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

Add to Chrome

Add to Firefox

Picture for Florian Metze

Florian Metze

Multimodal Abstractive Summarization for How2 Videos

Jun 19, 2019
Shruti Palaskar, Jindrich Libovický, Spandana Gella, Florian Metze

Figure 1 for Multimodal Abstractive Summarization for How2 Videos

Figure 2 for Multimodal Abstractive Summarization for How2 Videos

Figure 3 for Multimodal Abstractive Summarization for How2 Videos

Figure 4 for Multimodal Abstractive Summarization for How2 Videos

* To appear in ACL 2019

Access Paper or Ask Questions

Acoustic-to-Word Models with Conversational Context Information

May 21, 2019
Suyoun Kim, Florian Metze

Figure 1 for Acoustic-to-Word Models with Conversational Context Information

Figure 2 for Acoustic-to-Word Models with Conversational Context Information

Figure 3 for Acoustic-to-Word Models with Conversational Context Information

Figure 4 for Acoustic-to-Word Models with Conversational Context Information

* NAACL 2019. arXiv admin note: text overlap with arXiv:1808.02171

Access Paper or Ask Questions

Phoneme Level Language Models for Sequence Based Low Resource ASR

Feb 20, 2019
Siddharth Dalmia, Xinjian Li, Alan W Black, Florian Metze

Figure 1 for Phoneme Level Language Models for Sequence Based Low Resource ASR

Figure 2 for Phoneme Level Language Models for Sequence Based Low Resource ASR

Figure 3 for Phoneme Level Language Models for Sequence Based Low Resource ASR

Figure 4 for Phoneme Level Language Models for Sequence Based Low Resource ASR

* To appear in ICASSP 2019

Access Paper or Ask Questions

Learned In Speech Recognition: Contextual Acoustic Word Embeddings

Feb 18, 2019
Shruti Palaskar, Vikas Raunak, Florian Metze

Figure 1 for Learned In Speech Recognition: Contextual Acoustic Word Embeddings

Figure 2 for Learned In Speech Recognition: Contextual Acoustic Word Embeddings

Figure 3 for Learned In Speech Recognition: Contextual Acoustic Word Embeddings

Figure 4 for Learned In Speech Recognition: Contextual Acoustic Word Embeddings

* Accepted at ICASSP 2019, 5 pages, 1 figure, 3 tables

Access Paper or Ask Questions

Multimodal Grounding for Sequence-to-Sequence Speech Recognition

Nov 09, 2018
Ozan Caglayan, Ramon Sanabria, Shruti Palaskar, Loïc Barrault, Florian Metze

Figure 1 for Multimodal Grounding for Sequence-to-Sequence Speech Recognition

Figure 2 for Multimodal Grounding for Sequence-to-Sequence Speech Recognition

Figure 3 for Multimodal Grounding for Sequence-to-Sequence Speech Recognition

Figure 4 for Multimodal Grounding for Sequence-to-Sequence Speech Recognition

* Submitted to ICASSP 2019

Access Paper or Ask Questions

Domain Robust Feature Extraction for Rapid Low Resource ASR Development

Sep 30, 2018
Siddharth Dalmia, Xinjian Li, Florian Metze, Alan W. Black

Figure 1 for Domain Robust Feature Extraction for Rapid Low Resource ASR Development

Figure 2 for Domain Robust Feature Extraction for Rapid Low Resource ASR Development

Figure 3 for Domain Robust Feature Extraction for Rapid Low Resource ASR Development

Figure 4 for Domain Robust Feature Extraction for Rapid Low Resource ASR Development

* To appear in SLT 2018

Access Paper or Ask Questions

Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset

Sep 13, 2018
Ankit Shah, Harini Kesavamoorthy, Poorva Rane, Pramati Kalwad, Alexander Hauptmann, Florian Metze

Figure 1 for Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset

Figure 2 for Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset

Figure 3 for Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset

Figure 4 for Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset

* Action recognition submission for Moments in Time Dataset - Improved results over challenge submission

Access Paper or Ask Questions