Darshan Prabhu
5 papers · 2023–2025 · 2 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
Venues
Top co-authors
Research topics
Keywords
automatic speech recognition
(3)
low-resource language
(2)
word error rate
(2)
large language model
(2)
accent adaptation
(2)
speech recognition
(2)
conformer model
(1)
end-to-end asr
(1)
local context
(1)
learnable codebook
(1)
accent invariance
(1)
synchronous decoding
(1)
token fertility gap
(1)
zero-shot transfer
(1)
self-supervised pretraining
(1)
parameter efficiency
(1)
codebook learning
(1)
convolution kernel
(1)
Papers
Skip-Salsa: Skip Synchronous Fusion of ASR LLM Decoders
Interspeech 2025
Improving Self-supervised Pre-training using Accent-Specific Codebooks
Interspeech 2024
MULTI-CONVFORMER: Extending Conformer with Multiple Convolution Kernels
Interspeech 2024
SALSA: Speedy ASR-LLM Synchronous Aggregation
Interspeech 2024
Accented Speech Recognition With Accent-specific Codebooks
EMNLP 2023