Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks

By Raul Fernandez, Asaf Rendel, Bhuvana Ramabhadran, Ron Hoory. 2014

89 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Deep learning in neural networks: An overview (2014, methodology): “…in language identification (GonzalezDominguez et al., 2014), medium-vocabulary speech recognition (Geiger et al., 2014), prosody contour prediction (Fernandez et al., 2014), audio onset detection (Marchi et al., 2014), text-to-speech synthesis (Fan et al., 2014), and social signal classification…”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, background): “Many recent state-of-the-art results in sequence processing are based on LSTM, which learned to control robots [159], and was used to set benchmark records in prosody contour prediction [55] (IBM), textto-speech synthesis [54] (Microsoft), large vocabulary speech recognition [213] (Google), and mach”
Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis (2015, methodology): “It has been successfully applied to various applications, such as speech recognition [26] [27], handwriting recognition [28], and speech synthesis [19] [20] [21] [22].”
Word embedding for recurrent neural network based TTS synthesis (2015, background): “Bidirectional long short term memory (BLSTM) recurrent neural network (RNN) [3, 4, 5] which can make use of features of a long context is introduced to replace DNN in [6, 7].”
Recent Advances in Recurrent Neural Networks (2017, background): “The BLSTM has been shown to perform very well in speech synthesis due to the ability to integrate the relationship with neighbouring frames in both future and past time steps [112], [113].”
Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks (2016, background): “LSTMs have been applied in a range of speech problems [15, 16], including regression problems such as text-to-speech [17, 18, 19, 20, 21] and as previously mentioned speech enhancement [10, 8].”
Tacotron-Based Acoustic Model Using Phoneme Alignment for Practical Neural Text-to-Speech Systems (2019, methodology): “Duration and acoustic models for pipeline neural text-to-speech systems with full-context label input: (a) conventional duration model with simple bidirectional LSTM and linear layers [40,41]; (b) conventional acoustic model with simple bidirectional LSTM and linear layers [3, 5]; (c) Tacotron with ”
A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis (2016, methodology): “Recurrent neural networks and long-short term memories have been used for prosody modeling [3] and acoustic trajectory modeling [4].”
Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech (2016, unknown): “LSTMs have been applied in a range of speech problems [17, 18], including regression problems such as text-to-speech [19, 20, 21, 22, 23] and as previously mentioned speech enhancement [8, 9].”
Multi-output RNN-LSTM for multiple speaker speech synthesis with α-interpolation model (2016, unknown): “Some example works using this structures can be seen in [6, 7, 8, 9].”
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].”
A Deep Generative Architecture for Postfiltering in Statistical Parametric Speech Synthesis (2015, background): “Recently, recurrent neural networks (RNNs) with long-short term memories (LSTMs) have been used for prosody modeling [10] and acoustic trajectory modeling [11], [12].”
A Template-Based Approach for Speech Synthesis Intonation Generation Using LSTMs (2016, unknown): “[10] proposes predicting state-level F0 statistics and durations using so-called long short-term memory (LSTM) units.”
Investigating gated recurrent neural networks for speech synthesis (2016, unknown): “In [17], an LSTM was employed to model the F0 contour.”