paper-with-me

Papers

Using IPA-Based Tacotron for Data Efficient Cross-Lingual Speaker Adaptation and Pronunciation Enhancement

2020-11-12 · Hamed Hemati, Damian Borth

Recent neural Text-to-Speech (TTS) models have been shown to perform very well when enough data is available. However, fine-tuning them for new speakers or languages is not straightforward in a low-resource setup. In this paper, we show that by applying minor modifications to a Tacotron model, one can transfer an existing TTS model for new speakers from the same or a different language using only 20 minutes of data. For this purpose, we first introduce a base multi-lingual Tacotron with language-agnostic input, then demonstrate how transfer learning is done for different scenarios of speaker adaptation without exploiting any pre-trained speaker encoder or code-switching technique. We evaluate the transferred model in both subjective and objective ways.

📄 PDF Abstract BibTeX arXiv:2011.06392

Code (0)

등록된 구현이 없습니다.

Tasks

text-to-speechText to SpeechTransfer Learning

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Highway Layer 설명 없음
Highway Network A Highway Network is an architecture designed to ease gradient-based training of very deep networks. They allow unimpeded information flow across several layers on…
Batch Normalization 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Griffin-Lim Algorithm The Griffin-Lim Algorithm (GLA) is a phase reconstruction method based on the redundancy of the short-time Fourier transform. It promotes the consistency of a spectrogram by…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BiGRU A Bidirectional GRU, or BiGRU, is a sequence processing model that consists of two GRUs. one taking the input in a forward…

Similar Papers 제목 키워드 기반

Towards Natural Bilingual and Code-Switched Speech Synthesis Based on Mix of Monolingual Recordings and Cross-Lingual Voice Conversion

2020-10-16 · Shengkui Zhao, Trung Hieu Nguyen, Hao Wang, Bin Ma

Recent state-of-the-art neural text-to-speech (TTS) synthesis models have dramatically improved intelligibility and naturalness of generated speech from text. However, building a good bilingual or code-switched TTS for a…

Speech Synthesistext-to-speechText to SpeechVoice Conversion

Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?

2020-05-04 · Erica Cooper, Cheng-I Lai, Yusuke Yasuda, Junichi Yamagishi

Previous work on speaker adaptation for end-to-end speech synthesis still falls short in speaker similarity. We investigate an orthogonal approach to the current speaker adaptation paradigms, speaker augmentation, by cre…

Speech Synthesis

Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario

2020-05-21 · Zexin Cai, Yaogen Yang, Ming Li

Modeling voices for multiple speakers and multiple languages in one text-to-speech system has been a challenge for a long time. This paper presents an extension on Tacotron2 to achieve bilingual multispeaker speech synth…

AttributeSpeech Synthesistext-to-speechText to Speech

Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging

2021-07-26 · Csaba Zainkó, László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya 외

For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer lear…

text-to-speechText to SpeechTransfer Learning

Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation

2022-10-31 · Nikolaos Ellinas, Georgios Vamvoukakis, Konstantinos Markopoulos, Georgia Maniati 외

This paper presents a method for end-to-end cross-lingual text-to-speech (TTS) which aims to preserve the target language's pronunciation regardless of the original speaker's language. The model used is based on a non-at…

DecoderDisentanglementtext-to-speechText to Speech+1