Overview
India is a land of language diversity, wherein it has around 1500 languages being spoken as a medium of communication. Out of which 22 languages are recognized as official languages by the Government of India. According to a recent census, 30 Indian languages have more than a million speakers. But most of the multi-media content on the internet is in English and most of the Indian languages have very little content on the internet. Hence, there is a need to develop Speech to speech translation systems in the Indian context to reduce the language barrier as the manual transcription process is expensive and time-consuming. Speech to speech translation is a very challenging problem due to variations in speech, context, etc. This workshop aims to encourage researchers to send papers related to issues in speech-to-speech translation.
Particular topics of interest of the workshop include (but not limited to):
- ASR and MT in SSMT
- Prosody information extraction
- Rich text from speech including punctuation marks
- Prosody information in machine translation
- Discourse in machine translation
- Speech to speech translation systems and their performance measures
- Disfluency detection from speech
- Speech synthesis with prosody
- Multi-lingual speech recognition and synthesis
- Open challenge related papers
Contact Address
Email:
wssmt.iiith@gmail.com