paper-with-me

홈 › Papers

A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis

2019-11-11 · Junjie Pan, Xiang Yin, Zhiling Zhang, Shichao Liu, Yang Zhang, Zejun Ma, Yuxuan Wang

In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this paper, we proposed a unified sequence-to-sequence front-end model for Mandarin TTS that converts raw texts to linguistic features directly. Compared to the pipeline-based front-end, our unified front-end can achieve comparable performance in polyphone disambiguation and prosody word prediction, and improve intonation phrase prediction by 0.0738 in F1 score. We also implemented the unified front-end with Tacotron and WaveRNN to build a Mandarin TTS system. The synthesized speech by that got a comparable MOS (4.38) with the pipeline-based front-end (4.37) and close to human recordings (4.49).

📄 PDF Abstract BibTeX arXiv:1911.04111

Code (0)

등록된 구현이 없습니다.

Tasks

Polyphone disambiguationSpeech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
WaveRNN WaveRNN is a single-layer recurrent neural network for audio generation that is designed efficiently predict 16-bit raw audio samples. The overall computation in the…
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…
Sigmoid Activation 설명 없음
Highway Layer 설명 없음
Residual Connection 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Unified Mandarin TTS Front-end Based on Distilled BERT Model

2020-12-31 · Yang Zhang, Liqun Deng, Yasheng Wang

The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size…

Knowledge DistillationLanguage ModelingLanguage ModellingMulti-Task Learning+2

A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading

2019-08-14 · Ya Zhao, Rui Xu, Mingli Song

Lip reading aims at decoding texts from the movement of a speaker's mouth. In recent years, lip reading methods have made great progress for English, at both word-level and sentence-level. Unlike English, however, Chines…

LipreadingLip ReadingSentence

Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese

2018-04-28 · Shiyu Zhou, Linhao Dong, Shuang Xu, Bo Xu

Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural netwo…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage Modeling+7

Towards unified brain-to-text decoding across speech production and perception

2026-03-13 · Zhizhang Yuan, Yang Yang, Gaorui Zhang, Baowen Cheng 외 arxiv

Speech production and perception are the main ways humans communicate daily. Prior brain-to-text decoding studies have largely focused on a single modality and alphabetic languages. Here, we present a unified brain-to-se…

A Character-level Span-based Model for Mandarin Prosodic Structure Prediction

2022-03-31 · Xueyuan Chen, Changhe Song, Yixuan Zhou, Zhiyong Wu 외

The accuracy of prosodic structure prediction is crucial to the naturalness of synthesized speech in Mandarin text-to-speech system, but now is limited by widely-used sequence-to-sequence framework and error accumulation…

Sentencetext-to-speechText to Speech