Tongzhou Chen

On the Optimal Interpolation Weights for Hybrid Autoregressive Transducer Model

B. Ramabhadran, M. Riley, David Rybach, 2022 .

Modular Hybrid Autoregressive Transducer

B. Ramabhadran, P. Moreno, Rohit Prabhavalkar, 2022, ArXiv.

TOPICS ON THE LENGTH OF THE LONGEST COMMON SUBSEQUENCES, WITH BLOCKS, IN BINARY RANDOM WORDS

R. Foley, Chenyou Fan, C. Houdré, 2019 .

Mixture Model Attention: Flexible Streaming and Non-Streaming Automatic Speech Recognition

Bhuvana Ramabhadran, Kartik Audhkhasi, Pedro J. Moreno, 2021, Interspeech.

Improving Rare Word Recognition with LM-aware MWER Training

Tara N. Sainath, B. Ramabhadran, Rohit Prabhavalkar, 2022, INTERSPEECH.

Modular Hybrid Autoregressive Transducer

B. Ramabhadran, P. Moreno, Rohit Prabhavalkar, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Neural Oracle Search on N-BEST Hypotheses

Bhuvana Ramabhadran, Pedro J. Moreno, Ehsan Variani, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition

Tara N. Sainath, B. Ramabhadran, Rohit Prabhavalkar, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Large-Scale Language Model Rescoring on Long-Form Data

Pedro J. Moreno, B. Ramabhadran, M. Riley, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).