282 citations · 700 across the 18 of their papers we have counts for
21 papers
Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Study
Zijian Yang, Jörg Barkoczi, Ralf Schlüter +1
Unsupervised speech recognition is a task of training a speech recognition model with unpaired data. To determine when and how unsupervised speech recognition can succeed, and how…
Right Label Context in End-to-End Training of Time-Synchronous ASR Models
Tina Raissi, Ralf Schlüter, Hermann Ney
Current time-synchronous sequence-to-sequence automatic speech recognition (ASR) models are trained by using sequence level cross-entropy that sums over all alignments. Due to the…
Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition
Jingjing Xu, Wei Zhou, Zijian Yang +2
Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints such as memory and latency. To avoid redundant training and opt…
Automatic Learning of Subword Dependent Model Scales
Felix Meyer, Wilfried Michel, Mohammad Zeineldeen +2
To improve the performance of state-of-the-art automatic speech recognition systems it is common practice to include external knowledge sources such as language models or prior cor…
On Sampling-Based Training Criteria for Neural Language Modeling
Yingbo Gao, David Thulke, Alexander Gerstenberger +3
As the vocabulary size of modern word-based language models becomes ever larger, many sampling-based training criteria are proposed and investigated. The essence of these sampling…
The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech
Yu Qiao, Wei Zhou, Elma Kerz +1
In recent years, automated approaches to assessing linguistic complexity in second language (L2) writing have made significant progress in gauging learner performance, predicting h…
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures
Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes +2
Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resourc…
On Architectures and Training for Raw Waveform Feature Extraction in ASR
Peter Vieting, Christoph Lüscher, Wilfried Michel +2
With the success of neural network based modeling in automatic speech recognition (ASR), many studies investigated acoustic modeling and learning of feature extractors directly bas…
Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
Wei Zhou, Simon Berger, Ralf Schlüter +1
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 modeli…
Context-Dependent Acoustic Modeling without Explicit Phone Clustering
Tina Raissi, Eugen Beck, Ralf Schlüter +1
Phoneme-based acoustic modeling of large vocabulary automatic speech recognition takes advantage of phoneme context. The large number of context-dependent (CD) phonemes and their h…
Full-Sum Decoding for Hybrid HMM based Speech Recognition using LSTM Language Model
Wei Zhou, Ralf Schlüter, Hermann Ney
In hybrid HMM based speech recognition, LSTM language models have been widely applied and achieved large improvements. The theoretical capability of modeling any unlimited context…
On using 2D sequence-to-sequence models for speech recognition
Parnia Bahar, Albert Zeyer, Ralf Schlüter +1
Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are…
On Using SpecAugment for End-to-End Speech Translation
Parnia Bahar, Albert Zeyer, Ralf Schlüter +1
This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation. SpecAugment is a low-cost implementation method applied directly to the…
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
Wilfried Michel, Ralf Schlüter, Hermann Ney
Sequence discriminative training criteria have long been a standard tool in automatic speech recognition for improving the performance of acoustic models over their maximum likelih…
LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring
Eugen Beck, Wei Zhou, Ralf Schlüter +1
LSTM based language models are an important part of modern LVCSR systems as they significantly improve performance over traditional backoff language models. Incorporating them effi…
Cumulative Adaptation for BLSTM Acoustic Models
Markus Kitza, Pavel Golik, Ralf Schlüter +1
This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Lon…
Language Modeling with Deep Transformers
Kazuki Irie, Albert Zeyer, Ralf Schlüter +1
We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifica…
Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech
Tobias Menne, Ilya Sklyar, Ralf Schlüter +1
Significant performance degradation of automatic speech recognition (ASR) systems is observed when the audio signal contains cross-talk. One of the recently proposed approaches to…
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation
Christoph Lüscher, Eugen Beck, Kazuki Irie +5
We present state-of-the-art automatic speech recognition (ASR) systems employing a standard hybrid DNN/HMM architecture compared to an attention-based encoder-decoder design for th…
Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition
Tobias Menne, Ralf Schlüter, Hermann Ney
This paper presents, in the context of multi-channel ASR, a method to adapt a mask based, statistically optimal beamforming approach to a speaker of interest. The beamforming vecto…
Improved training of end-to-end attention models for speech recognition
Albert Zeyer, Kazuki Irie, Ralf Schlüter +1
Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competit…