Ashwin Sankar
7 papers · 2024–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(15)
👥
Mega-Team · Legion
Top co-authors
Research topics
Speech & Audio
(5)
Natural Language Processing
(4)
Synthesis
(4)
Machine Learning
(3)
Resources & Methods
(3)
Artificial Intelligence
(2)
Application Areas
(2)
Applications
(2)
Learning Types · Machine Learning
(2)
Recognition
(2)
Deep Learning
(1)
Analysis
(1)
Core AI
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Keywords
speech synthesis
(3)
low-resource language
(3)
indian language
(3)
expressive speech
(2)
speech dataset
(2)
multilingual speech
(2)
speech enhancement
(1)
synthetic data
(1)
pre-trained language model
(1)
domain shift
(1)
text-to-speech synthesis
(1)
speaker generalization
(1)
speech-to-speech translation
(1)
multilingual model
(1)
shared task
(1)
speech translation
(1)
speaker adaptation
(1)
multilingual system
(1)
spoken language translation
(1)
shared task evaluation
(1)
Papers
Findings of the IWSLT 2025 Evaluation Campaign
ACL 2025
Mark My Words: A Robust Multilingual Model for Punctuation in Text and Speech Transcripts
IJCNLP 2025
Rasmalai : Resources for Adaptive Speech Modeling in IndiAn Languages with Accents and Intonations
Interspeech 2025
Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages
ACL 2025
Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies
Interspeech 2024
IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
NeurIPS 2024
Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings
Interspeech 2024