Alex Waibel

is this you? claim profile

∙ 0 followers
KIT ∙ Carnegie Mellon University

Professor of Computer Science at the Language Technologies Institute (LTI) of Carnegie Mellon University (CMU)

Super-Human Performance in Online Low-latency Recognition of Conversational Speech

Achieving super-human performance in recognizing human speech has been a...
10/07/2020 ∙ by Thai-Son Nguyen, et al. ∙ 0 ∙ share

read it
Error-correction and extraction in request dialogs

We propose a component that gets a request and a correction and outputs ...
04/08/2020 ∙ by Stefan Constantin, et al. ∙ 0 ∙ share

read it
High Performance Sequence-to-Sequence Model for Streaming Speech Recognition

Recently sequence-to-sequence models have started to achieve state-of-th...
03/22/2020 ∙ by Thai-Son Nguyen, et al. ∙ 0 ∙ share

read it
Low Latency ASR for Simultaneous Speech Translation

User studies have shown that reducing the latency of our simultaneous le...
03/22/2020 ∙ by Thai-Son Nguyen, et al. ∙ 0 ∙ share

read it
Toward Cross-Domain Speech Recognition with End-to-End Models

In the area of multi-domain speech recognition, research in the past foc...
03/09/2020 ∙ by Thai-Son Nguyen, et al. ∙ 0 ∙ share

read it
An Interactive Indoor Drone Assistant

With the rapid advance of sophisticated control algorithms, the capabili...
12/09/2019 ∙ by Tino Fuhrman, et al. ∙ 0 ∙ share

read it
Bimodal Speech Emotion Recognition Using Pre-Trained Language Models

Speech emotion recognition is a challenging task and an important step t...
11/29/2019 ∙ by Verena Heusser, et al. ∙ 11 ∙ share

read it
Low-Resource Machine Translation using Interlinear Glosses

Neural Machine Translation (NMT) does not handle low-resource translatio...
11/07/2019 ∙ by Zhong Zhou, et al. ∙ 0 ∙ share

read it
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation

Sequence-to-Sequence (S2S) models recently started to show state-of-the-...
10/29/2019 ∙ by Thai-Son Nguyen, et al. ∙ 57 ∙ share

read it
Incremental processing of noisy user utterances in the spoken language understanding task

The state-of-the-art neural network architectures make it possible to cr...
09/30/2019 ∙ by Stefan Constantin, et al. ∙ 0 ∙ share

read it
Improving Zero-shot Translation with Language-Independent Constraints

An important concern in training multilingual neural machine translation...
06/20/2019 ∙ by Ngoc-Quan Pham, et al. ∙ 0 ∙ share

read it
Self-Attentional Models for Lattice Inputs

Lattices are an efficient and effective method to encode ambiguity of up...
06/04/2019 ∙ by Matthias Sperber, et al. ∙ 0 ∙ share

read it
Fluent Translations from Disfluent Speech in End-to-End Speech Translation

Spoken language translation applications for speech suffer due to conver...
06/03/2019 ∙ by Elizabeth Salesky, et al. ∙ 0 ∙ share

read it
Very Deep Self-Attention Networks for End-to-End Speech Recognition

Recently, end-to-end sequence-to-sequence models for speech recognition ...
04/30/2019 ∙ by Ngoc-Quan Pham, et al. ∙ 0 ∙ share

read it
Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation

Speech translation has traditionally been approached through cascaded mo...
04/15/2019 ∙ by Matthias Sperber, et al. ∙ 0 ∙ share

read it
Learning Shared Encoding Representation for End-to-End Speech Recognition Models

In this work, we learn a shared encoding representation for a multi-task...
03/31/2019 ∙ by Thai-Son Nguyen, et al. ∙ 0 ∙ share

read it
Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models

Acoustic-to-word (A2W) models that allow direct mapping from acoustic si...
02/02/2019 ∙ by Thai-Son Nguyen, et al. ∙ 0 ∙ share

read it
Multi-task learning to improve natural language understanding

Recently advancements in sequence-to-sequence neural network architectur...
12/17/2018 ∙ by Stefan Constantin, et al. ∙ 0 ∙ share

read it
Towards Fluent Translations from Disfluent Speech

When translating from speech, special consideration for conversational s...
11/07/2018 ∙ by Elizabeth Salesky, et al. ∙ 0 ∙ share

read it
Towards one-shot learning for rare-word translation with external experts

