Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems.
Fei HeShan-Hui Cathy ChuOddur KjartanssonClara RiveraAnna KatanovaAlexander GutkinIsin DemirsahinCibu JohnyMartin JanscheSupheakmungkol SarinKnot PipatsrisawatPublished in: LREC (2020)
Keyphrases
- speech synthesis
- indian languages
- speech recognition
- prosodic features
- vocal tract
- open source
- text to speech
- language identification
- document images
- cross lingual
- character recognition
- speaker verification
- speech recognition systems
- automatic speech recognition
- handwritten characters
- speaker identification
- speech signal
- hidden markov models
- automatic speech recognition systems
- optical character recognition
- spoken language
- audio visual
- source code
- speech corpus
- automatic transcription
- noisy environments
- word segmentation
- neural network
- machine translation
- natural language processing
- image processing
- computer vision