Automatic Speech Recognition (ASR) is an impressive achievement of computer science, bringing together signal processing, machine-learning algorithms and computing hardware, to realize systems that effectively translate speech into text. While we can create functional ASR systems today in several languages, they are still far from human-level performance in various scenarios. Also, building an ASR system remains too expensive and data-intensive to be appropriate for low-resource languages. At CSALT, we focus on the machine-learning components that can improve ASR performance. We also focus on developing speech processing techniques for low-resource languages, together with addressing broader technical challenges that emerge when only limited amounts of data are available. More generally, we also explore the interactions between speech and text.
People
Associate Professor
Research: Machine learning applied to speech and natural language
Research: Machine learning applied to speech and natural language
Preethi
PhD student
Research: Domain adaptation for speech recognition
Research: Domain adaptation for speech recognition
Vinit
PhD student
Research: Computational models for code-switched data
Research: Computational models for code-switched data
Barah
PhD student
Research: Improving Low-resource ASR/NLP for conversational and code-switched data
Research: Improving Low-resource ASR/NLP for conversational and code-switched data
Ashish
PhD student
Research: Cross-lingual Transfer for Low-resource Languages
Research: Cross-lingual Transfer for Low-resource Languages
Sona
PhD student
Research: Shallow NLP for extremely low-resource languages
Research: Shallow NLP for extremely low-resource languages
Sanjeev
PhD student
Research: New architectures for ASR
Research: New architectures for ASR
Darshan
3rd yr MTech student
Research: Accented speech processing
Research: Accented speech processing
Abhishek
2nd yr MS student
Research: Cross-lingual NLP
Research: Cross-lingual NLP
Snegha
2nd yr MS student
Research: Cross-lingual NLP
Research: Cross-lingual NLP
Soumen
5th yr BTech student
Research: Speech foundation models
Research: Speech foundation models
Amruta
5th yr BTech student
Research: Speech foundation models
Research: Speech foundation models
Sameep
4th yr BTech student
Research: Multilingual NLP in LLMs
Research: Multilingual NLP in LLMs
Sabyasachi
4th yr BTech student
Research: Equivariant and Invariant learning for speech
Research: Equivariant and Invariant learning for speech
Harsh
4th yr BTech student
Research: Accented ASR using codebooks
Research: Accented ASR using codebooks
Pulkit
4th yr BTech student
Research: Accented ASR using codebooks
Research: Accented ASR using codebooks
Priyanshu
4th yr BTech student
Research: Code-switched detection
Research: Code-switched detection
Adyasha
4th yr BTech student
Research: Accented ASR using codebooks
Research: Accented ASR using codebooks
Omkar
4th yr BTech student
Research: Voice transfer for dialectal speech
Research: Voice transfer for dialectal speech
Azeem
4th yr BTech student
Research: Voice transfer for dialectal speech
Research: Voice transfer for dialectal speech
Sahil
4th yr BTech student
Research: Discrete speech codecs for ASR
Research: Discrete speech codecs for ASR
