Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition

no code implementations • 12 Jun 2023 • Belen Alastruey, Lukas Drude, Jahn Heymann, Simon Wiesler

Convolutional frontends are a typical choice for Transformer-based automatic speech recognition to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly.

Automatic Speech Recognition speech-recognition +1

Contextual-Utterance Training for Automatic Speech Recognition

no code implementations • 27 Oct 2022 • Alejandro Gomez-Alanis, Lukas Drude, Andreas Schwarz, Rupak Vignesh Swaminathan, Simon Wiesler

Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Improving RNN-T ASR Accuracy Using Context Audio

no code implementations • 20 Nov 2020 • Andreas Schwarz, Ilya Sklyar, Simon Wiesler

We present a training scheme for streaming automatic speech recognition (ASR) based on recurrent neural network transducers (RNN-T) which allows the encoder network to learn to exploit context audio from a stream, using segmented or partially labeled sequences of the stream during training.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Compacting Neural Network Classifiers via Dropout Training

no code implementations • 18 Nov 2016 • Yotaro Kubo, George Tucker, Simon Wiesler

We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization, yet extracts a compact neural network for run-time efficiency.

speech-recognition Speech Recognition

A Convergence Analysis of Log-Linear Training

no code implementations • NeurIPS 2011 • Simon Wiesler, Hermann Ney

Log-linear models are widely used probability models for statistical pattern recognition.

Handwriting Recognition