paper-with-me

Papers

Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus

2022-03-29 · Minchan Kim, Myeonghun Jeong, Byoung Jin Choi, Sunghwan Ahn, Joun Yeop Lee, Nam Soo Kim

Training a text-to-speech (TTS) model requires a large scale text labeled speech corpus, which is troublesome to collect. In this paper, we propose a transfer learning framework for TTS that utilizes a large amount of unlabeled speech dataset for pre-training. By leveraging wav2vec2.0 representation, unlabeled speech can highly improve performance, especially in the lack of labeled speech. We also extend the proposed method to zero-shot multi-speaker TTS (ZS-TTS). The experimental results verify the effectiveness of the proposed method in terms of naturalness, intelligibility, and speaker generalization. We highlight that the single speaker TTS model fine-tuned on the only 10 minutes of labeled dataset outperforms the other baselines, and the ZS-TTS model fine-tuned on the only 30 minutes of single speaker dataset can generate the voice of the arbitrary speaker, by pre-training on unlabeled multi-speaker speech corpus.

📄 PDF Abstract BibTeX arXiv:2203.15447

Code (0)

등록된 구현이 없습니다.

Tasks

text-to-speechText to SpeechTransfer LearningZero-Shot Multi-Speaker TTS

Similar Papers 제목 키워드 기반

Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios

2025-05-30 · Gerard I. Gállego, Oriol Pareras, Martí Cortada Garcia, Lucas Takanori 외

We propose a Speech-to-Text Translation (S2TT) approach that integrates phoneme representations into a Chain-of-Thought (CoT) framework to improve translation in low-resource and zero-resource settings. By introducing ph…

Cross-Lingual TransferPhoneme RecognitionSpeech-to-TextSpeech-to-Text Translation+1

Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity

2021-11-02 · Peter Wu, Jiatong Shi, Yifan Zhong, Shinji Watanabe 외

Speech processing systems currently do not support the vast majority of languages, in part due to the lack of data in low-resource languages. Cross-lingual transfer offers a compelling way to help bridge this digital div…

Cross-Lingual Transferspeech-recognitionSpeech RecognitionSpeech Synthesis

Speech Synthesis for Low Resource Languages using Transliteration Enabled Transfer Learning

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In the area of Human Computer Interaction (HCI), Text To Speech (TTS) synthesis has received a significant boost in recent years, especially with the development of various deep learning techniques capable of generating …

speech-recognitionSpeech RecognitionSpeech Synthesistext-to-speech+3

Transfer Learning for Less-Resourced Semitic Languages Speech Recognition: the Case of Amharic

2020-05-01 · LREC 2020 5 · Yonas Woldemariam

While building automatic speech recognition (ASR) requires a large amount of speech and text data, the problem gets worse for less-resourced languages. In this paper, we investigate a model adaptation method, namely tran…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1

End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learning

2019-04-13 · Tao Tu, Yuan-Jui Chen, Cheng-chieh Yeh, Hung-Yi Lee

End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hi…

Cross-Lingual Transfertext-to-speechText to SpeechTransfer Learning