Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Bhuvana Ramabhadran

Bhuvana Ramabhadran

Modular Hybrid Autoregressive Transducer

Oct 31, 2022
Zhong Meng, Tongzhou Chen, Rohit Prabhavalkar, Yu Zhang, Gary Wang, Kartik Audhkhasi, Jesse Emond, Trevor Strohman, Bhuvana Ramabhadran, W. Ronny Huang, Ehsan Variani, Yinghui Huang, Pedro J. Moreno

Figure 1 for Modular Hybrid Autoregressive Transducer

Figure 2 for Modular Hybrid Autoregressive Transducer

Figure 3 for Modular Hybrid Autoregressive Transducer

Figure 4 for Modular Hybrid Autoregressive Transducer

* 2022 IEEE Spoken Language Technology Workshop (SLT), Doha, Qatar
* 8 pages, 1 figure, SLT 2022

Access Paper or Ask Questions

Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech

Oct 27, 2022
Takaaki Saeki, Heiga Zen, Zhehuai Chen, Nobuyuki Morioka, Gary Wang, Yu Zhang, Ankur Bapna, Andrew Rosenberg, Bhuvana Ramabhadran

Figure 1 for Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech

Figure 2 for Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech

Figure 3 for Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech

Figure 4 for Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech

* Submitted to ICASSP 2023

Access Paper or Ask Questions

G-Augment: Searching For The Meta-Structure Of Data Augmentation Policies For ASR

Oct 19, 2022
Gary Wang, Ekin D. Cubuk, Andrew Rosenberg, Shuyang Cheng, Ron J. Weiss, Bhuvana Ramabhadran, Pedro J. Moreno, Quoc V. Le, Daniel S. Park

Figure 1 for G-Augment: Searching For The Meta-Structure Of Data Augmentation Policies For ASR

Figure 2 for G-Augment: Searching For The Meta-Structure Of Data Augmentation Policies For ASR

Figure 3 for G-Augment: Searching For The Meta-Structure Of Data Augmentation Policies For ASR

Figure 4 for G-Augment: Searching For The Meta-Structure Of Data Augmentation Policies For ASR

* 6 pages, accepted at SLT 2022

Access Paper or Ask Questions

Non-Parallel Voice Conversion for ASR Augmentation

Sep 15, 2022
Gary Wang, Andrew Rosenberg, Bhuvana Ramabhadran, Fadi Biadsy, Yinghui Huang, Jesse Emond, Pedro Moreno Mengibar

Figure 1 for Non-Parallel Voice Conversion for ASR Augmentation

Figure 2 for Non-Parallel Voice Conversion for ASR Augmentation

Figure 3 for Non-Parallel Voice Conversion for ASR Augmentation

Figure 4 for Non-Parallel Voice Conversion for ASR Augmentation

* Accepted by Interspeech 2022

Access Paper or Ask Questions

Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition

Sep 13, 2022
Kartik Audhkhasi, Yinghui Huang, Bhuvana Ramabhadran, Pedro J. Moreno

Figure 1 for Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition

Figure 2 for Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition

Figure 3 for Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition

Figure 4 for Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition

* Accepted for publication in Interspeech 2022

Access Paper or Ask Questions

Improving Rare Word Recognition with LM-aware MWER Training

Apr 15, 2022
Weiran Wang, Tongzhou Chen, Tara N. Sainath, Ehsan Variani, Rohit Prabhavalkar, Ronny Huang, Bhuvana Ramabhadran, Neeraj Gaur, Sepand Mavandadi, Cal Peyser, Trevor Strohman, Yanzhang He, David Rybach

Figure 1 for Improving Rare Word Recognition with LM-aware MWER Training

Figure 2 for Improving Rare Word Recognition with LM-aware MWER Training

Figure 3 for Improving Rare Word Recognition with LM-aware MWER Training

Figure 4 for Improving Rare Word Recognition with LM-aware MWER Training

* In submission to INTERSPEECH 2022

Access Paper or Ask Questions

MAESTRO: Matched Speech Text Representations through Modality Matching

Apr 07, 2022
Zhehuai Chen, Yu Zhang, Andrew Rosenberg, Bhuvana Ramabhadran, Pedro Moreno, Ankur Bapna, Heiga Zen

Figure 1 for MAESTRO: Matched Speech Text Representations through Modality Matching

Figure 2 for MAESTRO: Matched Speech Text Representations through Modality Matching

Figure 3 for MAESTRO: Matched Speech Text Representations through Modality Matching

Figure 4 for MAESTRO: Matched Speech Text Representations through Modality Matching

* Submitted to Interspeech 2022

Access Paper or Ask Questions