5 papers
LLMs and Speech: Integration vs. Combination
Robin Schmitt, Albert Zeyer, Mohammad Zeineldeen +2
In this work, we study different approaches to utilize large language models (LLMs) for automatic speech recognition (ASR). Specifically, we compare the tight integration of an aco…
Revisiting the Relation Between Language Model Perplexity and ASR Word Error Rate for Modern End-to-End Speech Recognition
Mohammad Zeineldeen, Albert Zeyer, Haoran Zhang +3
Language model (LM) perplexity (PPL) has historically been used as a proxy for automatic speech recognition (ASR) word error rate (WER), with prior work reporting an approximately…
Supplementary Resources and Analysis for Automatic Speech Recognition Systems Trained on the Loquacious Dataset
Nick Rossenbach, Robin Schmitt, Tina Raissi +3
The recently published Loquacious dataset aims to be a replacement for established English automatic speech recognition (ASR) datasets such as LibriSpeech or TED-Lium. The main goa…
A Comparative Analysis on ASR System Combination for Attention, CTC, Factored Hybrid, and Transducer Models
Noureldin Bayoumi, Robin Schmitt, Tina Raissi +3
Combination approaches for speech recognition (ASR) systems cover structured sentence-level or word-based merging techniques as well as combination of model scores during beam sear…
The Conformer Encoder May Reverse the Time Dimension
Robin Schmitt, Albert Zeyer, Mohammad Zeineldeen +2
We sometimes observe monotonically decreasing cross-attention weights in our Conformer-based global attention-based encoder-decoder (AED) models, Further investigation shows that t…