6 papers
Positional Encoding in the Context of Memristor-Based Analog Computation for Automatic Speech Recognition
Benedikt Hilmes, Nick Rossenbach, Ralf Schlüter
Memristors provide a new chance for resource-efficient computation of neural models for natural language processing by enabling analog execution of vector-matrix-multiplication. Ye…
Regularizing Learnable Feature Extraction for Automatic Speech Recognition
Peter Vieting, Maximilian Kannen, Benedikt Hilmes +2
Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained…
Unified Learnable 2D Convolutional Feature Extraction for ASR
Peter Vieting, Benedikt Hilmes, Ralf Schlüter +1
Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for dif…
Analyzing the Importance of Blank for CTC-Based Knowledge Distillation
Benedikt Hilmes, Nick Rossenbach, Ralf Schlüter
With the rise of large pre-trained foundation models for automatic speech recognition new challenges appear. While the performance of these models is good, runtime and cost of infe…
Running Conventional Automatic Speech Recognition on Memristor Hardware: A Simulated Approach
Nick Rossenbach, Benedikt Hilmes, Leon Brackmann +2
Memristor-based hardware offers new possibilities for energy-efficient machine learning (ML) by providing analog in-memory matrix multiplication. Current hardware prototypes cannot…
On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures
Benedikt Hilmes, Nick Rossenbach, and Ralf Schlüter
In this work we evaluate the utility of synthetic data for training automatic speech recognition (ASR). We use the ASR training data to train a text-to-speech (TTS) system similar…