Skip to content
AI News HubLIVE
More
Summary only

Lightweight Voice Gender Classifier for European Voice AI (1MB, ONNX, 4ms)

A sub-1MB Bi-LSTM model that classifies voice gender in under 5ms on CPU, designed for real-time voice AI pipelines in European languages with grammatical gender. Achieves over 94% accuracy on standard-accent speech, with limitations on accented speech and binary classification only.

SourceHacker News AIAuthor: biduskamil
Lightweight Voice Gender Classifier for European Voice AI (1MB, ONNX, 4ms)
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Model size 0.64MB, inference ~4ms on CPU single-threaded, no PyTorch required at inference.
  • Trained on LibriSpeech and FLEURS for English, German, French, Spanish, Italian.
  • Enables correct gender-specific address inflection for voice assistants in gendered languages.
  • Binary classification only; not suitable for non-binary individuals or heavily accented speech without retraining.

Highlights and analysis are generated automatically and may contain errors. Check the original source.