Scaling and bias codes for modeling speaker-adaptive DNN-based speech synthesis systems

07/31/2018
by   Hieu-Thi Luong, et al.
0

Most neural-network based speaker-adaptive acoustic models for speech synthesis can be categorized into either layer-based or input-code approaches. Although both approaches have their own pros and cons, most existing works on speaker adaptation focus on improving one or the other. In this paper, after we first systematically overview the common principles of neural-network based speaker-adaptive models, we show that these approaches can be represented in a unified framework and can be generalized further. More specifically, we introduce the use of scaling and bias codes as generalized means for speaker-adaptive transformation. By utilizing these codes, we can create a more efficient factorized speaker-adaptive model and capture advantages of both approaches while reducing their disadvantages. The experiments show that the proposed method can improve the performance of speaker adaptation compared with speaker adaptation based on the conventional input code.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/05/2018

Linear networks based speaker adaptation for speech synthesis

Speaker adaptation methods aim to create fair quality synthesis speech v...
research
08/20/2018

Multimodal speech synthesis architecture for unsupervised speaker adaptation

This paper proposes a new architecture for speaker adaptation of multi-s...
research
11/08/2018

Speaker-adaptive neural vocoders for statistical parametric speech synthesis systems

This paper proposes speaker-adaptive neural vocoders for statistical par...
research
06/18/2019

A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation

By representing speaker characteristic as a single fixed-length vector e...
research
05/01/2018

Adaptive Scaling for Sparse Detection in Information Extraction

This paper focuses on detection tasks in information extraction, where p...
research
03/27/2018

Empirical Evaluation of Speaker Adaptation on DNN based Acoustic Model

Speaker adaptation aims to estimate a speaker specific acoustic model fr...
research
09/30/2019

Embeddings for DNN speaker adaptive training

In this work, we investigate the use of embeddings for speaker-adaptive ...

Please sign up or login with your details

Forgot password? Click here to reset