Florian Metze

is this you? claim profile

∙ 0 followers
Facebook ∙ Carnegie Mellon University

Research Faculty at Carnegie Mellon University- School of Computer Science since 2009, Senior Research Scientist (T-Labs) at Technische Universität Berlin from 2006-2008, Research Scientist at Universität Karlsruhe (TH) from 1999-2005, Intern-Telecommunication strategy 1999, PhD in Computer Science at Universität Karlsruhe (TH) 1999-2005.

Featured Co-authors

Graham Neubig
163 publications
Andrea Vedaldi
101 publications
Shinji Watanabe
99 publications
Luke Zettlemoyer
78 publications
J. Zico Kolter
57 publications
Alan W Black
54 publications
Laurent Besacier
53 publications
Xavier Giro-i-Nieto
50 publications
Yiming Yang
48 publications
Eduard Hovy
48 publications
Lucia Specia
46 publications

Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks

End-to-end approaches for sequence tasks are becoming increasingly popul...
05/02/2021 ∙ by Siddharth Dalmia, et al. ∙ 7 ∙ share

read it
Self-supervised object detection from audio-visual correspondence

We tackle the problem of learning object detectors without supervision. ...
04/13/2021 ∙ by Triantafyllos Afouras, et al. ∙ 0 ∙ share

read it
Space-Time Crop Attend: Improving Cross-modal Video Representation Learning

The quality of the image representations obtained from self-supervised l...
03/18/2021 ∙ by Mandela Patrick, et al. ∙ 7 ∙ share

read it
Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models

This paper studies zero-shot cross-lingual transfer of vision-language m...
03/16/2021 ∙ by Po-Yao Huang, et al. ∙ 7 ∙ share

read it
Audio-Visual Event Recognition through the lens of Adversary

As audio/visual classification models are widely deployed for sensitive ...
11/15/2020 ∙ by Juncheng B. Li, et al. ∙ 0 ∙ share

read it
Multimodal Speech Recognition with Unstructured Audio Masking

Visual context has been shown to be useful for automatic speech recognit...
10/16/2020 ∙ by Tejas Srinivasan, et al. ∙ 16 ∙ share

read it
Support-set bottlenecks for video-text representation learning

The dominant paradigm for learning video-text representations – noise co...
10/06/2020 ∙ by Mandela Patrick, et al. ∙ 1 ∙ share

read it
Fine-Grained Grounding for Multimodal Speech Recognition

Multimodal automatic speech recognition systems integrate information fr...
10/05/2020 ∙ by Tejas Srinivasan, et al. ∙ 0 ∙ share

read it
Revisiting Factorizing Aggregated Posterior in Learning Disentangled Representations

In the problem of learning disentangled representations, one of the prom...
09/12/2020 ∙ by Ze Cheng, et al. ∙ 5 ∙ share

read it
How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language

Sign Language is the primary means of communication for the majority of ...
08/18/2020 ∙ by Amanda Duarte, et al. ∙ 20 ∙ share

read it
AlloVera: A Multilingual Allophone Database

We introduce a new resource, AlloVera, which provides mappings from 218 ...
04/17/2020 ∙ by David R. Mortensen, et al. ∙ 0 ∙ share

read it
ASR Error Correction and Domain Adaptation Using Machine Translation

Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are...
03/13/2020 ∙ by Anirudh Mani, et al. ∙ 7 ∙ share

read it
Universal Phone Recognition with a Multilingual Allophone System

Multilingual models can improve language processing, particularly for lo...
02/26/2020 ∙ by Xinjian Li, et al. ∙ 0 ∙ share

read it
Towards Zero-shot Learning for Automatic Phonemic Transcription

Automatic phonemic transcription tools are useful for low-resource langu...
02/26/2020 ∙ by Xinjian Li, et al. ∙ 0 ∙ share

read it
Looking Enhances Listening: Recovering Missing Speech Using Images

Speech is understood better by using visual context; for this reason, th...
02/13/2020 ∙ by Tejas Srinivasan, et al. ∙ 0 ∙ share

read it
Gun Source and Muzzle Head Detection

There is a surging need across the world for protection against gun viol...
01/29/2020 ∙ by Zhong Zhou, et al. ∙ 16 ∙ share

read it
Enforcing Encoder-Decoder Modularity in Sequence-to-Sequence Models

Inspired by modular software design principles of independence, intercha...
11/09/2019 ∙ by Siddharth Dalmia, et al. ∙ 0 ∙ share

read it
On Compositionality in Neural Machine Translation

We investigate two specific manifestations of compositionality in Neural...
11/04/2019 ∙ by Vikas Raunak, et al. ∙ 0 ∙ share

read it
Adversarial Music: Real World Audio Adversary Against Wake-word Detection System

Voice Assistants (VAs) such as Amazon Alexa or Google Assistant rely on ...
10/31/2019 ∙ by Juncheng B. Li, et al. ∙ 0 ∙ share

read it
Multitask Learning For Different Subword Segmentations In Neural Machine Translation

In Neural Machine Translation (NMT) the usage of subwords and characters...
10/27/2019 ∙ by Tejas Srinivasan, et al. ∙ 0 ∙ share

read it
On Leveraging the Visual Modality for Neural Machine Translation

Leveraging the visual modality effectively for Neural Machine Translatio...
10/07/2019 ∙ by Vikas Raunak, et al. ∙ 0 ∙ share

read it
On Dimensional Linguistic Properties of the Word Embedding Space

Word embeddings have become a staple of several natural language process...
10/05/2019 ∙ by Vikas Raunak, et al. ∙ 0 ∙ share

read it
SANTLR: Speech Annotation Toolkit for Low Resource Languages

While low resource speech recognition has attracted a lot of attention f...
08/02/2019 ∙ by Xinjian Li, et al. ∙ 0 ∙ share

read it
Multilingual Speech Recognition with Corpus Relatedness Sampling

Multilingual acoustic models have been successfully applied to low-resou...
08/02/2019 ∙ by Xinjian Li, et al. ∙ 0 ∙ share

read it
Cross-Attention End-to-End ASR for Two-Party Conversations

We present an end-to-end speech recognition model that learns interactio...
07/24/2019 ∙ by Suyoun Kim, et al. ∙ 0 ∙ share

read it
Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions

Multimodal learning allows us to leverage information from multiple sour...
06/30/2019 ∙ by Tejas Srinivasan, et al. ∙ 0 ∙ share

read it
Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion

We present a novel conversational-context aware end-to-end speech recogn...
06/27/2019 ∙ by Suyoun Kim, et al. ∙ 0 ∙ share

read it
Multimodal Abstractive Summarization for How2 Videos

In this paper, we study abstractive summarization for open-domain videos...
06/19/2019 ∙ by Shruti Palaskar, et al. ∙ 0 ∙ share

read it
Grounding Object Detections With Transcriptions

A vast amount of audio-visual data is available on the Internet thanks t...
06/13/2019 ∙ by Yasufumi Moriya, et al. ∙ 0 ∙ share

read it
Acoustic-to-Word Models with Conversational Context Information

Conversational context information, higher-level knowledge that spans ac...
05/21/2019 ∙ by Suyoun Kim, et al. ∙ 0 ∙ share

read it
The ARIEL-CMU Systems for LoReHLT18

This paper describes the ARIEL-CMU submissions to the Low Resource Human...
02/24/2019 ∙ by Aditi Chaudhary, et al. ∙ 0 ∙ share

read it
Phoneme Level Language Models for Sequence Based Low Resource ASR

Building multilingual and crosslingual models help bring different langu...
02/20/2019 ∙ by Siddharth Dalmia, et al. ∙ 0 ∙ share

read it
Learned In Speech Recognition: Contextual Acoustic Word Embeddings

End-to-end acoustic-to-word speech recognition models have recently gain...
02/18/2019 ∙ by Shruti Palaskar, et al. ∙ 0 ∙ share

