speech

Definition

Spoken language as an audio signal, covering recognition, synthesis, speaker separation, and speech-to-speech translation. The characteristic difficulty is variability: the same words differ by speaker, accent, rate, and background noise, while the signal itself is continuous with no clean word boundaries. It is a subset of audio, distinguished by carrying linguistic content.

Explainers using this term

• Paper Walkthrough: Motion-Omni — Speaking and Moving in One Forward PassMotion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue
• Representing Sound — Mel Spectrograms and Audio TokensRobust Speech Recognition via Large-Scale Weak Supervision
• Paper Walkthrough: SwanTale — Designing Voices from Words Alone, with Speech and Sound in One WaveformSwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks