Deep Feed-forward Sequential Memory Networks For Speech Synthesis

Abstract

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.

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keybi2018deep

Related papers

• A Novel Pyramidal-fsmn Architecture With Lattice-free MMI For Speech Recognition (2018)0.00
• Devicetts: A Small-footprint, Fast, Stable Network For On-device Text-to-speech (2020)0.00
• Rnn-based Speech Synthesis Using A Continuous Sinusoidal Model (2019)3.58
• Fast, Compact, And High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers For Mobile Devices (2016)13.05
• Investigating Gated Recurrent Neural Networks For Speech Synthesis (2016)0.00
• LSTM Deep Neural Networks Postfiltering For Improving The Quality Of Synthetic Voices (2016)0.00
• Evaluating Text-to-speech Synthesis From A Large Discrete Token-based Speech Language Model (2024)0.00
• DFSMN-SAN With Persistent Memory Model For Automatic Speech Recognition (2019)5.84