7 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…
Reproducing and Dissecting Denoising Language Models for Speech Recognition
Dorian Koch, Albert Zeyer, Nick Rossenbach +2
Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their abilit…
Supplementary Resources and Analysis for Automatic Speech Recognition Systems Trained on the Loquacious Dataset
Nick Rossenbach, Robin Schmitt, Tina Raissi +3
The recently published Loquacious dataset aims to be a replacement for established English automatic speech recognition (ASR) datasets such as LibriSpeech or TED-Lium. The main goa…
Analysis of Domain Shift across ASR Architectures via TTS-Enabled Separation of Target Domain and Acoustic Conditions
Tina Raissi, Nick Rossenbach, Ralf Schlüter
We analyze automatic speech recognition (ASR) modeling choices under domain mismatch, comparing classic modular and novel sequence-to-sequence (seq2seq) architectures. Across the d…
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…