The German Text-to-Speech Synthesis System MARY: A Tool for Research, Development and Teaching

By Marc Schröder, Jürgen Trouvain. International Journal of Speech Technology, 2003

512 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/98a067775710886ee7d24f123b7a09116415ab2e

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

Redefining the Linguistic Context Feature Set for HMM and DNN TTS Through Position and Parsing (2016, unknown): “Festival [18] and Flite [19] are exactly equivalent, and Idlak [20] uses a subset of the Festival/Flite set, while MaryTTS [21] is overall very similar to Festival/Flite.”
Generation of landmark-based navigation instructions from open-source data (2012, methodology): “The generated instructions were converted to speech using MARY, an open-source text-to-speech sys-tem (Schr¨oder and Trouvain, 2003), and played back on loudspeakers.”
Phonological Features for 0-shot Multilingual Speech Synthesis (2020, methodology): “For test sentences in German, the lexicon from the German MARY-TTS voice [24] is used.”
Text-to-Speech Synthesis Using Found Data for Low-Resource Languages (2019, methodology): “The MaryTTS project (Schröder and Trouvain, 2003) aims to make available TTS data and modular toolkits in many languages for teaching and research.”
The HMM-based speech synthesis system (HTS) version 2.0 (2007, methodology): “[31] used the text analysis provided by the MARY software [32] instead of the Festival.”
To Err is Human(-like): Effects of Robot Gesture on Perceived Anthropomorphism and Likability (2013, methodology): “The robot’s speech was identical across conditions and was generated using the text-to-speech system MARY (Modular Architecture for Research on speech sYnthesis) [22] set to a neutral voice.”
Multimodal child-robot interaction: building social bonds (2013, methodology): “For speech synthesis we either use the commercial Acapella TTS system available on the Nao robot (Gouaillier et al., 2008), or the open source MARY TTS platform 5 (Schröder & Trouvain, 2003), with the latter allowing more control over prosody and voice quality.”