← authors · overview

• Direct Acoustics-to-Word Models for English Conversational Speech Recognition
  2017 · 114 citations
• Invariant Representations for Noisy Speech Recognition
  2016 · 66 citations
• Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
  2018 · 5 citations
• Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition
  2022 · 4 citations
• Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard
  2020 · 3 citations
• LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors
  2025
• Building competitive direct acoustics-to-word models for English conversational speech recognition
  2017
• Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition
  2019
• Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems
  2020
• Modular Hybrid Autoregressive Transducer
  2022
• O-1: Self-training with Oracle and 1-best Hypothesis
  2023
• STAB: Speech Tokenizer Assessment Benchmark
  2024