Hyundai Motor Company AIR Lab · Feb 2022 – Apr 2022
In-vehicle & Mobile Speech Recognition
01Background & Goals
- Engine and road noise degrade speech recognition inside a car.
- To offset this, we used a language model in decoding, then proposed and studied decoding with a language model that reads the previous dialogue turns.
02Contributions
Context-aware LM-integrated decoding
- Trained a generative LM (KoGPT) on spoken-dialogue data
- Modified the decoding algorithm to combine acoustic-model and LM scores
- Built a recognition pipeline that includes the previous dialogue turns
03Tech Stack
- Framework / Platform
- PyTorch, Fairseq, Transformers
- Methodology
- Joint decoding, Beam search, LM fine-tuning
04Results
- Improved recognition accuracy by 5% under external noise