activity
20192022
most citedWhy does CTC result in peaky behavior?

18 citations · 26 across the 6 of their papers we have counts for

collaborators

15 papers

cs.CL2022

Monotonic segmental attention for automatic speech recognition

Albert Zeyer, Robin Schmitt, Wei Zhou +2

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, bette…

cs.SD20221 cited

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

Tina Raissi, Wei Zhou, Simon Berger +2

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 a…

cs.SD2022

Improving Factored Hybrid HMM Acoustic Modeling without State Tying

Tina Raissi, Eugen Beck, Ralf Schlüter +1

In this work, we show that a factored hybrid hidden Markov model (FH-HMM) which is defined without any phonetic state-tying outperforms a state-of-the-art hybrid HMM. The factored…

cs.LG202118 cited

Why does CTC result in peaky behavior?

Albert Zeyer, Ralf Schlüter, Hermann Ney

The peaky behavior of CTC models is well known experimentally. However, an understanding about why peaky behavior occurs is missing, and whether this is a good property. We provide…

cs.CL2021

Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models

Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel +3

Attention-based encoder-decoder (AED) models learn an implicit internal language model (ILM) from the training transcriptions. The integration with an external LM trained on much m…

cs.CL2021

Librispeech Transducer Model with Internal Language Model Prior Correction

Albert Zeyer, André Merboldt, Wilfried Michel +2

We present our transducer model on Librispeech. We study variants to include an external language model (LM) with shallow fusion and subtract an estimated internal LM. This is just…