Keyword boosting

Keyword boosting is a technique to improve the recognition of domain-specific words/phrases and proper nouns. It works by boosting the probability of specific tokens at inference time. The framework is inspired by TurboBias [1].

The framework can support up to 100 keywords, although 10-40 is recommended for optimal performance.

Keyword list format

Create a json containing your keywords, in the following format:

{
  "keywords": [
    "car",
    " cat",
    " Bat ",
    " New York "
  ]
}

Keywords are case and space sensitive, they should be formatted using the same character-set as the output of your decoder.

In the above example, the framework would increase the probabilities of words containing the sequence car, words starting with cat, the whole word Bat, and the whole phrase New York.

Keyword metrics

When a valid JSON is passed to --keywords_path, additional metrics are calculated:

• Biased WER (b-WER): WER of hypotheses that contain at least one keyword in the reference.
• Unbiased WER (u-WER): WER of hypotheses that do not contain any keywords in the reference.
• Precision: TP/(TP+FP) - Accuracy of keyword predictions (i.e., how many of the keywords that the model predicted were correct).
• Recall: TP/(TP+FN) - Model’s ability to find all keywords (i.e., what proportion of keywords in the ground truth did the model correctly predict).
• F1 Score: Harmonic mean of precision and recall.

Usage

Compute metrics

To compute metrics on your keywords, pass a valid JSON to the --keywords_path argument:

./scripts/val.sh \
  # ... other args ...
  --keywords_path path/to/words.json

Boost keywords

To boost the keywords, additionally supply the --boost_keywords flag:

./scripts/val.sh \
  # ... other args ...
  --keywords_path path/to/words.json
  --boost_keywords

How it works

We build an Aho-Corasick automaton over your phrases. Each node has a depth-shaped potential:

shape(d) =
            0                     if d = 0
            c0                    if d = 1
            c0*beta + ln(d)       if d >= 2

S(d) = context_score * shape(d)

At each token, we follow AC failure links (refunding partial bias), then take a goto edge (adding the incremental bias). Completed keywords keep their reward; partial near-misses net ≈ 0. This design is deterministic, efficient, and robust to overlaps, large lists and out-of-domain distractors.

Hyperparameters

• --keyword_boost_c0 (default 0.3): start-of-keyword boost (depth 1).
• --keyword_boost_beta (default 0.9): extra front-loading at depth 2; later steps taper via ln(depth).
• --keyword_boost_context_score (default 0.4 for greedy decoder, 1.0 for beam decoder): global strength.

Recommendations

Keep c0 and beta at their defaults; they work well across domains and for different keyword list sizes (up to 100).

• Greedy Decoder

  If you wish to trade F1 vs WER (figure 1), adjust only context_score:

  • Try 0.1-0.6

  • Lowering towards 0.1 -> slightly better WER and precision, slightly lower F1 and recall.

  • Exceeding 0.6 typically degrades both WER and F1.

  • Default 0.4 is recommended.

    

    Figure 1: WER and F1 vs context score, averaged across 4 test datasets with 10-15 keywords each.

• Beam Decoder

  If you wish to trade F1 vs WER (figure 2), adjust only context_score:

  • Try 0.6-1.0

  • Lowering towards 0.6 -> slightly better WER and precision, slightly lower F1 and recall.

  • Exceeding 1.0 typically degrades both WER and F1.

  • Default 1.0 is recommended.

    

    Figure 2: WER and F1 vs context score, averaged across 4 test datasets with 10-15 keywords each.

  See figure 3 for scaling with the number of boosted keywords. Guidance:

  • Recommended: 10-40 keywords

  • Maximum: 100 keywords

  • Although the framework is remarkably robust to out-of-domain “distractors”, best results come from keeping the list of keywords relevant.

    Figure 3: WER and F1 versus the number of boosted keywords for one test dataset. The shaded region (>75) adds out-of-domain “distractor” phrases in addition to the original 75 relevant ones.

Expected Results

When boosting is enabled:

• F1: 10-40% relative improvement
• WER: up to ~1% relative improvement

Actual gains vary by domain, audio conditions, and list composition.

References

[1] A. Andrusenko, V. Bataev, L. Grigoryan, V. Lavrukhin, and B. Ginsburg, ‘TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree’, arXiv [eess.AS]. 2025.