← Back to curriculum
Phase 06 · 17 lessons
Speech & Audio
Hear, understand, speak.
01Audio Fundamentals — Waveforms, Sampling, Fourier TransformLearn02Spectrograms, Mel Scale & Audio FeaturesBuild03Audio Classification — From k-NN on MFCCs to AST and BEATsBuild04Speech Recognition (ASR) — CTC, RNN-T, AttentionBuild05Whisper — Architecture & Fine-TuningBuild06Speaker Recognition & VerificationBuild07Text-to-Speech (TTS) — From Tacotron to F5 and KokoroBuild08Voice Cloning & Voice ConversionBuild09Music Generation — MusicGen, Stable Audio, Suno, and the Licensing EarthquakeBuild10Audio-Language Models — Qwen2.5-Omni, Audio Flamingo, GPT-4o AudioBuild11Real-Time Audio ProcessingBuild12Build a Voice Assistant Pipeline — The Phase 6 CapstoneBuild13Neural Audio Codecs — EnCodec, SNAC, Mimi, DAC and the Semantic-Acoustic SplitLearn14Voice Activity Detection & Turn-Taking — Silero, Cobra, and the Flush TrickBuild15Streaming Speech-to-Speech — Moshi, Hibiki, and Full-Duplex DialogueLearn16Voice Anti-Spoofing & Audio Watermarking — ASVspoof 5, AudioSeal, WaveVerifyBuild17Audio Evaluation — WER, MOS, UTMOS, MMAU, FAD, and the Open LeaderboardsLearn