Search Results - "Schluter, Ralf"

From Feedforward to Recurrent LSTM Neural Networks for Language Modeling by Sundermeyer, Martin, Ney, Hermann, Schluter, Ralf

“…Language models have traditionally been estimated based on relative frequencies, using count statistics that can be extracted from huge amounts of text data…”
Get full text

Investigations on an EM-Style Optimization Algorithm for Discriminative Training of HMMs by Heigold, Georg, Ney, Hermann, Schluter, Ralf

“…Today's speech recognition systems are based on hidden Markov models (HMMs) with Gaussian mixture models whose parameters are estimated using a discriminative…”
Get full text

Mean-normalized stochastic gradient for large-scale deep learning by Wiesler, Simon, Richard, Alexander, Schluter, Ralf, Ney, Hermann

“…Deep neural networks are typically optimized with stochastic gradient descent (SGD). In this work, we propose a novel second-order stochastic optimization…”
Get full text

A Comparison of Transformer and LSTM Encoder Decoder Models for ASR by Zeyer, Albert, Bahar, Parnia, Irie, Kazuki, Schluter, Ralf, Ney, Hermann

“…We present competitive results using a Transformer encoder-decoder-attention model for end-to-end speech recognition needing less training time compared to a…”
Get full text

Does the Cost Function Matter in Bayes Decision Rule? by Schluter, Ralf, Nussbaum-Thom, Markus, Ney, Hermann

“…In many tasks in pattern recognition, such as automatic speech recognition (ASR), optical character recognition (OCR), part-of-speech (POS) tagging, and other…”
Get full text

WFST Enabled Solutions to ASR Problems: Beyond HMM Decoding by Hoffmeister, B., Heigold, G., Rybach, D., Schluter, R., Ney, H.

“…During the last decade, weighted finite-state transducers (WFSTs) have become popular in speech recognition. While their main field of application remains…”
Get full text

End-to-End Speech Recognition: A Survey by Prabhavalkar, Rohit, Hori, Takaaki, Sainath, Tara N., Schluter, Ralf, Watanabe, Shinji

“…In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning has brought considerable reductions in word error rate of…”
Get full text

Tight Integrated End-to-End Training for Cascaded Speech Translation by Bahar, Parnia, Bieschke, Tobias, Schluter, Ralf, Ney, Hermann

“…A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps…”
Get full text

Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition by Zhou, Wei, Berger, Simon, Schluter, Ralf, Ney, Hermann

“…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…”
Get full text

Returnn: The RWTH extensible training framework for universal recurrent neural networks by Doetsch, Patrick, Zeyer, Albert, Voigtlaender, Paul, Kulikov, Ilia, Schluter, Ralf, Ney, Hermann

“…In this work we release our extensible and easily configurable neural network training software. It provides a rich set of functional layers with a particular…”
Get full text

On Language Model Integration for RNN Transducer Based Speech Recognition by Zhou, Wei, Zheng, Zuoyun, Schluter, Ralf, Ney, Hermann

“…The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM…”
Get full text

Conformer-Based Hybrid ASR System For Switchboard Dataset by Zeineldeen, Mohammad, Xu, Jingjing, Luscher, Christoph, Michel, Wilfried, Gerstenberger, Alexander, Schluter, Ralf, Ney, Hermann

“…The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving…”
Get full text

Efficient Sequence Training of Attention Models Using Approximative Recombination by Wynands, Nils-Philipp, Michel, Wilfried, Rosendahl, Jan, Schluter, Ralf, Ney, Hermann

“…Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over…”
Get full text

Multilingual representations for low resource speech recognition and keyword search by Jia Cui, Kingsbury, Brian, Ramabhadran, Bhuvana, Sethy, Abhinav, Audhkhasi, Kartik, Xiaodong Cui, Kislal, Ellen, Mangu, Lidia, Nussbaum-Thom, Markus, Picheny, Michael, Tuske, Zoltan, Golik, Pavel, Schluter, Ralf, Ney, Hermann, Gales, Mark J. F., Knill, Kate M., Ragni, Anton, Haipeng Wang, Woodland, Phil

“…This paper examines the impact of multilingual (ML) acoustic representations on Automatic Speech Recognition (ASR) and keyword search (KWS) for low resource…”
Get full text

Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems by Rossenbach, Nick, Zeyer, Albert, Schluter, Ralf, Ney, Hermann

“…Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based…”
Get full text

A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition by Zeyer, Albert, Doetsch, Patrick, Voigtlaender, Paul, Schluter, Ralf, Ney, Hermann

“…Recent experiments show that deep bidirectional long short-term memory (BLSTM) recurrent neural network acoustic models outperform feedforward neural networks…”
Get full text

Exploring A Zero-Order Direct Hmm Based on Latent Attention for Automatic Speech Recognition by Bahar, Parnia, Makarov, Nikita, Zeyer, Albert, Schluter, Ralf, Ney, Hermann

“…In this paper, we study a simple yet elegant latent variable attention model for automatic speech recognition (ASR) which enables an integration of attention…”
Get full text

Multilingual MRASTA features for low-resource keyword search and speech recognition systems by Tuske, Zoltan, Nolden, David, Schluter, Ralf, Ney, Hermann

“…This paper investigates the application of hierarchical MRASTA bottleneck (BN) features for under-resourced languages within the IARPA Babel project. Through…”
Get full text

Faster sequence training by Zeyer, Albert, Kulikov, Ilia, Schluter, Ralf, Ney, Hermann

“…It has been shown that sequence-discriminative training can improve the performance for large vocabulary continuous speech recognition. Our main contribution…”
Get full text

Upper and Lower Tight Error Bounds for Feature Omission with an Extension to Context Reduction by Schluter, Ralf, Beck, Eugen, Ney, Hermann

“…In this work, fundamental analytic results in the form of error bounds are presented that quantify the effect of feature omission and selection for pattern…”
Get full text