173 citations · 306 across the 58 of their papers we have counts for
7 papers · 1 filter
Tight Integrated End-to-End Training for Cascaded Speech Translation
Parnia Bahar, Tobias Bieschke, Ralf Schlüter +1
A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation b…
Early Stage LM Integration Using Local and Global Log-Linear Combination
Wilfried Michel, Ralf Schlüter, Hermann Ney
Sequence-to-sequence models with an implicit alignment mechanism (e.g. attention) are closing the performance gap towards traditional hybrid hidden Markov models (HMM) for the task…
Investigation of Large-Margin Softmax in Neural Language Modeling
Jingjing Huo, Yingbo Gao, Weiyue Wang +2
To encourage intra-class compactness and inter-class separability among trainable feature vectors, large-margin softmax methods are developed and widely applied in the face recogni…
A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models
Mohammad Zeineldeen, Albert Zeyer, Wei Zhou +3
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…
A New Training Pipeline for an Improved Neural Transducer
Albert Zeyer, André Merboldt, Ralf Schlüter +1
The RNN transducer is a promising end-to-end model candidate. We compare the original training criterion with the full marginalization over all alignments, to the commonly used max…
Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition without Length Bias
Wei Zhou, Ralf Schlüter, Hermann Ney
As one popular modeling approach for end-to-end speech recognition, attention-based encoder-decoder models are known to suffer the length bias and corresponding beam problem. Diffe…
The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment
Wei Zhou, Wilfried Michel, Kazuki Irie +3
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. Data augmentation using SpecAugment is su…