TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
[eess.AS] Autorzy: Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko i 3 więcej
Contextualization is essential for production automatic speech recognition (ASR) systems, where user-provided phrases must be recognized accurately under strict latency constraints. Although many context-biasing methods improve recognition accuracy, they often do not address the practical requirements of modern production ASR systems: streaming inference, efficient batched decoding, user-specific context lists, and low runtime overhead. We propose TurboBias 2.0, a production-oriented framework for efficient phrase boosting in Transducer-based ASR systems. The framework extends GPU-accelerated TurboBias with a case-insensitive boosting graph and per-stream batched decoding, allowing each utterance in a batch to use an independent context-biasing configuration. This enables personalized context biasing for multiple simultaneous users without sharing or mixing their context lists. The prop…
- Kategoria arxiv
- eess.AS
- Kategoria
- eess.AS