Experimental and theoretical advances in prosody: A review
By Michael Wagner, Duane G. Watson. 2010
344 citations recorded by the source corpus.
Research on prosody has recently become an important focus in various disciplines, including Linguistics, Psychology, and Computer Science. This article reviews recent research advances on two key issues: prosodic phrasing and prosodic prominence. Both aspects of prosody are influenced by linguistic factors such as syntactic constituent structure, semantic relations, phonological rhythm, pragmatic considerations, and also by processing factors such as the length, complexity, or predictability of linguistic material. Our review summarises recent insights into the production and perception of these two components of prosody and their grammatical underpinnings. While this review only covers a subset of a broader set of research topics on prosody in cognitive science, these topics are representative of a tendency in the field towards a more interdisciplinary approach.
Subfields: Artificial Intelligence, Cognitive Neuroscience, Experimental and Cognitive Psychology
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 Cognitive Neuroscience
In Experimental and Cognitive Psychology
Citations in the corpus
- A Survey on Neural Speech Synthesis (2021, background): “• Prosody, style, and emotion information, which covers the intonation, stress, and rhythm of speech and represents how to say the text [365, 175].”
- Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron (2018, neutral): “This view of prosody is compatible with interpretations of prosody from previous works (Wagner & Watson, 2010; Ladd, 2008).”
- Generating Diverse and Natural Text-to-Speech Samples Using a Quantized Fine-Grained VAE and Autoregressive Prosody Prior (2020, background): “Prosody [10] collectively refers to stress, intonation and rhythm in speech.”
- Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis (2020, background): “The focus of this paper, prosody, is a collection of attributes including fundamental frequency (F0), energy and duration [9].”
- Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations (2019, methodology): “…methods utilizing acoustic features seem to provide better performance for the unsupervised detection of prominences in speech (Suni et al., 2017; Wang and Narayanan, 2007; Kakouros and Räsänen, 2016), with state-of-the-art results reaching high level of accuracy, close to that of the…”
- CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer (2022, positive): “We exploit the contextual information available in a sentence to predict its prosody, since it has been cogently hypothesised that prosody is driven by it [29].”
- Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis (2019, background): “These attributes convey linguistic, semantic, and emotional meaning beyond what is present in the lexical representation (i.e., the text) (Wagner & Watson, 2010).”
- Prosody conveys speaker's intentions: Acoustic cues for speech act perception (2014, background): “It conveys, for example, semantic 103 relationships (Cutler, Dahan, & van Donselaar, 1997; Wagner & Watson, 2010), disambiguates 104 the syntactic constituent structure (Carlson, Frazier, & Clifton, 2009), and marks declarative vs. 105 interrogative sentence mode (Schneider, Lintfert, Dogil, &…”
- Prosody in context: a review (2015, background): “Moreover, several studies have shown that the relative strength of prosodic boundaries internal to a complex sentence can disambiguate between competing syntactic structures for the sentence (Wagner, 2010; see Wagner & Watson, 2010 for a review).”