Summary of Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription Without Explicit Fine-tuning Of Whisper Model, by Vishakha Lall et al.
Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Model
by Vishakha Lall, Yisi Liu
First submitted to arxiv on: 24 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Sound (cs.SD); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces a method to enhance the accuracy of OpenAI’s Whisper Automated Speech Recognition (ASR) model without fine-tuning or altering its parameters, using only a relatively small training dataset. The approach leverages contextual biasing, integrating a neural-symbolic prefix tree structure to guide the model’s transcription output towards a specific vocabulary. Experimental results on a maritime dataset show a notable reduction in word error rate and improved performance of downstream applications compared to original Whisper models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps improve speech-to-text technology by making it better at recognizing words in specific situations, like maritime communication. The researchers found a way to make the OpenAI Whisper model more accurate without needing lots of extra training data or changing its internal workings. They used a special technique called contextual biasing that guides the model’s output towards certain words and phrases, which worked really well on their test dataset. |
Keywords
» Artificial intelligence » Fine tuning
