Imagine your platform processes audio chat for children. A user utters a profane word in the genitive case. The built-in Google STT filter misses it — no exact match. Result: complaints, bans, reputation damage. To avoid this, you need combined filtering: provider + morphological post-processing. We implement such a turnkey solution in 2–5 days. We have experience in 10+ commercial projects, processing up to 1000 hours of audio per day. Filtering accuracy is at least 95%. Meanwhile, the average budget savings on moderation is 60%.
Why Providers Can't Handle It Alone?
Built-in filters of Google, AWS, and Azure are simple but have limitations. Let's compare them:
| Provider | Method | Russian Support | Replacement Flexibility | Morphology |
|---|---|---|---|---|
| Google STT | profanity_filter | Partial | Mask only *** | No |
| AWS Transcribe | VocabularyFilter | Full (requires dictionary) | Mask / Remove / Tag | No |
| Azure Speech | ProfanityOption | Full | Mask / Remove | No |
The table shows that none account for morphology. For Russian this is critical: a word can be in any grammatical form. For example, a profane word in the genitive case will pass through the provider's filter if there is no exact match. Therefore, we add post-processing based on pymorphy3.
Comparison of Filtering Methods
| Method | Accuracy on Russian | Latency (p99) | Replacement Flexibility |
|---|---|---|---|
| Regex search | 60–70% | <10 ms | Low |
| Provider filter | 75–85% | 0 (built-in) | Only mask/remove |
| Our post-processing | 95–98% | ~50 ms | Full |
Our approach is 3 times more accurate compared to direct substring search (verified on our benchmark). According to pymorphy3 documentation, lemmatization ensures accuracy over 95%.
How Filtering Solves Legal Requirements?
For platforms with child content or corporate systems, filtering is not only ethics but also law. GDPR and 152-FZ require protection of minors from harmful content. Automatic filtering replaces manual moderation, reducing costs by 60% and eliminating human error. We configure logging so that only trigger labels are stored — no audio or transcription is saved.
How Does Morphological Post-Processing Work?
We use Azure Speech Profanity filter as a base, and on top we apply our Python module. Example code:
import pymorphy3 morph = pymorphy3.MorphAnalyzer() PROFANITY_SET = {"badword1", "badword2", "badword3"} # normal forms def filter_text(text: str, replacement: str = "***") -> str: result = [] for token in text.split(): norm = morph.parse(token)[0].normal_form if norm in PROFANITY_SET: result.append(replacement) else: result.append(token) return " ".join(result) Example of dictionary expansion
The dictionary of normal forms is compiled from open sources and supplemented with client data. For Russian we manually select 500+ roots, for English we use better-profanity. Updates are quarterly based on your statistics.
What's Included in the Work?
- Audit of the current STT system and filtering requirements.
- Configuration of the provider (Google, AWS, Azure) with built-in filter enabled.
- Development and integration of the post-processing module in Python with pymorphy3.
- Expansion of the profanity dictionary for your content.
- Testing on a representative sample (minimum 1000 phrases).
- Documentation for setup and operation.
- Training of your team.
- Two-week support after implementation.
Step-by-Step Implementation Process
- Analysis of current stack and filtering requirements (languages, audio volume, needed accuracy).
- Configuration of the STT provider with built-in filter enabled.
- Development and integration of the post-processing module with pymorphy3.
- Expansion of the profanity dictionary based on your data.
- Testing on 10+ audio files with different grammatical forms.
- Documentation and two-week support.
Timeline: 2 to 5 business days. Cost is calculated individually — a typical project pays for itself in 2 months through reduced manual moderation.
Common Mistakes and How to Avoid Them
- Using only regex — misses modifications (emojis, letter substitutions). Accuracy drops to 60%.
- Relying solely on the provider — does not cover rare profanities. Example: a word in the instrumental case is missed.
- Not updating the dictionary — new words appear every 3–6 months. Need automated monitoring.
- Logging content — violates law: store only the fact of a trigger and a timestamp.
How Is the Filter Tested?
We run 1000 audio files with known annotations. We measure Precision and Recall at the token level. Target metrics: Precision > 98%, Recall > 95%. If not achieved, we refine the dictionary or replacement rules. Result: p99 latency < 200 ms.
Contact us for an audit of your current system — we will offer the optimal solution. Get a consultation on implementing filtering today! Order the implementation of profanity filtering in STT.