All 21 articles, sorted alphabetically
Acoustic echo cancellation architecture
Deep-dive on AEC: loopback reference capture, delay estimation, partitioned-block frequency-domain NLMS, double-talk detection, residual echo suppress…
Read article →Automatic gain control architecture
Deep-dive on automatic gain control (AGC) for voice: level estimation, the gain-computer control loop, fast-attack/slow-release dynamics, the noise ga…
Read article →Clock-drift compensation architecture
Deep-dive on clock-drift compensation in real-time audio: why independent sample clocks inevitably diverge, inferring the parts-per-million drift from…
Read article →Audio dereverberation architecture
Deep-dive on speech dereverberation: why reverberation is convolution not additive noise, STFT analysis, late-reflection estimation with weighted pred…
Read article →DTX and comfort noise architecture
Deep-dive on discontinuous transmission and comfort noise generation in voice codecs: a VAD forking speech from silence, DTX stopping full-frame trans…
Read article →Audio forward error correction
Deep-dive on FEC and redundancy for real-time audio: why retransmission fails against the conversational deadline, in-band Opus FEC and RED-style redu…
Read article →Acoustic howling suppression architecture
Deep-dive on howling/feedback suppression: loop-gain stability and maximum/added stable gain, feedback detection and notch filtering, frequency shifti…
Read article →Adaptive jitter buffer architecture
Deep-dive on adaptive jitter buffers: RTP reordering, percentile-based delay estimation, accelerate/expand time-stretching, packet-loss concealment, c…
Read article →Audio Loudness Normalization
LUFS over peak, and why every platform requires it.
Read article →Multi-party audio mixing architecture
Deep-dive on server-side multi-party audio mixing (the MCU): per-stream jitter buffering and decoding, resampling to a common clock to correct device …
Read article →Neural audio codecs -- learned compression and audio tokens
Deep-dive on neural audio codecs: learned compression, the encoder-quantizer-decoder architecture, residual vector quantization (RVQ), the bitrate-vs-…
Read article →Real-time noise suppression architecture
Deep-dive on streaming noise suppression: framing and STFT features, causal GRU/TCN mask estimators (RNNoise, DTLN, DeepFilterNet), post-filter smooth…
Read article →Opus codec architecture
Deep-dive on the Opus audio codec: SILK speech and CELT music engines, hybrid mode and content-adaptive switching, flexible frame sizes, FEC and PLC p…
Read article →Packet loss concealment
Deep-dive on packet loss concealment (PLC) for real-time voice: manufacturing replacement frames for lost packets by extrapolating from recent history…
Read article →Real-Time Audio Architecture in Depth
A 2500-word walkthrough of real-time audio: capture, AEC, noise, VAD, Opus codec, packetize + FEC, transport, jitter buffer, decoder, ASR, barge-in.
Read article →Sample-rate conversion architecture
Deep-dive on audio sample-rate conversion (resampling): how to move audio between rates like 48 kHz, 44.1 kHz, and 16 kHz without aliasing or imaging.…
Read article →Spatial audio -- placing sound in 3D space
Deep-dive on spatial audio: the brain's localization cues (ITD, ILD, spectral), the HRTF, binaural rendering, object-based au…
Read article →Streaming ASR architecture
Deep-dive on streaming speech recognition: VAD, streaming encoder, CTC/transducer, partials, endpointing, rescore, and observability.
Read article →Audio Streaming Protocols Compared
HLS, DASH, Icecast, WebRTC — pick by use case.
Read article →Audio super-resolution -- reconstructing the missing high frequencies
Deep-dive on audio super-resolution (bandwidth extension): the narrowband problem, adding missing high frequencies, learned reconstruction (not upsamp…
Read article →Voice Activity Detection (VAD)
How VAD identifies when someone is speaking versus silence or background noise.
Read article →