← Authors

Bhuvana Ramabhadran

41 papers · 2009–2025 · 3 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (12) πŸƒ Academic Marathon (16) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (3) 🌈 Renaissance Researcher (6) πŸ—ΊοΈ Taxonomy Completionist (15) 🏠 Conference Loyalist (36) 🀝 Dynamic Duo (16) 🧬 Topic Evolution πŸ”¬ Deep Specialist (25) πŸ—ƒοΈ Keyword Collector (56) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ”₯ Unstoppable (10) ⚑ Prolific Year (8) ❓ The Questioner πŸ’Ž Century Club (41)

Conferences

INTERSPEECH (36) NAACL (4) EMNLP (1)

Top co-authors

Andrew Rosenberg (16) Pedro J. Moreno (10) Kartik Audhkhasi (8) Yu Zhang (6) Gary Wang (6) Zhehuai Chen (6) Yinghui Huang (5) Samuel Thomas (5) Abhinav Sethy (5) Gakuto Kurata (5)

Keywords

automatic speech recognition (16) speech recognition (8) word error rate (6) data augmentation (6) language model (5) domain adaptation (4) long short-term memory (4) connectionist temporal classification (4) convolutional neural network (4) text injection (3) semi-supervised learning (3) neural network (3) self-supervised learning (2) data selection (2) text-to-speech synthesis (2) voice conversion (2) modality alignment (2) representation learning (2) knowledge distillation (2) acoustic modeling (2)

Papers

LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors EMNLP 2025
ASTRA: Aligning Speech and Text Representations for Asr without Sampling INTERSPEECH 2024
Contemplative Mechanism for Speech Recognition: Speech Encoders can Think INTERSPEECH 2024
Text Injection for Neural Contextual Biasing INTERSPEECH 2024
Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions INTERSPEECH 2024
Speculative Speech Recognition by Audio-Prefixed Low-Rank Adaptation of Language Models INTERSPEECH 2024
Using Text Injection to Improve Recognition of Personal Identifiers in Speech INTERSPEECH 2023
O-1: Self-training with Oracle and 1-best Hypothesis INTERSPEECH 2023
MAESTRO: Matched Speech Text Representations through Modality Matching INTERSPEECH 2022
Non-Parallel Voice Conversion for ASR Augmentation INTERSPEECH 2022
Reducing Domain mismatch in Self-supervised speech pre-training INTERSPEECH 2022
On Adaptive Weight Interpolation of the Hybrid Autoregressive Transducer INTERSPEECH 2022
Improving Rare Word Recognition with LM-aware MWER Training INTERSPEECH 2022
Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition INTERSPEECH 2022
Mixture Model Attention: Flexible Streaming and Non-Streaming Automatic Speech Recognition INTERSPEECH 2021
Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation INTERSPEECH 2021
Self-Adaptive Distillation for Multilingual Speech Recognition: Leveraging Student Independence INTERSPEECH 2021
Regularizing Word Segmentation by Creating Misspellings INTERSPEECH 2021
Conformer Parrotron: A Faster and Stronger End-to-End Speech Conversion and Recognition Model for Atypical Speech INTERSPEECH 2021
Multilingual Speech Recognition with Self-Attention Structured Parameterization INTERSPEECH 2020
SCADA: Stochastic, Consistent and Adversarial Data Augmentation to Improve ASR INTERSPEECH 2020
Improving Speech Recognition Using GAN-Based Speech Synthesis and Contrastive Unspoken Text Selection INTERSPEECH 2020
Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model INTERSPEECH 2019
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning INTERSPEECH 2019
Open Problems in Speech Recognition INTERSPEECH 2018
Data Augmentation Improves Recognition of Foreign Accented Speech INTERSPEECH 2018
English Conversational Telephone Speech Recognition by Humans and Machines INTERSPEECH 2017
Weakly-Supervised Phrase Assignment from Text in a Speech-Synthesis System Using Noisy Labels INTERSPEECH 2017
Bias and Statistical Significance in Evaluating Speech Synthesis with Mean Opinion Scores INTERSPEECH 2017
Efficient Knowledge Distillation from an Ensemble of Teachers INTERSPEECH 2017
Symbol Sequence Search from Telephone Conversation INTERSPEECH 2017
Direct Acoustics-to-Word Models for English Conversational Speech Recognition INTERSPEECH 2017
Empirical Exploration of Novel Architectures and Objectives for Language Models INTERSPEECH 2017
Fast Neural Network Language Model Lookups at N-Gram Speeds INTERSPEECH 2017
Domain Adaptation of CNN Based Acoustic Models Under Limited Resource Settings INTERSPEECH 2016
Acoustic Modeling Using Bidirectional Gated Recurrent Convolutional Units INTERSPEECH 2016
Multilingual Data Selection for Low Resource Speech Recognition INTERSPEECH 2016
Deep Neural Network Language Models NAACL 2012
Proceedings of the NAACL-HLT 2012 Workshop: Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT NAACL 2012
Unsupervised Model Adaptation using Information-Theoretic Criterion NAACL 2010
Fast decoding for open vocabulary spoken term detection NAACL 2009