English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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, wefurther analyze their capability for generating high-quality time alignmentbetween the speech signal and the transcription, which can be crucial for manysubsequent applications. Moreover, we propose several methods to improveconvergence of from-scratch full-sum training by addressing the alignmentmodeling issue. Systematic comparison is conducted on both Switchboard andLibriSpeech corpora across CTC, posterior HMM with and w/o transitionprobabilities, and standard hybrid HMM. We also provide a detailed analysis ofboth Viterbi forced-alignment and Baum-Welch full-sum occupation probabilities.

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