activity
20182020
most citedOn Using SpecAugment for End-to-End Speech Translation

23 citations · 23 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CL2020

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…

cs.CL2020

Two-Way Neural Machine Translation: A Proof of Concept for Bidirectional Translation Modeling using a Two-Dimensional Grid

Parnia Bahar, Christopher Brix, Hermann Ney

Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence. However, it is not e…

cs.LG2020

Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture

Christopher Brix, Parnia Bahar, Hermann Ney

Sparse models require less memory for storage and enable a faster inference by reducing the necessary number of FLOPs. This is relevant both for time-critical and on-device computa…

cs.CL2019

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…

cs.CL201923 cited

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…

cs.CL2019

A Comparative Study on End-to-end Speech to Text Translation

Parnia Bahar, Tobias Bieschke, Hermann Ney

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. In this work, we provide an o…