Search Results for author:
Found 28 papers, 2 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.
KIT’s IWSLT 2021 Offline Speech Translation System
We describe a system in both cascaded condition and end-to-end condition.
Effective combination of pretrained models - KIT@IWSLT2022
Pretrained models in acoustic and textual modalities can potentially improve speech translation for both Cascade and End-to-end approaches.
Multilingual Speech Translation KIT @ IWSLT2021
This paper contains the description for the submission of Karlsruhe Institute of Technology (KIT) for the multilingual TEDx translation task in the IWSLT 2021 evaluation campaign.
KIT’s Multilingual Neural Machine Translation systems for IWSLT 2017
For the SLT track, in addition to a monolingual neural translation system used to generate correct punctuations and true cases of the data prior to training our multilingual system, we introduced a noise model in order to make our system more robust.
The IWSLT 2019 KIT Speech Translation System
This paper describes KIT’s submission to the IWSLT 2019 Speech Translation task on two sub-tasks corresponding to two different datasets.
Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages
We explore how this zero-shot translation capability develops with varying number of languages seen by the encoder.
Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024
Firstly, we refine the ASR outputs by utilizing the N-best lists generated by our system and fine-tuning the LLM to predict the transcript accurately.
KIT's Multilingual Speech Translation System for IWSLT 2023
In this paper, we describe our speech translation system for the multilingual track of IWSLT 2023, which evaluates translation quality on scientific conference talks.
Towards continually learning new languages
Multilingual speech recognition with neural networks is often implemented with batch-learning, when all of the languages are available before training.
Adaptive multilingual speech recognition with pretrained models
Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research.
Efficient Weight factorization for Multilingual Speech Recognition
The key idea of the method is to assign fast weight matrices for each language by decomposing each weight matrix into a shared component and a language dependent component.
Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings
In an attempt to train the mapping from the encoder sentence representation to a new target language we use our model as an autoencoder.
KIT's IWSLT 2020 SLT Translation System
This paper describes KIT{'}s submissions to the IWSLT2020 Speech Translation evaluation campaign.
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.
Modeling Confidence in Sequence-to-Sequence Models
We show improvements on segment-level confidence estimation as well as on confidence estimation for source tokens.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
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.
Very Deep Self-Attention Networks for End-to-End Speech Recognition
Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community.
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.
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.
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.
