Audio Engineering

Audio Engineering

Opus, jitter buffers, VAD, AEC, LUFS targets, WebRTC pipeline.

53Articles
53Topics covered
Articles in this category

All 53 articles, sorted alphabetically

Advertisement
ARTICLE · 01

Adaptive Jitter Buffer Design

Trade latency for smoothness without overshooting.

Read article
ARTICLE · 02

AAC

How AAC (Advanced Audio Coding) provides better quality than MP3 at same bitrate, becoming streaming standard.

Read article
ARTICLE · 03

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
ARTICLE · 04

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
ARTICLE · 05

ASR

How ASR systems convert speech to text, and the modern neural approaches replacing older HMM systems.

Read article
ARTICLE · 06

Automatic Speech Recognition Architecture in Depth

A 2500-word walkthrough of ASR architecture: audio input, feature extraction, encoder-decoder, streaming decoding, Whisper family, diarization, VAD, p…

Read article
ARTICLE · 07

Microphone beamforming architecture

Deep-dive on microphone beamforming: mic array, delay-and-sum, adaptive MVDR/GSC, DOA estimation, noise, echo, speech enhancement.

Read article
ARTICLE · 08

Audio Buffer Management for Low Latency

Underruns, drift correction, and why ring buffers beat queues for audio.

Read article
ARTICLE · 09

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
ARTICLE · 10

Audio Codecs

How audio codecs (MP3, AAC, Opus) compress audio using psychoacoustic models.

Read article
ARTICLE · 11

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
ARTICLE · 12

Speaker Diarization

How diarization identifies different speakers in an audio recording (meeting transcription, call analytics).

Read article
ARTICLE · 13

Speaker diarization architecture

Deep-dive on speaker diarization: VAD, segments, ECAPA/x-vector embed, spectral clustering, change point, overlap, labels, ASR fusion.

Read article
ARTICLE · 14

Speaker diarization v2 architecture

Deep-dive on speaker diarization v2: VAD, segmentation, speaker embeddings, clustering, speaker turn detection, streaming, overlap.

Read article
ARTICLE · 15

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
ARTICLE · 16

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
ARTICLE · 17

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
ARTICLE · 18

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
ARTICLE · 19

Audio Loudness Normalization

LUFS over peak, and why every platform requires it.

Read article
ARTICLE · 20

Loudness normalization architecture

Deep-dive on loudness normalization: why peak normalization fails perceptually, the ITU-R BS.1770 chain (K-weighting, 400ms block mean-square, absolut…

Read article
ARTICLE · 21

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
ARTICLE · 22

Music generation architecture

Deep-dive on music generation: audio tokenizer, acoustic transformer, vocoder, style conditioning, watermark, rights, streaming.

Read article
ARTICLE · 23

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
ARTICLE · 24

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
ARTICLE · 25

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
ARTICLE · 26

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
ARTICLE · 27

PCM Audio

How PCM represents analog audio as discrete samples, and how sample rate + bit depth determine quality.

Read article
ARTICLE · 28

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
ARTICLE · 29

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
ARTICLE · 30

Audio source separation architecture

Deep-dive on audio source separation: STFT, neural model (U-Net/TasNet), masks, iSTFT, streaming causal, targeting, metrics.

Read article
ARTICLE · 31

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
ARTICLE · 32

Audio Streaming

How audio streaming works: adaptive chunk-based (HLS/DASH) and continuous (Icecast, Shoutcast).

Read article
ARTICLE · 33

Streaming ASR architecture

Deep-dive on streaming speech recognition: VAD, streaming encoder, CTC/transducer, partials, endpointing, rescore, and observability.

Read article
ARTICLE · 34

Audio Streaming Protocols Compared

HLS, DASH, Icecast, WebRTC — pick by use case.

Read article
ARTICLE · 35

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
ARTICLE · 36

Text-to-Speech (TTS)

How modern TTS systems generate natural-sounding speech, from concatenative to neural TTS.

Read article
ARTICLE · 37

TTS architecture

Deep-dive on text-to-speech: text encoder, acoustic model, vocoder, streaming, voice cloning with consent + watermark, emotion, metrics.

Read article
ARTICLE · 38

Voice Activity Detection (VAD)

How VAD identifies when someone is speaking versus silence or background noise.

Read article
ARTICLE · 39

Voice Activity Detection architecture

Deep-dive on VAD: capture and framing, energy vs GMM vs neural (Silero) scoring, hysteresis thresholds, hangover and pre-roll smoothing, ASR gating, b…

Read article
ARTICLE · 40

Wake word detection architecture

Deep-dive on wake word detection: mic, VAD, KWS model, trigger, false accepts + rejects, user tuning, privacy, multi-language.

Read article
ARTICLE · 41

OpenAI Whisper

How Whisper does speech recognition across languages with strong noise robustness.

Read article
ARTICLE · 42

Echo Cancellation for Speakerphone

Adaptive filter design with NLMS and frequency-domain implementations.

Read article
ARTICLE · 43

Jitter Buffer Design

Smoothing arrival jitter without adding too much latency.

Read article
ARTICLE · 44

MP3 vs AAC vs Opus for Streaming

Codec choice for podcasts music and voice.

Read article
ARTICLE · 45

The Opus Codec for Real-Time Voice

Why Opus is the default codec for WebRTC and how to tune it for voice vs music.

Read article
ARTICLE · 46

Opus Codec Parameters That Matter

Bitrate, complexity, FEC — pick by use case.

Read article
ARTICLE · 47

Packet Loss Concealment Algorithms

Reconstructing missing audio packets for VoIP.

Read article
ARTICLE · 48

Real-Time Audio Pipelines in Rust

cpal crate ring buffers and avoiding allocations on the audio thread.

Read article
ARTICLE · 49

Sample Rate Conversion Techniques

Sinc-based vs FFT-based resampling tradeoffs.

Read article
ARTICLE · 50

Speech-to-Text Stack in 2026

Whisper, AssemblyAI, Deepgram — the current trade-offs.

Read article
ARTICLE · 51

Voice Activity Detection (VAD)

When to send silence, when to detect speech.

Read article
ARTICLE · 52

WebRTC Audio Pipeline End to End

What happens between the mic and the speaker.

Read article