Festival Speech Synthesis System

By Alan W. Black, Paul A. Taylor, R. Caley. 1998

How researchers see this paper

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

Citations in the corpus

Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding (2016, methodology): “TTS front-end [59], and the resulting phonetic labels were used for training of the synthesis DNN.”
Towards robotic assistants in nursing homes: Challenges and results (2003, methodology): “On the software side, the robot features off-theshelf autonomous mobile robot navigation system (5; 29), speech recognition software (25), speech synthesis software (4), fast image capture and compression software for online video streaming, face detection tracking software (26), as well as the thre”
Experiences with a mobile robotic guide for the elderly (2002, background): “…both robots feature off-the-shelf autonomous mobile robot navigation system [5] [24], speech recognition software [20], speech synthesis software [3], fast image capture and compression software for online video streaming, face detection tracking software [21], and various new software modules…”
The HMM-based speech synthesis system (HTS) version 2.0 (2007, background): “– HTS voices for the Festival speech synthesis system [26].”
Spoken Dialogue Management Using Probabilistic Reasoning (2000, methodology): “Flo uses the Sphinx II speech recognition system (Ravishankar, 1996), and the Festival speech synthesis system (Black et al., 1999).”
Normalization of non-standard words (2001, background): “The second system is Festival (Black et al., 1999), a publicly available text-to-speech synthesis system.”
Improving Emotional TTS with an Emotion Intensity Input from Unsupervised Extraction (2021, methodology): “99 ], which were derived from the forced-aligned (with HTK [28]) phoneme sequence previously extracted with Festival [29].”
Identifying speakers in children's stories for speech synthesis (2003, methodology): “ESPER is implemented within the Festival Speech Synthesis framework [4].”
The voice bank corpus: Design, collection and data analysis of a large regional accent speech database (2013, methodology): “ICASSP-95, pp.81-84 1995 [7] D’Arcy S., Russel M. J., Browning S. R., Tomlinson, M. J., “The Accents of the British Isles (ABI) corpus”, Proc MIDL, Paris, 2004 [8] Weinberger, S., “George Mason University’s Speech Accent Archive”, George Mason University, 2013 [9] Black, A. W. and Taylor, P., “The F”
Exploiting Acoustic and Syntactic Features for Prosody Labeling in a Maximum Entropy Framework (2007, background): “Festival (Black et al., 1998) and AT&T Natural Voices R © (NV) speech synthesizer (att, ) are two publicly available speech synthesizers that have a prosody prediction module available.”
Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis (2009, methodology): “We used the U.S. English phone set “radio” of the Festival speech synthesis system [61], and obtained the phonetic and linguistic contexts from Fes-tival utterance ﬁles (as distributed with these corpora) without any modiﬁcations.”
CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network (2019, methodology): “This could be considered a step backwards from earlier approaches, for example: (Black et al., 1998; Van Santen, 1994; Goubanova & King, 2008) Additionaly, in these models F0 is considered as just another acoustic feature, i.e., a local feature of a contextdependent phone, rather than a…”