End-to-end Training Of A Neural HMM With Label And Transition Probabilities

Abstract

We investigate a novel modeling approach for end-to-end neural network training using hidden Markov models (HMM) where the transition probabilities between hidden states are modeled and learned explicitly. Most contemporary sequence-to-sequence models allow for from-scratch training by summing over all possible label segmentations in a given topology. In our approach there are explicit, learnable probabilities for transitions between segments as opposed to a blank label that implicitly encodes duration statistics. We implement a GPU-based forward-backward algorithm that enables the simultaneous training of label and transition probabilities. We investigate recognition results and additionally Viterbi alignments of our models. We find that while the transition model training does not improve recognition performance, it has a positive impact on the alignment quality. The generated alignments are shown to be viable targets in state-of-the-art Viterbi trainings.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keymann2023end

Related papers

• End-to-end Training Approaches For Discriminative Segmental Models (2016)5.84
• An Infinite Hidden Markov Model With Similarity-biased Transitions (2017)0.00
• Right Label Context In End-to-end Training Of Time-synchronous ASR Models (2025)0.00
• Phoneme Based Neural Transducer For Large Vocabulary Speech Recognition (2020)9.59
• Neural Sequence-to-sequence Speech Synthesis Using A Hidden Semi-markov Model Based Structured Attention Mechanism (2021)0.00
• Equivalence Of Segmental And Neural Transducer Modeling: A Proof Of Concept (2021)4.52
• Hmm-free Encoder Pre-training For Streaming RNN Transducer (2021)0.00
• Full-sum Decoding For Hybrid HMM Based Speech Recognition Using LSTM Language Model (2020)0.00