Phase 06
Speech and Audio
The other half of human communication. Hear, understand, speak.
Lessons (17)
- 01Audio Fundamentals — Waveforms, Sampling, Fourier Transform
- 02Spectrograms, Mel Scale & Audio Features
- 03Audio Classification — From k-NN on MFCCs to AST and BEATs
- 04Speech Recognition (ASR) — CTC, RNN-T, Attention
- 05Whisper — Architecture & Fine-Tuning
- 06Speaker Recognition & Verification
- 07Text-to-Speech (TTS) — From Tacotron to F5 and Kokoro
- 08Voice Cloning & Voice Conversion
- 09Music Generation — MusicGen, Stable Audio, Suno, and the Licensing Earthquake
- 10Audio-Language Models — Qwen2.5-Omni, Audio Flamingo, GPT-4o Audio
- 11Real-Time Audio Processing
- 12Build a Voice Assistant Pipeline — The Phase 6 Capstone
- 13Neural Audio Codecs — EnCodec, SNAC, Mimi, DAC and the Semantic-Acoustic Split
- 14Voice Activity Detection & Turn-Taking — Silero, Cobra, and the Flush Trick
- 15Streaming Speech-to-Speech — Moshi, Hibiki, and Full-Duplex Dialogue
- 16Voice Anti-Spoofing & Audio Watermarking — ASVspoof 5, AudioSeal, WaveVerify
- 17Audio Evaluation — WER, MOS, UTMOS, MMAU, FAD, and the Open Leaderboards