Alert button
Picture for Kartik Audhkhasi

Kartik Audhkhasi

Alert button

Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation

Apr 17, 2019
Gakuto Kurata, Kartik Audhkhasi

Figure 1 for Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation
Figure 2 for Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation
Figure 3 for Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation
Figure 4 for Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation
Viaarxiv icon

Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition

Mar 29, 2019
Shane Settle, Kartik Audhkhasi, Karen Livescu, Michael Picheny

Figure 1 for Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition
Figure 2 for Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition
Figure 3 for Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition
Figure 4 for Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition
Viaarxiv icon

Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition

Feb 07, 2018
Xuesong Yang, Kartik Audhkhasi, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Mark Hasegawa-Johnson

Figure 1 for Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
Figure 2 for Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
Figure 3 for Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
Figure 4 for Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
Viaarxiv icon

Building competitive direct acoustics-to-word models for English conversational speech recognition

Dec 08, 2017
Kartik Audhkhasi, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Michael Picheny

Figure 1 for Building competitive direct acoustics-to-word models for English conversational speech recognition
Figure 2 for Building competitive direct acoustics-to-word models for English conversational speech recognition
Figure 3 for Building competitive direct acoustics-to-word models for English conversational speech recognition
Figure 4 for Building competitive direct acoustics-to-word models for English conversational speech recognition
Viaarxiv icon

Direct Acoustics-to-Word Models for English Conversational Speech Recognition

Mar 22, 2017
Kartik Audhkhasi, Bhuvana Ramabhadran, George Saon, Michael Picheny, David Nahamoo

Figure 1 for Direct Acoustics-to-Word Models for English Conversational Speech Recognition
Figure 2 for Direct Acoustics-to-Word Models for English Conversational Speech Recognition
Figure 3 for Direct Acoustics-to-Word Models for English Conversational Speech Recognition
Figure 4 for Direct Acoustics-to-Word Models for English Conversational Speech Recognition
Viaarxiv icon

English Conversational Telephone Speech Recognition by Humans and Machines

Mar 06, 2017
George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi, Phil Hall

Figure 1 for English Conversational Telephone Speech Recognition by Humans and Machines
Figure 2 for English Conversational Telephone Speech Recognition by Humans and Machines
Figure 3 for English Conversational Telephone Speech Recognition by Humans and Machines
Figure 4 for English Conversational Telephone Speech Recognition by Humans and Machines
Viaarxiv icon

End-to-End ASR-free Keyword Search from Speech

Jan 13, 2017
Kartik Audhkhasi, Andrew Rosenberg, Abhinav Sethy, Bhuvana Ramabhadran, Brian Kingsbury

Figure 1 for End-to-End ASR-free Keyword Search from Speech
Figure 2 for End-to-End ASR-free Keyword Search from Speech
Figure 3 for End-to-End ASR-free Keyword Search from Speech
Figure 4 for End-to-End ASR-free Keyword Search from Speech
Viaarxiv icon

Invariant Representations for Noisy Speech Recognition

Nov 27, 2016
Dmitriy Serdyuk, Kartik Audhkhasi, Philémon Brakel, Bhuvana Ramabhadran, Samuel Thomas, Yoshua Bengio

Figure 1 for Invariant Representations for Noisy Speech Recognition
Figure 2 for Invariant Representations for Noisy Speech Recognition
Viaarxiv icon

Diverse Embedding Neural Network Language Models

Apr 15, 2015
Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran

Figure 1 for Diverse Embedding Neural Network Language Models
Figure 2 for Diverse Embedding Neural Network Language Models
Figure 3 for Diverse Embedding Neural Network Language Models
Figure 4 for Diverse Embedding Neural Network Language Models
Viaarxiv icon

Generalized Ambiguity Decomposition for Understanding Ensemble Diversity

Dec 28, 2013
Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth S. Narayanan

Figure 1 for Generalized Ambiguity Decomposition for Understanding Ensemble Diversity
Figure 2 for Generalized Ambiguity Decomposition for Understanding Ensemble Diversity
Figure 3 for Generalized Ambiguity Decomposition for Understanding Ensemble Diversity
Figure 4 for Generalized Ambiguity Decomposition for Understanding Ensemble Diversity
Viaarxiv icon