read it
Learning from Multiview Correlations in Open-Domain Videos

An increasing number of datasets contain multiple views, such as video, ...
11/21/2018 ∙ by Nils Holzenberger, et al. ∙ 0 ∙ share

read it
Multimodal Grounding for Sequence-to-Sequence Speech Recognition

Humans are capable of processing speech by making use of multiple sensor...
11/09/2018 ∙ by Ozan Caglayan, et al. ∙ 0 ∙ share

read it
How2: A Large-scale Dataset for Multimodal Language Understanding

In this paper, we introduce How2, a multimodal collection of instruction...
11/01/2018 ∙ by Ramon Sanabria, et al. ∙ 0 ∙ share

read it
Connectionist Temporal Localization for Sound Event Detection with Sequential Labeling

Research on sound event detection (SED) with weak labeling has mostly fo...
10/22/2018 ∙ by Yun Wang, et al. ∙ 0 ∙ share

read it
A comparison of five multiple instance learning pooling functions for sound event detection with weak labeling

Sound event detection (SED) entails two subtasks: recognizing what types...
10/22/2018 ∙ by Yun Wang, et al. ∙ 0 ∙ share

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

Moments capture a huge part of our lives. Accurate recognition of these ...
09/01/2018 ∙ by Ankit Shah, et al. ∙ 0 ∙ share

read it
Dialog-context aware end-to-end speech recognition

Existing speech recognition systems are typically built at the sentence ...
08/07/2018 ∙ by Suyoun Kim, et al. ∙ 0 ∙ share

read it
Domain Robust Feature Extraction for Rapid Low Resource ASR Development

Developing a practical speech recognizer for a low resource language is ...
07/28/2018 ∙ by Siddharth Dalmia, et al. ∙ 0 ∙ share

read it
Acoustic-to-Word Recognition with Sequence-to-Sequence Models

Acoustic-to-Word recognition provides a straightforward solution to end-...
07/23/2018 ∙ by Shruti Palaskar, et al. ∙ 0 ∙ share

read it
Hierarchical Multi Task Learning With CTC

In Automatic Speech Recognition, it is still challenging to learn useful...
07/18/2018 ∙ by Ramon Sanabria, et al. ∙ 0 ∙ share

read it
End-to-End Multimodal Speech Recognition

Transcription or sub-titling of open-domain videos is still a challengin...
04/25/2018 ∙ by Shruti Palaskar, et al. ∙ 0 ∙ share

read it
Comparing the Max and Noisy-Or Pooling Functions in Multiple Instance Learning for Weakly Supervised Sequence Learning Tasks

Many sequence learning tasks require the localization of certain events ...
04/03/2018 ∙ by Yun Wang, et al. ∙ 0 ∙ share

read it
Sequence-based Multi-lingual Low Resource Speech Recognition

Techniques for multi-lingual and cross-lingual speech recognition can he...
02/21/2018 ∙ by Siddharth Dalmia, et al. ∙ 0 ∙ share

read it
Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop

We summarize the accomplishments of a multi-disciplinary workshop explor...
02/14/2018 ∙ by Odette Scharenborg, et al. ∙ 0 ∙ share

read it
A Light-Weight Multimodal Framework for Improved Environmental Audio Tagging

The lack of strong labels has severely limited the state-of-the-art full...
12/27/2017 ∙ by Juncheng Li, et al. ∙ 0 ∙ share

read it
Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection

State-of-the-art audio event detection (AED) systems rely on supervised ...
12/27/2017 ∙ by Shao-Yen Tseng, et al. ∙ 0 ∙ share

read it
Multiple Instance Deep Learning for Weakly Supervised Audio Event Detection

State-of-the-art audio event detection (AED) systems rely on supervised ...
12/27/2017 ∙ by Shao-Yen Tseng, et al. ∙ 0 ∙ share

read it