Sentence-level control vectors for deep neural network speech synthesis

By Oliver Watts, Zhizheng Wu, Simon King. 2015

54 citations recorded by the source corpus.

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

Citations in the corpus

Semi-supervised Training for Improving Data Efficiency in End-to-end Speech Synthesis (2018, background): “There exists previous work studying the application of unsupervised and weakly supervised learning for TTS [4, 5, 6, 7].”
Improving Prosody Modelling with Cross-Utterance Bert Embeddings for End-to-End Speech Synthesis (2020, methodology): “Comparing to the previous studies [29–34], our approach is more “end-to-end” since it only uses the raw texts as input and does not require any explicitly defined symbolic prosody labels or DRs.”
Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages (2020, background): “Some studied introducing distributional textual or linguistic information into TTS within the traditional TTS paradigm [13–15].”
Uncovering Latent Style Factors for Expressive Speech Synthesis (2017, background): “More generally, these conditioning inputs are termed as control vectors in TTS literature [11, 12].”
Investigating different representations for modeling and controlling multiple emotions in DNN-based speech synthesis (2018, unknown): “Speech parameters can be predicted for an arbitrary text by a trained DNN using forward propagation.”
Median-based generation of synthetic speech durations using a non-parametric approach (2016, unknown): “A major motivation for this is that such a joint model would allow the simultaneous adaptation [4] and control [5] of rhythmic, melodic and phonetic characteristics in a stable and consistent way.”
On the training of DNN-based average voice model for speech synthesis (2016, methodology): “In [18], a prosodic controlling vector, which is similar to the idea of i-vectors, was introduced to DNN-based speech synthesis to control the global prosodic characteristics.”
Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis (2018, methodology): “2) We introduce and detail various theoretical connections between the techniques in [7], [10]–[12] and encoder-decoder models, particularly VQ-VAEs.”