15 citations
- Indian Institute of Technology BombayIN1 paper
- Indian Institute of Technology GuwahatiIN1 paper
- Indian Institute of Technology KanpurIN1 paper
- Newcastle UniversityGB1 paper
- Sikkim Manipal UniversityIN1 paper
- University of Newcastle AustraliaAU1 paper
- University of North TexasUS1 paper
- University of WolverhamptonGB1 paper
7 papers · 1 filter
LIP: Lightweight Intelligent Preprocessor for meaningful text-to-speech
Harshvardhan Anand, Nansi Begam, Richa Verma +3
Existing Text-to-Speech (TTS) systems need to read messages from the email which may have Personal Identifiable Information (PII) to text messages that can have a streak of emojis…
Adaptive Beam Search to Enhance On-device Abstractive Summarization
Harichandana B S S, Sumit Kumar
We receive several essential updates on our smartphones in the form of SMS, documents, voice messages, etc. that get buried beneath the clutter of content. We often do not realize…
VoiceMoji: A Novel On-Device Pipeline for Seamless Emoji Insertion in Dictation
Sumit Kumar, Harichandana B S S, Himanshu Arora
Most of the speech recognition systems recover only words in the speech and fail to capture emotions. Users have to manually add emoji(s) in text for adding tone and making communi…
Real-Time Optimized N-gram For Mobile Devices
Sharmila Mani, Sourabh Vasant Gothe, Sourav Ghosh +4
With the increasing number of mobile devices, there has been continuous research on generating optimized Language Models (LMs) for soft keyboard. In spite of advances in this domai…
Language Detection Engine for Multilingual Texting on Mobile Devices
Sourabh Vasant Gothe, Sourav Ghosh, Sharmila Mani +3
More than 2 billion mobile users worldwide type in multiple languages in the soft keyboard. On a monolingual keyboard, 38% of falsely auto-corrected words are valid in another lang…
edATLAS: An Efficient Disambiguation Algorithm for Texting in Languages with Abugida Scripts
Sourav Ghosh, Sourabh Vasant Gothe, Chandramouli Sanchi +1
Abugida refers to a phonogram writing system where each syllable is represented using a single consonant or typographic ligature, along with a default vowel or optional diacritic(s…