The Blizzard Challenge 2012
By Simon King, Vasilis Karaiskos. 2012
55 citations recorded by the source corpus.
The Blizzard Challenge 2012 was the eighth annual Blizzard Challenge which was once again organised by the University of Edinburgh with assistance from the other members of the Bliz- zard Challenge committee - Prof. Keiichi Tokuda and Prof. Alan Black. One single-speaker English corpus was used, created from audiobook recordings on the Librivox website. Besides the main task of creating synthetic voices from these data, participants were invited to propose novel forms of evaluation. Index Terms: Blizzard Challenge, speech synthesis, evaluation, listening test
Subfields: Evaluation & Benchmarks, 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 Evaluation & Benchmarks
- Daniel Povey
- Sanjeev Khudanpur
- James R. Glass
- Gabriel Synnaeve
- Hung-yi Lee
- Yu-An Chung
- Ronan Collobert
- Sebastian Möller
In Speech & Audio
- Sanjeev Khudanpur
- Daniel Povey
- Guoguo Chen
- Sebastian Möller
- Gabriel Mittag
- Oliver Watts
- Adèle Aubin
- Alessandra Cervone
Citations in the corpus
- Librispeech: An ASR corpus based on public domain audio books (2015, methodology): “Although the use of audio books for building synthetic voice s [1, 2] has previously been investigated, we are not aware of any f reely available read speech corpus in English that is suitable for training and testing speech recognition systems, and which is as larg e scale as the one we present her”
- The Blizzard Challenge 2013 - Indian Language Task (2013, unknown): “[1–9] are summary papers which provide information about the previous challenges.”
- Improving Speech Synthesis with Discourse Relations (2019, methodology): “We chose the corpus from the Blizzard Challenge 2012 [18], which includes four audiobooks, read by the same American English male speaker and freely available on LibriVox.”
- Deep Learning Based Assessment of Synthetic Speech Naturalness (2020, methodology): “We used all available results of the Blizzard Challenge3 [22, 23, 24, 25, 26, 27, 28, 29, 30, 31], which are currently all years except for 2017 and 2018 (see Table 2).”