Text-to-speech conversion with neural networks: a recurrent TDNN approach

By O. Karaali, Gerald Corrigan, I. Gerson, N. Massey. 1997

This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system. The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries. Recurrent data input also helps smooth the output parameter tracks. Independent testing has demonstrated that the voice quality produced by this system compares favorably with speech from existing commercial text-to-speech systems.

Subfields: Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Speech & Audio

Citations in the corpus

WaveNet: A Generative Model for Raw Audio (2016, background): “…Markov models (HMMs) (Yoshimura, 2002), feed-forward neural networks (Zen et al., 2013), and recurrent neural networks (Tuerk & Robinson, 1993; Karaali et al., 1997; Fan et al., 2014), is trained from the extracted vocoder parameters and linguistic features as where Λ denotes the set of…”
Recent Advances in Recurrent Neural Networks (2017, methodology): “RNNs were first used for speech synthesis to leverage these sequential dependencies [109], [110], and were then replaced with LSTM models to better learn long term sequential dependencies [111].”
Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis (2015, methodology): “Tuerk and Ronbinson [16] and Karaani et al. [17] applied standard RNNs to speech synthesis, whereas long short-term memory RNNs (LSTM- RNNs) [18], which can capture long-term dependencies, were recently applied to acoustic modeling for SPSS [19] [20] [21]; Fan et al. and Fernandez et al. applied dee”
Review of end-to-end speech synthesis technology based on deep learning (2021, unknown): “Based on this, some researchers use RNN instead of DNN to capture the long-term dependence of speech frames in order to improve the quality of synthesized speech [51, 53, 93, 213, 248, 251].”