The Blizzard Challenge 2013 - Indian Language Task
By Kishore Prahallad, Anandaswarup Vadapalli, Naresh Kumar Elluru, G. Mantena, Bhargav Pulugundla, P. Bhaskararao, Hema A. Murthy, Simon King, Vasilis Karaiskos, Alan W. Black. 2013
39 citations recorded by the source corpus.
The Blizzard challenge 2013 was the ninth annual Blizzard challenge which was organized by University of Edinburgh handling the English language tasks and IIIT Hyderabad handling the Indian language tasks. This paper decsribes the Indian language tasks in the Blizzard challenge 2013. The Indian language tasks consisted of data from four Indian languages : Hindi, Bengali, Kannada and Tamil taken from the IIIT-H Indic database. Eight participants from across the world used the speech data provided as well as the corresponding text data in UTF-8, to build synthetic voices, which were then evaluated by means of listening tests.
Subfields: Artificial Intelligence
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
- Yoshua Bengio
- Aaron C. Courville
- Sergey Levine
- Kyunghyun Cho
- Jianfeng Gao
- Stefano Ermon
- Mohit Bansal
- Hung-yi Lee
Citations in the corpus
- SampleRNN: An Unconditional End-to-End Neural Audio Generation Model (2016, methodology): “The description of each dataset and their preprocessing is as follows: Blizzard which is a dataset presented by Prahallad et al. (2013) for speech synthesis task, contains 315 hours of a single female voice actor in English; however, for our experiments we are using only 20.5 hours.”
- The Blizzard Challenge 2013 (2013, methodology): “[9] Kishore Prahallad, Anandaswarup Vadapalli, Naresh Elluru, Gautam Mantena, Bhargav Pulugundla, Peri Bhaskararao, Hema A.”
- A survey on speech synthesis techniques in Indian languages (2020, background): “[110] and Black and Tokuda [111] is presented on the associated challenges for designing corpus-based speech synthesis systems.”
- Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems (2020, methodology): “This corpus served as de-facto standard TTS corpus for Indian languages for a number of years (Prahallad et al., 2013).”