Dhananjaya Gowda
12 papers · 2016–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Academic Marathon (9) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (2) π Cross-Pollinator (9)
πΊοΈ
Taxonomy Completionist
(21)
π
Conference Polyglot
(2)
π
Academic Marathon
(9)
π
Century Club
(12)
π
Conference Pioneer
ποΈ
Keyword Collector
(64)
Conferences
INTERSPEECH (11)
EMNLP (1)
Top co-authors
Research topics
Keywords
end-to-end speech recognition
(3)
attention mechanism
(2)
time-varying linear prediction
(2)
automatic speech recognition
(2)
word error rate
(2)
speaker verification
(2)
model compression
(2)
data augmentation
(1)
knowledge distillation
(1)
multi-task learning
(1)
speech analysis
(1)
speaker recognition
(1)
signal processing
(1)
linear prediction
(1)
inference efficiency
(1)
speech enhancement
(1)
parameter-efficient tuning
(1)
low-rank adaptation
(1)
parameter-efficient fine-tuning
(1)
autoregressive model
(1)
Papers
zFLoRA: Zero-Latency Fused Low-Rank Adapters
EMNLP 2025
Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction
INTERSPEECH 2023
Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition
INTERSPEECH 2022
Prototypical speaker-interference loss for target voice separation using non-parallel audio samples
INTERSPEECH 2022
Hierarchical Multi-Stage Word-to-Grapheme Named Entity Corrector for Automatic Speech Recognition
INTERSPEECH 2020
Utterance Invariant Training for Hybrid Two-Pass End-to-End Speech Recognition
INTERSPEECH 2020
Streaming On-Device End-to-End ASR System for Privacy-Sensitive Voice-Typing
INTERSPEECH 2020
Utterance Confidence Measure for End-to-End Speech Recognition with Applications to Distributed Speech Recognition Scenarios
INTERSPEECH 2020
Multi-Task Multi-Resolution Char-to-BPE Cross-Attention Decoder for End-to-End Speech Recognition
INTERSPEECH 2019
Improved Vocal Tract Length Perturbation for a State-of-the-Art End-to-End Speech Recognition System
INTERSPEECH 2019
Time-Varying Autoregressions for Speaker Verification in Reverberant Conditions
INTERSPEECH 2017
Time-Varying Quasi-Closed-Phase Weighted Linear Prediction Analysis of Speech for Accurate Formant Detection and Tracking
INTERSPEECH 2016