Posts

All the articles I've posted.

• Deep Learning Audio Note 4: Language, Knowledge, and Deployment in ASR

  9 Oct, 2026

  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

  5 Oct, 2026

  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:4 Oct, 2026

  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

  2 Oct, 2026

  An introduction to speech tasks, sound, sampling rates, Fourier transforms, STFT, Mel spectrograms, and MFCCs.

• Omni Model Architectures: One Framework, Two Families

  8 Aug, 2026

  A visual comparison of omni model architectures across audio encoding, Thinker, Talker, vocoder, discrete codecs, continuous latents, and ASR.

• Encode Before You Admit

  23 Jul, 2026

  How Fun-ASR moved full-context audio encoding ahead of LM admission with batching, single-flight deduplication, and LRU caching.