Alert button
Picture for Harish Arsikere

Harish Arsikere

Alert button

Unified Modeling of Multi-Domain Multi-Device ASR Systems

May 13, 2022
Soumyajit Mitra, Swayambhu Nath Ray, Bharat Padi, Arunasish Sen, Raghavendra Bilgi, Harish Arsikere, Shalini Ghosh, Ajay Srinivasamurthy, Sri Garimella

Figure 1 for Unified Modeling of Multi-Domain Multi-Device ASR Systems
Figure 2 for Unified Modeling of Multi-Domain Multi-Device ASR Systems
Figure 3 for Unified Modeling of Multi-Domain Multi-Device ASR Systems
Figure 4 for Unified Modeling of Multi-Domain Multi-Device ASR Systems
Viaarxiv icon

Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End

May 14, 2021
Swayambhu Nath Ray, Minhua Wu, Anirudh Raju, Pegah Ghahremani, Raghavendra Bilgi, Milind Rao, Harish Arsikere, Ariya Rastrow, Andreas Stolcke, Jasha Droppo

Figure 1 for Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Figure 2 for Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Figure 3 for Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Figure 4 for Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Viaarxiv icon

REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling

Dec 14, 2020
Hu Hu, Xuesong Yang, Zeynab Raeesy, Jinxi Guo, Gokce Keskin, Harish Arsikere, Ariya Rastrow, Andreas Stolcke, Roland Maas

Figure 1 for REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
Figure 2 for REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
Viaarxiv icon

Knowledge Distillation and Data Selection for Semi-Supervised Learning in CTC Acoustic Models

Aug 10, 2020
Prakhar Swarup, Debmalya Chakrabarty, Ashtosh Sapru, Hitesh Tulsiani, Harish Arsikere, Sri Garimella

Figure 1 for Knowledge Distillation and Data Selection for Semi-Supervised Learning in CTC Acoustic Models
Figure 2 for Knowledge Distillation and Data Selection for Semi-Supervised Learning in CTC Acoustic Models
Figure 3 for Knowledge Distillation and Data Selection for Semi-Supervised Learning in CTC Acoustic Models
Figure 4 for Knowledge Distillation and Data Selection for Semi-Supervised Learning in CTC Acoustic Models
Viaarxiv icon

Streaming End-to-End Bilingual ASR Systems with Joint Language Identification

Jul 08, 2020
Surabhi Punjabi, Harish Arsikere, Zeynab Raeesy, Chander Chandak, Nikhil Bhave, Ankish Bansal, Markus Müller, Sergio Murillo, Ariya Rastrow, Sri Garimella, Roland Maas, Mat Hans, Athanasios Mouchtaris, Siegfried Kunzmann

Figure 1 for Streaming End-to-End Bilingual ASR Systems with Joint Language Identification
Figure 2 for Streaming End-to-End Bilingual ASR Systems with Joint Language Identification
Figure 3 for Streaming End-to-End Bilingual ASR Systems with Joint Language Identification
Viaarxiv icon

Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition

Dec 02, 2019
Surabhi Punjabi, Harish Arsikere, Sri Garimella

Figure 1 for Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition
Figure 2 for Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition
Figure 3 for Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition
Figure 4 for Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition
Viaarxiv icon