Search Results for author:
Found 95 papers, 5 papers with code
KIT’s IWSLT 2018 SLT Translation System
The baseline system is a cascade of an ASR system, a system to segment the ASR output and a neural machine translation system.
The 2017 KIT IWSLT Speech-to-Text Systems for English and German
For the English lecture task, our best combination system has a WER of 8. 3% on the tst2015 development set while our other combinations gained 25. 7% WER for German lecture tasks.
KIT’s Submission to the IWSLT 2019 Shared Task on Text Translation
In this paper, we describe KIT’s submission for the IWSLT 2019 shared task on text translation.
ELITR: European Live Translator
ELITR (European Live Translator) project aims to create a speech translation system for simultaneous subtitling of conferences and online meetings targetting up to 43 languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Toward Robust Neural Machine Translation for Noisy Input Sequences
We note that unlike our baseline model, models trained on noisy data are able to generate outputs of proper length even for noisy inputs, while gradually reducing output length for higher amount of noise, as might also be expected from a human translator.
Domain-independent Punctuation and Segmentation Insertion
Experiments show that generalizing rare and unknown words greatly improves the punctuation insertion performance, reaching up to 8. 8 points of improvement in F-score when applied to the out-of-domain test scenario.
The 2016 KIT IWSLT Speech-to-Text Systems for English and German
For the English TED task, our best combination system has a WER of 7. 8% on the development set while our other combinations gained 21. 8% and 28. 7% WERs for the English and German MSLT tasks.
Adaptation and Combination of NMT Systems: The KIT Translation Systems for IWSLT 2016
In addition, we investigated methods to combine NMT systems that encode the input as well as the output differently.
Multilingual Disfluency Removal using NMT
In this paper, we investigate a multilingual approach for speech disfluency removal.
Towards Improving Low-Resource Speech Recognition Using Articulatory and Language Features
For system training, we use additional data from French, German and Turkish.
Findings of the IWSLT 2024 Evaluation Campaign
This paper reports on the shared tasks organized by the 21st IWSLT Conference.
Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience
Verbalization of robot experience, i. e., summarization of and question answering about a robot's past, is a crucial ability for improving human-robot interaction.
Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff
Further, this method lacks mechanisms for \textit{controlling} the quality vs. latency tradeoff.
Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models
In this paper, we propose a system to achieve incremental learning of complex behavior from natural interaction, and demonstrate its implementation on a humanoid robot.
Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages
We examine two approaches: 1. best selection of seed sentences to jump start translations in a new language in view of best generalization to the remainder of a larger targeted text(s), and 2. we adapt large general multilingual translation engines from many other languages to focus on a specific text in a new, unknown language.
Adaptive multilingual speech recognition with pretrained models
Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research.
Active Learning for Massively Parallel Translation of Constrained Text into Low Resource Languages
We compare the portion-based approach that optimizes coherence of the text locally with the random sampling approach that increases coverage of the text globally.
Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation
In other words, given a text in 124 source languages, we translate it into a severely low resource language using only ~1, 000 lines of low resource data without any external help.
ELITR Multilingual Live Subtitling: Demo and Strategy
This paper presents an automatic speech translation system aimed at live subtitling of conference presentations.
Super-Human Performance in Online Low-latency Recognition of Conversational Speech
Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks.
FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN
The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2020) featured this year six challenge tracks: (i) Simultaneous speech translation, (ii) Video speech translation, (iii) Offline speech translation, (iv) Conversational speech translation, (v) Open domain translation, and (vi) Non-native speech translation.
Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation
Simultaneous machine translation systems rely on a policy to schedule read and write operations in order to begin translating a source sentence before it is complete.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
KIT's IWSLT 2020 SLT Translation System
This paper describes KIT{'}s submissions to the IWSLT2020 Speech Translation evaluation campaign.
Removing European Language Barriers with Innovative Machine Translation Technology
This paper presents our progress towards deploying a versatile communication platform in the task of highly multilingual live speech translation for conferences and remote meetings live subtitling.
DaCToR: A Data Collection Tool for the RELATER Project
Collecting domain-specific data for under-resourced languages, e. g., dialects of languages, can be very expensive, potentially financially prohibitive and taking long time.
Error correction and extraction in request dialogs
If yes, it corrects the second last utterance according to the error correction in the last utterance and outputs the extracted pairs of reparandum and repair entity.
High Performance Sequence-to-Sequence Model for Streaming Speech Recognition
However, when it comes to performing run-on recognition on an input stream of audio data while producing recognition results in real-time and with low word-based latency, these models face several challenges.
Low Latency ASR for Simultaneous Speech Translation
User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Toward Cross-Domain Speech Recognition with End-to-End Models
We show that for the hybrid models, supplying additional training data from other domains with mismatched acoustic conditions does not increase the performance on specific domains.
Bimodal Speech Emotion Recognition Using Pre-Trained Language Models
Speech emotion recognition is a challenging task and an important step towards more natural human-machine interaction.
Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation
Firstly, we pool IGT for 1, 497 languages in ODIN (54, 545 glosses) and 70, 918 glosses in Arapaho and train a gloss-to-target NMT system from IGT to English, with a BLEU score of 25. 94.
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-art performance for automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Incremental processing of noisy user utterances in the spoken language understanding task
The state-of-the-art neural network architectures make it possible to create spoken language understanding systems with high quality and fast processing time.
Natural Language Understanding
Spoken Language Understanding
Improving Zero-shot Translation with Language-Independent Constraints
We investigated the behaviour of such models on the standard IWSLT 2017 multilingual dataset.
Self-Attentional Models for Lattice Inputs
Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic analyses.
Fluent Translations from Disfluent Speech in End-to-End Speech Translation
Spoken language translation applications for speech suffer due to conversational speech phenomena, particularly the presence of disfluencies.
Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation
Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts.
Learning Shared Encoding Representation for End-to-End Speech Recognition Models
In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria.
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 signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multi-task learning to improve natural language understanding
When building a neural network-based Natural Language Understanding component, one main challenge is to collect enough training data.
Towards Fluent Translations from Disfluent Speech
We introduce a corpus of cleaned target data for the Fisher Spanish-English dataset for this task.
The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018
We present our experiments in the scope of the news translation task in WMT 2018, in directions: English→German.
Towards one-shot learning for rare-word translation with external experts
Neural machine translation (NMT) has significantly improved the quality of automatic translation models.
Paraphrases as Foreign Languages in Multilingual Neural Machine Translation
Our multi-paraphrase NMT that trains only on two languages outperforms the multilingual baselines.
Low-Latency Neural Speech Translation
After adaptation, we are able to reduce the number of corrections displayed during incremental output construction by 45%, without a decrease in translation quality.
KIT Lecture Translator: Multilingual Speech Translation with One-Shot Learning
{\%} Combining these techniques, we are able to provide an adapted speech translation system for several European languages.
A Hierarchical Approach to Neural Context-Aware Modeling
Our approach overcomes recent limitations with extended narratives through a multi-layered computational approach to generate an abstract context representation.
Robust and Scalable Differentiable Neural Computer for Question Answering
Deep learning models are often not easily adaptable to new tasks and require task-specific adjustments.
Neural Language Codes for Multilingual Acoustic Models
Multilingual Speech Recognition is one of the most costly AI problems, because each language (7, 000+) and even different accents require their own acoustic models to obtain best recognition performance.
Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation
The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding problem that is common in neural systems.
Self-Attentional Acoustic Models
Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities.
Automated Evaluation of Out-of-Context Errors
We present a new approach to evaluate computational models for the task of text understanding by the means of out-of-context error detection.
An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation
Furthermore, by using a feedforward neural network, we are able to generate the output word by word and are no longer restricted to a fixed number of possible response candidates.
Subword and Crossword Units for CTC Acoustic Models
This paper proposes a novel approach to create an unit set for CTC based speech recognition systems.
Phonemic and Graphemic Multilingual CTC Based Speech Recognition
We evaluated the use of different language combinations as well as the addition of Language Feature Vectors (LFVs).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Multilingual Adaptation of RNN Based ASR Systems
In this work, we focus on multilingual systems based on recurrent neural networks (RNNs), trained using the Connectionist Temporal Classification (CTC) loss function.
Transcribing Against Time
We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion.
Comparison of Decoding Strategies for CTC Acoustic Models
The CTC loss function maps an input sequence of observable feature vectors to an output sequence of symbols.
Analyzing Neural MT Search and Model Performance
By separating the search space and the modeling using $n$-best list reranking, we analyze the influence of both parts of an NMT system independently.
Yeah, Right, Uh-Huh: A Deep Learning Backchannel Predictor
BCs can be expressed in different ways, depending on the modality of the interaction, for example as gestures or acoustic cues.
Neural Lattice-to-Sequence Models for Uncertain Inputs
In this work, we extend the TreeLSTM (Tai et al., 2015) into a LatticeLSTM that is able to consume word lattices, and can be used as encoder in an attentional encoder-decoder model.
Lightly Supervised Quality Estimation
Evaluating the quality of output from language processing systems such as machine translation or speech recognition is an essential step in ensuring that they are sufficient for practical use.
Pre-Translation for Neural Machine Translation
We analyzed the influence of the quality of the initial system on the final result.
Evaluation of the KIT Lecture Translation System
One obstacle to achieving this goal is that lectures at KIT are usually held in German which many foreign students are not sufficiently proficient in, as, e. g., opposed to English.
Optimizing Computer-Assisted Transcription Quality with Iterative User Interfaces
Our goal is to improve the human transcription quality via appropriate user interface design.
Lexical Translation Model Using a Deep Neural Network Architecture
In this paper we combine the advantages of a model using global source sentence contexts, the Discriminative Word Lexicon, and neural networks.
A Corpus of Spontaneous Speech in Lectures: The KIT Lecture Corpus for Spoken Language Processing and Translation
With the increasing number of applications handling spontaneous speech, the needs to process spoken languages become stronger.
Manual Analysis of Structurally Informed Reordering in German-English Machine Translation
However, it is a crucial aspect for humans when deciding on translation quality.
Segmentation for Efficient Supervised Language Annotation with an Explicit Cost-Utility Tradeoff
In this paper, we study the problem of manually correcting automatic annotations of natural language in as efficient a manner as possible.
The KIT Lecture Corpus for Speech Translation
Academic lectures offer valuable content, but often do not reach their full potential audience due to the language barrier.
