# TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems

arXiv: https://arxiv.org/abs/2608.21343 · HTML: https://mlsanity.com/paper/2608.21343/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://mlsanity.com/paper/2305.05084/) (2023)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [Contextual RNN-T For Open Domain ASR](https://mlsanity.com/paper/2006.03411/) (2020)
- [SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation](https://mlsanity.com/paper/2310.09424/) (2023)
- [SLM: Bridge the thin gap between speech and text foundation models](https://mlsanity.com/paper/2310.00230/) (2023)
- [Efficient Sequence Transduction by Jointly Predicting Tokens and Durations](https://mlsanity.com/paper/2304.06795/) (2023)
- [PromptASR for contextualized ASR with controllable style](https://mlsanity.com/paper/2309.07414/) (2023)
- [Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU](https://mlsanity.com/paper/2406.03791/) (2024)
- [Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation](https://mlsanity.com/paper/2407.10303/) (2024)
- [Spell my name: keyword boosted speech recognition](https://mlsanity.com/paper/2110.02791/) (2021)
- [Label-Looping: Highly Efficient Decoding for Transducers](https://mlsanity.com/paper/2406.06220/) (2024)
- [Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter](https://mlsanity.com/paper/2406.07096/) (2024)
- [NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding](https://mlsanity.com/paper/2505.22857/) (2025)
- [Pushing the Limits of Beam Search Decoding for Transducer-based ASR models](https://mlsanity.com/paper/2506.00185/) (2025)
- [TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree](https://mlsanity.com/paper/2508.07014/) (2025)
- [Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wild](https://mlsanity.com/paper/2604.07354/) (2026)
- [Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization](https://mlsanity.com/paper/2604.19079/) (2026)

## Abstract (arXiv)

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 proposed framework supports both offline and streaming inference and can be used with greedy and beam-search decoding. Experiments show that TurboBias 2.0 improves contextual phrase recognition while preserving low latency and high throughput.