Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
akhaliq
Abstract
In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck. We propose a non-autoregressive LM-fused ASR system that effectively leverages the parallelization capabilities of accelerator hardware. Our approach combines the Universal Speech Model (USM) and the PaLM 2 language model in per-segment scoring mode, achieving an average relative WER improvement across all languages of 10.8% on FLEURS and 3.6% on YouTube captioning. Furthermore, our comprehensive ablation study analyzes key parameters such as LLM size, context length, vocabulary size, fusion methodology. For instance, we explore the impact of LLM size ranging from 128M to 340B parameters on ASR performance. This study provides valuable insights into the factors influencing the effectiveness of practical large-scale LM-fused speech recognition systems.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers (2024)
- Boosting Large Language Model for Speech Synthesis: An Empirical Study (2023)
- USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models (2023)
- Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR (2024)
- Improved Long-Form Speech Recognition By Jointly Modeling The Primary And Non-Primary Speakers (2023)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper