← Authors

Kartik Audhkhasi

18 papers · 2016–2025 · 2 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (2) πŸƒ Academic Marathon (9) πŸ—ΊοΈ Taxonomy Completionist (25) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸ”¬ Deep Specialist (13) 🧬 Topic Evolution πŸ† Keyword Champion (5) πŸ—ƒοΈ Keyword Collector (75) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ’Ž Century Club (18) πŸ”₯ Unstoppable (5) ⚑ Prolific Year (6)

Conferences

INTERSPEECH (17) EMNLP (1)

Top co-authors

Bhuvana Ramabhadran (8) Brian Kingsbury (7) Michael Picheny (6) ZoltΓ‘n TΓΌske (6) Samuel Thomas (6) George Saon (6) Gakuto Kurata (4) Yinghui Huang (4) Tongzhou Chen (2) Pedro J. Moreno (2)

Keywords

automatic speech recognition (10) speech recognition (7) connectionist temporal classification (6) word error rate (6) language model (4) data augmentation (3) neural network (3) end-to-end model (2) attention mechanism (2) long short-term memory (2) end-to-end speech recognition (2) multitask learning (1) spoken language understanding (1) deep learning (1) self-supervised learning (1) video retrieval (1) feature representation (1) model architecture (1) knowledge distillation (1) posterior fusion (1)

Papers

LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors EMNLP 2025
O-1: Self-training with Oracle and 1-best Hypothesis INTERSPEECH 2023
Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition INTERSPEECH 2022
Regularizing Word Segmentation by Creating Misspellings INTERSPEECH 2021
AVLnet: Learning Audio-Visual Language Representations from Instructional Videos INTERSPEECH 2021
Mixture Model Attention: Flexible Streaming and Non-Streaming Automatic Speech Recognition INTERSPEECH 2021
Transliteration Based Data Augmentation for Training Multilingual ASR Acoustic Models in Low Resource Settings INTERSPEECH 2020
Single Headed Attention Based Sequence-to-Sequence Model for State-of-the-Art Results on Switchboard INTERSPEECH 2020
End-to-End Spoken Language Understanding Without Full Transcripts INTERSPEECH 2020
Advancing Sequence-to-Sequence Based Speech Recognition INTERSPEECH 2019
Challenging the Boundaries of Speech Recognition: The MALACH Corpus INTERSPEECH 2019
Multi-Task CTC Training with Auxiliary Feature Reconstruction for End-to-End Speech Recognition INTERSPEECH 2019
Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation INTERSPEECH 2019
Forget a Bit to Learn Better: Soft Forgetting for CTC-Based Automatic Speech Recognition INTERSPEECH 2019
Detection and Recovery of OOVs for Improved English Broadcast News Captioning INTERSPEECH 2019
English Conversational Telephone Speech Recognition by Humans and Machines INTERSPEECH 2017
Direct Acoustics-to-Word Models for English Conversational Speech Recognition INTERSPEECH 2017
Multilingual Data Selection for Low Resource Speech Recognition INTERSPEECH 2016