Search Results for author:
Found 166 papers, 24 papers with code
Towards a Better Evaluation of Metrics for Machine Translation
An important aspect of machine translation is its evaluation, which can be achieved through the use of a variety of metrics.
The RWTH Aachen Machine Translation Systems for IWSLT 2017
This work describes the Neural Machine Translation (NMT) system of the RWTH Aachen University developed for the English$German tracks of the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2017.
Analysis of Positional Encodings for Neural Machine Translation
In this work we analyze and compare the behavior of the Transformer architecture when using different positional encoding methods.
Detecting Various Types of Noise for Neural Machine Translation
The filtering and/or selection of training data is one of the core aspects to be considered when building a strong machine translation system. In their influential work, Khayrallah and Koehn (2018) investigated the impact of different types of noise on the performance of machine translation systems. In the same year the WMT introduced a shared task on parallel corpus filtering, which went on to be repeated in the following years, and resulted in many different filtering approaches being proposed. In this work we aim to combine the recent achievements in data filtering with the original analysis of Khayrallah and Koehn (2018) and investigate whether state-of-the-art filtering systems are capable of removing all the suggested noise types. We observe that most of these types of noise can be detected with an accuracy of over 90% by modern filtering systems when operating in a well studied high resource setting. However, we also find that when confronted with more refined noise categories or when working with a less common language pair, the performance of the filtering systems is far from optimal, showing that there is still room for improvement in this area of research.
Locality-Sensitive Hashing for Long Context Neural Machine Translation
After its introduction the Transformer architecture quickly became the gold standard for the task of neural machine translation.
Recurrent Attention for the Transformer
In this work, we conduct a comprehensive investigation on one of the centerpieces of modern machine translation systems: the encoder-decoder attention mechanism.
The RWTH Aachen Machine Translation System for IWSLT 2016
This work describes the statistical machine translation (SMT) systems of RWTH Aachen University developed for the evaluation campaign of International Workshop on Spoken Language Translation (IWSLT) 2016.
The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task
In this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems developed for the IWSLT-2016 evaluation campaign are described.
Document-Level Language Models for Machine Translation
Finally, we explore language model fusion in the light of recent advancements in large language models.
Investigating the Effect of Language Models in Sequence Discriminative Training for Neural Transducers
In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers.
End-to-End Training of a Neural HMM with Label and Transition Probabilities
We investigate recognition results and additionally Viterbi alignments of our models.
On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers
Empirically, we show that ILM subtraction and sequence discriminative training achieve similar performance across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context.
Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
We study a streamable attention-based encoder-decoder model in which either the decoder, or both the encoder and decoder, operate on pre-defined, fixed-size windows called chunks.
Comparative Analysis of the wav2vec 2.0 Feature Extractor
In this work, we study its capability to replace the standard feature extraction methods in a connectionist temporal classification (CTC) ASR model and compare it to an alternative neural FE.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Improving Language Model Integration for Neural Machine Translation
The integration of language models for neural machine translation has been extensively studied in the past.
Improving Long Context Document-Level Machine Translation
Document-level context for neural machine translation (NMT) is crucial to improve the translation consistency and cohesion, the translation of ambiguous inputs, as well as several other linguistic phenomena.
On Search Strategies for Document-Level Neural Machine Translation
On the other hand, in most works, the question on how to perform search with the trained model is scarcely discussed, sometimes not mentioned at all.
RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition
Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only.
Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10
This paper summarizes our contributions to the document-grounded dialog tasks at the 9th and 10th Dialog System Technology Challenges (DSTC9 and DSTC10).
Analyzing And Improving Neural Speaker Embeddings for ASR
By further adding neural speaker embeddings, we gain additional ~3% relative WER improvement on Hub5'00.
Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers
Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Enhancing and Adversarial: Improve ASR with Speaker Labels
Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training.
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token
We show: (1) [MASK]s can indeed be appended at a later layer, being disentangled from the word embedding; (2) The gathering of contextualized information from unmasked tokens can be conducted with a few layers.
Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes theorem.
Efficient Utilization of Large Pre-Trained Models for Low Resource ASR
Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Monotonic segmental attention for automatic speech recognition
We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable streaming.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
Does Joint Training Really Help Cascaded Speech Translation?
Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech
Language barriers present a great challenge in our increasingly connected and global world.
Revisiting Checkpoint Averaging for Neural Machine Translation
Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models.
