Text-to-speech synthesis
By Tunei Lin. 2006
48 citations recorded by the source corpus.
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
- Deep Voice: Real-time Neural Text-to-Speech (2017, methodology): “…Voice is inspired by traditional text-to-speech pipelines and adopts the same structure, while replacing all components with neural networks and using simpler features: first we convert text to phoneme and then use an audio synthesis model to convert linguistic features into speech (Taylor, 2009).”
- LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech (2019, methodology): “, abbreviations, numbers and currency expressions) and semiotic classes [36] (text tokens and token sequences that represent particular entities that are semantically constrained, such as measure phrases, addresses and dates) in the sentences are detected and normalized by a weighted finite state tr”
- Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis (2018, background): “Proper stylistic rendering affects overall perception (see e.g. “affective prosody” in (Taylor, 2009)), which is important for applications such as audiobooks and newsreaders.”
- ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech (2018, background): “Speech synthesis, also called text-to-speech (TTS), is traditionally done with complex multi-stage hand-engineered pipelines (Taylor, 2009).”
- Automatic Building of Synthetic Voices from Audio Books (2010, background): “There is no general theory which explains the correspondence between syntax and prosody [Bachenko and Fitzpatrick, 1990], [Taylor, 2009].”
- Unsupervised Learning for Expressive Speech Synthesis (2017, background): “Well known variations of the intonation contour are: The overall declination, often attributed to the sub-glottal pressure decline, as for instance according to Taylor (2009); stress marks as pitch movements; descent at the end of a phrase except if the phrase is an echo question with a rising conto”
- RNN Approaches to Text Normalization: A Challenge (2016, background): “In this case both examples are instances of the same semiotic class (Taylor, 2009), namely measure phrases.”