Tag:Deep Learning
All the articles with the tag "Deep Learning".
Deep Learning Audio Note 5: Keyword Spotting and Always-On Listening
Understand lightweight keyword spotting models, Google and Apple cascade systems, streaming caches, robust training, and on-device optimization through the trade-off between false alarms and missed triggers.
Deep Learning Audio Note 4: Language, Knowledge, and Deployment in ASR
Connect the five dimensions of ASR through language model fusion, knowledge sources, and the constraints of offline, streaming, and on-device deployment.
Deep Learning Audio Note 3: Alignment in ASR
From DTW and HMMs to CTC, LAS, and RNN-T: how continuous speech maps to discrete text, and the tradeoffs between alignment constraints, output dependencies, and streaming deployment.
Deep Learning Audio Note 2: ASR and Speech Representations
Updated:From ASR applications, WER/CER, and real-world challenges to MFCCs, CNNs, Transformers, Conformers, and self-supervised speech representations.
Deep Learning Audio Note 1: Speech Tasks and Audio Representations
An introduction to speech tasks, sound, sampling rates, Fourier transforms, STFT, Mel spectrograms, and MFCCs.