Is Encoder-Decoder Redundant for Neural Machine Translation?
Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks.
Improving the Training Recipe for a Robust Conformer-based Hybrid Model
In this work, we investigate various methods for speaker adaptive training (SAT) based on feature-space approaches for a conformer-based acoustic model (AM) on the Switchboard 300h dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Efficient Training of Neural Transducer for Speech Recognition
In this work, we propose an efficient 3-stage progressive training pipeline to build highly-performing neural transducer models from scratch with very limited computation resources in a reasonable short time period.
Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Model
This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations".
Self-Normalized Importance Sampling for Neural Language Modeling
Compared to our previous work, the criteria considered in this work are self-normalized and there is no need to further conduct a correction step.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Conformer-based Hybrid ASR System for Switchboard Dataset
The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Efficient Sequence Training of Attention Models using Approximative Recombination
Lastly, it is shown that this technique can be used to effectively perform sequence discriminative training for attention-based encoder-decoder acoustic models on the LibriSpeech task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Automatic Learning of Subword Dependent Model Scales
We show on the LibriSpeech (LBS) and Switchboard (SWB) corpora that the model scales for a combination of attentionbased encoder-decoder acoustic model and language model can be learned as effectively as with manual tuning.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
On Language Model Integration for RNN Transducer based Speech Recognition
In this work, we study various ILM correction-based LM integration methods formulated in a common RNN-T framework.
Investigation on Data Adaptation Techniques for Neural Named Entity Recognition
Data processing is an important step in various natural language processing tasks.
Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models.
Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer
Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs.
Transformer-Based Direct Hidden Markov Model for Machine Translation
The neural hidden Markov model has been proposed as an alternative to attention mechanism in machine translation with recurrent neural networks.
Cascaded Span Extraction and Response Generation for Document-Grounded Dialog
For the second subtask, we use a cascaded model which grounds the response prediction on the predicted span instead of the full document.
Data Filtering using Cross-Lingual Word Embeddings
While we find that our approaches come out at the top on all three tasks, different variants perform best on different tasks.
Why does CTC result in peaky behavior?
The peaky behavior of CTC models is well known experimentally.
On Sampling-Based Training Criteria for Neural Language Modeling
As the vocabulary size of modern word-based language models becomes ever larger, many sampling-based training criteria are proposed and investigated.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition
Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
With the advent of direct models in automatic speech recognition (ASR), the formerly prevalent frame-wise acoustic modeling based on hidden Markov models (HMM) diversified into a number of modeling architectures like encoder-decoder attention models, transducer models and segmental models (direct HMM).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
Attention-based encoder-decoder (AED) models learn an implicit internal language model (ILM) from the training transcriptions.
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures
We achieve a final word-error-rate of 3. 3%/10. 0% with a hybrid system on the clean/noisy test-sets, surpassing any previous state-of-the-art systems on Librispeech-100h that do not include unlabeled audio data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
On Architectures and Training for Raw Waveform Feature Extraction in ASR
With the success of neural network based modeling in automatic speech recognition (ASR), many studies investigated acoustic modeling and learning of feature extractors directly based on the raw waveform.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Librispeech Transducer Model with Internal Language Model Prior Correction
We present our transducer model on Librispeech.
Ranked #22 on
Speech Recognition
on LibriSpeech test-clean
A study of latent monotonic attention variants
We compare several monotonic latent models to our global soft attention baseline such as a hard attention model, a local windowed soft attention model, and a segmental soft attention model.
Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog
This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), "Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access".
Towards a Better Understanding of Label Smoothing in Neural Machine Translation
In order to combat overfitting and in pursuit of better generalization, label smoothing is widely applied in modern neural machine translation systems.
Predicting and Using Target Length in Neural Machine Translation
Attention-based encoder-decoder models have achieved great success in neural machine translation tasks.
Neural Language Modeling for Named Entity Recognition
Named entity recognition is a key component in various natural language processing systems, and neural architectures provide significant improvements over conventional approaches.
Unifying Input and Output Smoothing in Neural Machine Translation
Soft contextualized data augmentation is a recent method that replaces one-hot representation of words with soft posterior distributions of an external language model, smoothing the input of neural machine translation systems.
Two-Way Neural Machine Translation: A Proof of Concept for Bidirectional Translation Modeling using a Two-Dimensional Grid
Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence.
Tight Integrated End-to-End Training for Cascaded Speech Translation
Direct speech translation is an alternative method to avoid error propagation; however, its performance is often behind the cascade system.
Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine Translation
Mutual learning, where multiple agents learn collaboratively and teach one another, has been shown to be an effective way to distill knowledge for image classification tasks.
Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling.
Diving Deep into Context-Aware Neural Machine Translation
Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e. g., document-level translation, or having meta-information.
Early Stage LM Integration Using Local and Global Log-Linear Combination
This is compared to a global renormalization scheme which is equivalent to applying shallow fusion in training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Investigation of Large-Margin Softmax in Neural Language Modeling
After that, we apply the best norm-scaling setup in combination with various margins and conduct neural language models rescoring experiments in automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models
Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e. g. byte-pair encoding (BPE).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A New Training Pipeline for an Improved Neural Transducer
We compare the original training criterion with the full marginalization over all alignments, to the commonly used maximum approximation, which simplifies, improves and speeds up our training.
Context-Dependent Acoustic Modeling without Explicit Phone Clustering
In this work, we address a direct phonetic context modeling for the hybrid deep neural network (DNN)/HMM, that does not build on any phone clustering algorithm for the determination of the HMM state inventory.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Fine-Grained Visual Classification with Efficient End-to-end Localization
The term fine-grained visual classification (FGVC) refers to classification tasks where the classes are very similar and the classification model needs to be able to find subtle differences to make the correct prediction.
Ranked #7 on
Fine-Grained Image Classification
on Stanford Cars
Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture
Sparse models require less memory for storage and enable a faster inference by reducing the necessary number of FLOPs.
When and Why is Unsupervised Neural Machine Translation Useless?
This paper studies the practicality of the current state-of-the-art unsupervised methods in neural machine translation (NMT).
The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment
We present a complete training pipeline to build a state-of-the-art hybrid HMM-based ASR system on the 2nd release of the TED-LIUM corpus.
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems
We achieve improvements of up to 33% relative in word-error-rate (WER) over a strong baseline with data-augmentation in a low-resource environment (LibriSpeech-100h), closing the gap to a comparable oracle experiment by more than 50\%.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
On using 2D sequence-to-sequence models for speech recognition
Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A Comparative Study on End-to-end Speech to Text Translation
Recent advances in deep learning show that end-to-end speech to text translation model is a promising approach to direct the speech translation field.
On Using SpecAugment for End-to-End Speech Translation
This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation.
ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding
The task of fine-grained visual classification (FGVC) deals with classification problems that display a small inter-class variance such as distinguishing between different bird species or car models.
Ranked #15 on
Fine-Grained Image Classification
on FGVC Aircraft
Exploring Kernel Functions in the Softmax Layer for Contextual Word Classification
Prominently used in support vector machines and logistic regressions, kernel functions (kernels) can implicitly map data points into high dimensional spaces and make it easier to learn complex decision boundaries.
When and Why is Document-level Context Useful in Neural Machine Translation?
Document-level context has received lots of attention for compensating neural machine translation (NMT) of isolated sentences.
Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i. e., source-pivot and pivot-target, leading to a significant improvement in source-target translation.
uniblock: Scoring and Filtering Corpus with Unicode Block Information
The preprocessing pipelines in Natural Language Processing usually involve a step of removing sentences consisted of illegal characters.
EED: Extended Edit Distance Measure for Machine Translation
Over the years a number of machine translation metrics have been developed in order to evaluate the accuracy and quality of machine-generated translations.
The RWTH Aachen University Machine Translation Systems for WMT 2019
For the De-En task, none of the tested methods gave a significant improvement over last years winning system and we end up with the same performance, resulting in 39. 6{\%} BLEU on newstest2019.
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
This allows for a direct comparison of lattice-based and lattice-free sequence discriminative training criteria such as MMI and sMBR, both using the same language model during training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring
LSTM based language models are an important part of modern LVCSR systems as they significantly improve performance over traditional backoff language models.
Generalizing Back-Translation in Neural Machine Translation
Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT).
Cumulative Adaptation for BLSTM Acoustic Models
Further, i-vectors were used as an input to the neural network to perform instantaneous speaker and environment adaptation, providing 8\% relative improvement in word error rate on the NIST Hub5 2000 evaluation test set.
Learning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data.
Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies
Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies.
Cross-Lingual Transfer
Low-Resource Neural Machine Translation
+3
Language Modeling with Deep Transformers
We explore deep autoregressive Transformer models in language modeling for speech recognition.
Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech
In a more realistic ASR scenario the audio signal contains significant portions of single-speaker speech and only part of the signal contains speech of multiple competing speakers.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation
To the best knowledge of the authors, the results obtained when training on the full LibriSpeech training set, are the best published currently, both for the hybrid DNN/HMM and the attention-based systems.
Ranked #22 on
Speech Recognition
on LibriSpeech test-other
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes
We address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words.
A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing
This work systematically analyzes the smoothing effect of vocabulary reduction for phrase translation models.
Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder
Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences.
Sisyphus, a Workflow Manager Designed for Machine Translation and Automatic Speech Recognition
Training and testing many possible parameters or model architectures of state-of-the-art machine translation or automatic speech recognition system is a cumbersome task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation
This work investigates an alternative model for neural machine translation (NMT) and proposes a novel architecture, where we employ a multi-dimensional long short-term memory (MDLSTM) for translation modeling.
The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task
We use several rule-based, heuristic methods to preselect sentence pairs.
The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018
In total we improve by 6. 8{\%} BLEU over our last year{'}s submission and by 4. 8{\%} BLEU over the winning system of the 2017 German→English task.
The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018
This paper describes the unsupervised neural machine translation (NMT) systems of the RWTH Aachen University developed for the English ↔ German news translation task of the \textit{EMNLP 2018 Third Conference on Machine Translation} (WMT 2018).
Improving Neural Language Models with Weight Norm Initialization and Regularization
Embedding and projection matrices are commonly used in neural language models (NLM) as well as in other sequence processing networks that operate on large vocabularies.
On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation
This work investigates the alignment problem in state-of-the-art multi-head attention models based on the transformer architecture.
Neural Hidden Markov Model for Machine Translation
Attention-based neural machine translation (NMT) models selectively focus on specific source positions to produce a translation, which brings significant improvements over pure encoder-decoder sequence-to-sequence models.
Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition
The proposed adaptation approach is based on the integration of the beamformer, which includes the mask estimation network, and the acoustic model of the ASR system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Neural Sign Language Translation
SLR seeks to recognize a sequence of continuous signs but neglects the underlying rich grammatical and linguistic structures of sign language that differ from spoken language.
RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
We compare the fast training and decoding speed of RETURNN of attention models for translation, due to fast CUDA LSTM kernels, and a fast pure TensorFlow beam search decoder.
Improved training of end-to-end attention models for speech recognition
Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition.
Ranked #39 on
Speech Recognition
on LibriSpeech test-clean
Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation
Recently, the neural machine translation systems showed their promising performance and surpassed the phrase-based systems for most translation tasks.
Re-Sign: Re-Aligned End-To-End Sequence Modelling With Deep Recurrent CNN-HMMs
This work presents an iterative re-alignment approach applicable to visual sequence labelling tasks such as gesture recognition, activity recognition and continuous sign language recognition.
A comprehensive study of batch construction strategies for recurrent neural networks in MXNet
In this work we compare different batch construction methods for mini-batch training of recurrent neural networks.
Local System Voting Feature for Machine Translation System Combination
In this paper, we enhance the traditional confusion network system combination approach with an additional model trained by a neural network.
RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks
In this work we release our extensible and easily configurable neural network training software.
A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
On this task, we get our best result with an 8 layer bidirectional LSTM and we show that a pretraining scheme with layer-wise construction helps for deep LSTMs.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data Is Continuous and Weakly Labelled
Furthermore, we demonstrate its use in continuous sign language recognition on two publicly available large sign language data sets, where it outperforms the current state-of-the-art by a large margin.
Extensions of the Sign Language Recognition and Translation Corpus RWTH-PHOENIX-Weather
This paper introduces the RWTH-PHOENIX-Weather 2014, a video-based, large vocabulary, German sign language corpus which has been extended over the last two years, tripling the size of the original corpus.
Arabic-Segmentation Combination Strategies for Statistical Machine Translation
Next, we try a different strategy, where we combine the different segmentation methods rather than the different segmentation schemes.
RWTH-PHOENIX-Weather: A Large Vocabulary Sign Language Recognition and Translation Corpus
This paper introduces the RWTH-PHOENIX-Weather corpus, a video-based, large vocabulary corpus of German Sign Language suitable for statistical sign language recognition and translation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
A Convergence Analysis of Log-Linear Training
Log-linear models are widely used probability models for statistical pattern recognition.
