)
• Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features [30.37026279162593]
  In this work, we use embeddings derived from articulatory vectors rather than embeddings derived from phoneme identities to learn phoneme representations that hold across languages. This enables us to fine-tune a high-quality text-to-speech model on just 30 minutes of data in a previously unseen language spoken by a previously unseen speaker.
  arXiv  Detail & Related papers  (2022-03-07T07:58:01Z)
• Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity [81.51206991542242]
  Cross-lingual transfer offers a compelling way to help bridge this digital divide. Current cross-lingual algorithms have shown success in text-based tasks and speech-related tasks over some low-resource languages. We propose a language similarity approach that can efficiently identify acoustic cross-lingual transfer pairs across hundreds of languages.
  arXiv  Detail & Related papers  (2021-11-02T01:55:17Z)

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.