Neural machine translation (NMT) has significantly improved the quality ...
09/10/2018 ∙ by Ngoc-Quan Pham, et al. ∙ 0 ∙ share

read it
Paraphrases as Foreign Languages in Multilingual Neural Machine Translation

Using paraphrases, the expression of the same semantic meaning in differ...
08/25/2018 ∙ by Zhong Zhou, et al. ∙ 0 ∙ share

read it
Low-Latency Neural Speech Translation

Through the development of neural machine translation, the quality of ma...
08/01/2018 ∙ by Jan Niehues, et al. ∙ 0 ∙ share

read it
A Hierarchical Approach to Neural Context-Aware Modeling

We present a new recurrent neural network topology to enhance state-of-t...
07/27/2018 ∙ by Patrick Huber, et al. ∙ 0 ∙ share

read it
Robust and Scalable Differentiable Neural Computer for Question Answering

Deep learning models are often not easily adaptable to new tasks and req...
07/07/2018 ∙ by Jörg Franke, et al. ∙ 0 ∙ share

read it
Neural Language Codes for Multilingual Acoustic Models

Multilingual Speech Recognition is one of the most costly AI problems, b...
07/05/2018 ∙ by Markus Müller, et al. ∙ 0 ∙ share

read it
Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

We work on translation from rich-resource languages to low-resource lang...
04/21/2018 ∙ by Zhong Zhou, et al. ∙ 0 ∙ share

read it
Self-Attentional Acoustic Models

Self-attention is a method of encoding sequences of vectors by relating ...
03/26/2018 ∙ by Matthias Sperber, et al. ∙ 0 ∙ share

read it
Automated Evaluation of Out-of-Context Errors

We present a new approach to evaluate computational models for the task ...
03/23/2018 ∙ by Patrick Huber, et al. ∙ 0 ∙ share

read it
An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation

Recently advancements in deep learning allowed the development of end-to...
03/06/2018 ∙ by Stefan Constantin, et al. ∙ 0 ∙ share

read it
Subword and Crossword Units for CTC Acoustic Models

This paper proposes a novel approach to create an unit set for CTC based...
12/19/2017 ∙ by Thomas Zenkel, et al. ∙ 0 ∙ share

read it
Multilingual Adaptation of RNN Based ASR Systems

A large amount of data is required for automatic speech recognition (ASR...
11/13/2017 ∙ by Markus Müller, et al. ∙ 0 ∙ share

read it
Phonemic and Graphemic Multilingual CTC Based Speech Recognition

Training automatic speech recognition (ASR) systems requires large amoun...
11/13/2017 ∙ by Markus Müller, et al. ∙ 0 ∙ share

read it
Transcribing Against Time

We investigate the problem of manually correcting errors from an automat...
09/15/2017 ∙ by Matthias Sperber, et al. ∙ 0 ∙ share

read it
Comparison of Decoding Strategies for CTC Acoustic Models

Connectionist Temporal Classification has recently attracted a lot of in...
08/15/2017 ∙ by Thomas Zenkel, et al. ∙ 0 ∙ share

read it
Analyzing Neural MT Search and Model Performance

In this paper, we offer an in-depth analysis about the modeling and sear...
08/02/2017 ∙ by Jan Niehues, et al. ∙ 0 ∙ share

read it
Yeah, Right, Uh-Huh: A Deep Learning Backchannel Predictor

Using supporting backchannel (BC) cues can make human-computer interacti...
06/02/2017 ∙ by Robin Ruede, et al. ∙ 0 ∙ share

read it
Neural Lattice-to-Sequence Models for Uncertain Inputs

The input to a neural sequence-to-sequence model is often determined by ...
04/03/2017 ∙ by Matthias Sperber, et al. ∙ 0 ∙ share

read it
Pre-Translation for Neural Machine Translation

Recently, the development of neural machine translation (NMT) has signif...
10/17/2016 ∙ by Jan Niehues, et al. ∙ 0 ∙ share

read it
Lexical Translation Model Using a Deep Neural Network Architecture

In this paper we combine the advantages of a model using global source s...
04/28/2015 ∙ by Thanh-Le Ha, et al. ∙ 0 ∙ share

read it

Alex Waibel

Featured Co-authors