HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch

RWTH Publications (RWTH Aachen)

Abstract

In this work, we compare from-scratch sequence-level cross-entropy (full-sum) training of Hidden Markov Model (HMM) and Connectionist Temporal Classification (CTC) topologies for automatic speech recognition (ASR). Besides accuracy, we further analyze their capability for generating high-quality time alignment between the speech signal and the transcription, which can be crucial for many subsequent applications. Moreover, we propose several methods to improve convergence of from-scratch full-sum training by addressing the alignment modeling issue. Systematic comparison is conducted on both Switchboard and LibriSpeech corpora across CTC, posterior HMM with and w/o transition probabilities, and standard hybrid HMM. We also provide a detailed analysis of both Viterbi forced-alignment and Baum-Welch full-sum occupation probabilities.

Authors 5

1. Tina Raissi Aachen Human Language Technology and Pattern Recognition Group

   RWTH Aachen University

   Affiliation as printed

   Human Language Technology and Pattern Recognition Group , RWTH Aachen University , Germany

2. Wei Guo Zhou Aachen Human Language Technology and Pattern Recognition Group

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH , Aachen , Germany

   Human Language Technology and Pattern Recognition Group , RWTH Aachen University , Germany

3. Simon Berger Aachen Human Language Technology and Pattern Recognition Group

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH , Aachen , Germany

   Human Language Technology and Pattern Recognition Group , RWTH Aachen University , Germany

4. Ralf Schlüter
5. Hermann Ney Aachen Human Language Technology and Pattern Recognition Group

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH , Aachen , Germany

   Human Language Technology and Pattern Recognition Group , RWTH Aachen University , Germany