Comparative Analysis of the wav2vec 2.0 Feature Extractor

RWTH Publications (RWTH Aachen)

Abstract

Automatic speech recognition (ASR) systems typically use handcrafted feature extraction pipelines. To avoid their inherent information loss and to achieve more consistent modeling from speech to transcribed text, neural raw waveform feature extractors (FEs) are an appealing approach. Also the wav2vec 2.0 model, which has recently gained large popularity, uses a convolutional FE which operates directly on the speech waveform. However, it is not yet studied extensively in the literature. In this work, we study its capability to replace the standard feature extraction methods in a connectionist temporal classification (CTC) ASR model and compare it to an alternative neural FE. We show that both are competitive with traditional FEs on the LibriSpeech benchmark and analyze the effect of the individual components. Furthermore, we analyze the learned filters and show that the most important information for the ASR system is obtained by a set of bandpass filters.

Authors 3

1. Peter Vieting Aachen Machine Learning and Human Language Technology

   RWTH Aachen University

   Affiliation as printed

   Machine Learning and Human Language Technology , RWTH Aachen University , Germany

2. Ralf Schlüter
3. Hermann Ney Aachen Machine Learning and Human Language Technology

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH , Germany

   Machine Learning and Human Language Technology , RWTH Aachen University , Germany