Deep Feed-forward Sequential Memory Networks for Speech Synthesis
The Bidirectional LSTM (BLSTM) RNN based speech synthesis system is among the best parametric Text-to-Speech (TTS) systems in terms of the naturalness of generated speech, especially the naturalness in prosody. However, the model complexity and inference cost of BLSTM prevents its usage in many runtime applications. Meanwhile, Deep Feed-forward Sequential Memory Networks (DFSMN) has shown its consistent out-performance over BLSTM in both word error rate (WER) and the runtime computation cost in speech recognition tasks. Since speech synthesis also requires to model long-term dependencies compared to speech recognition, in this paper, we investigate the Deep-FSMN (DFSMN) in speech synthesis. Both objective and subjective experiments show that, compared with BLSTM TTS method, the DFSMN system can generate synthesized speech with comparable speech quality while drastically reduce model complexity and speech generation time.
Code (0)
등록된 구현이 없습니다.
Tasks
speech-recognitionSpeech RecognitionSpeech Synthesistext-to-speechText to SpeechMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Utterance-level Sequential Modeling For Deep Gaussian Process Based Speech Synthesis Using Simple Recurrent Unit
This paper presents a deep Gaussian process (DGP) model with a recurrent architecture for speech sequence modeling. DGP is a Bayesian deep model that can be trained effectively with the consideration of model complexity …
Speech SynthesisFeedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
In this paper, we propose a novel neural network structure, namely \emph{feedforward sequential memory networks (FSMN)}, to model long-term dependency in time series without using recurrent feedback. The proposed FSMN is…
Language Modellingspeech-recognitionSpeech RecognitionTime Series+1Feedforward Sequential Memory Neural Networks without Recurrent Feedback
We introduce a new structure for memory neural networks, called feedforward sequential memory networks (FSMN), which can learn long-term dependency without using recurrent feedback. The proposed FSMN is a standard feedfo…
Language ModelingLanguage ModellingParallel WaveNet: Fast High-Fidelity Speech Synthesis
The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, becau…
Speech SynthesisVocal Bursts Intensity PredictionAutomatic Prosody Prediction for Chinese Speech Synthesis using BLSTM-RNN and Embedding Features
Prosody affects the naturalness and intelligibility of speech. However, automatic prosody prediction from text for Chinese speech synthesis is still a great challenge and the traditional conditional random fields (CRF) b…
Feature EngineeringProsody PredictionSpeech Synthesis