HMM Vs. CTC For Automatic Speech Recognition: Comparison Based On Full-sum Training From Scratch

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyraissi2022hmm

Related papers

• Investigating The Effect Of Label Topology And Training Criterion On ASR Performance And Alignment Quality (2024)0.00
• Full-sum Decoding For Hybrid HMM Based Speech Recognition Using LSTM Language Model (2020)0.00
• On Lattice-free Boosted MMI Training Of HMM And Ctc-based Full-context ASR Models (2021)7.81
• Multiple-hypothesis Ctc-based Semi-supervised Adaptation Of End-to-end Speech Recognition (2021)5.84
• CR-CTC: Consistency Regularization On CTC For Improved Speech Recognition (2024)6.30
• Ctc-segmentation Of Large Corpora For German End-to-end Speech Recognition (2020)12.93
• Comparison Of Decoding Strategies For CTC Acoustic Models (2017)10.48
• Multitask Learning With CTC And Segmental CRF For Speech Recognition (2017)0.00