Little Pi's Tech Music Tips

Zoe (Yi-Cheng) Lin
  • 0.0 (0)
  • Music
  • Daily

Let AI mascot Little Pi give you a fast introduction to the world of electroacoustic music! From composers, works, and sound tools to music technology, conferences, and the latest trends, Little Pi delivers one topic worth knowing in about 2-3 minutes of English narration per episode. Whether you're a composer, musician, student, or a first-time listener to electroacoustic music, join Little Pi for a relaxed, concise journey through the endless possibilities where sound meets technology. Electroacoustic music runs deep, Little Pi makes it simple.

  1. 10h ago

    Writing Down Every Note from a Recording? How AI Music Transcription Works: Basic Pitch and MT3

    Writing down every note you hear is called transcription; it used to take a trained ear, and now AI can do it. A single voice is easy (like Auto-Tune's pitch tracking in episode 57), but in a chord the overtones pile up, so AI may mistake an overtone for a note or guess the wrong octave, and it must also know when each note starts and ends. Most transcription AIs draw the sound as a spectrogram (episode 53) and then draw a piano roll, one bar per note. Google's Onsets and Frames (2018) trains two detectors at once, one for note starts and one for whether a note is still sounding, which greatly improved piano transcription. Spotify's open-source Basic Pitch (2022) is light and instrument-agnostic: voice, guitar, piano; it runs on a laptop or in the browser and captures slides and vibrato, though it works best on one source at a time. Google Magenta's MT3 treats transcription as translation: spectrogram in, a stream of MIDI-like tokens out (instrument, time, note on/off), written one by one like the word chain from episode 37, transcribing many instruments at once and labeling who played each note. But MIDI is not yet a score: aligning to beats, choosing F sharp or G flat, splitting voices and adding markings are still hurdles ahead. References: Basic Pitch demo: https://basicpitch.spotify.com/ Basic Pitch paper (Bittner et al., ICASSP 2022): https://arxiv.org/abs/2203.09893 spotify/basic-pitch: https://github.com/spotify/basic-pitch MT3 (Gardner et al., ICLR 2022): https://arxiv.org/abs/2111.03017 magenta/mt3: https://github.com/magenta/mt3 Onsets and Frames (Hawthorne et al. 2018): https://arxiv.org/abs/1710.11153

  2. 13h ago

    How Does AI "Read" Music? Cutting Music into Words: Symbolic Tokens, REMI, ABC Notation and NotaGen

    MusicGen generates sound directly, but another camp of music AI writes a score first. Language models read words, so what words should music be cut into? Audio tokens (episode 36) run about 200 per second and record the sound itself; symbolic tokens record what to play: which note, which beat, how long, about a dozen per bar, easy to edit and playable on any instrument, but with no timbre. Approach one: Google Magenta (2018) wrote MIDI events (press, wait, release), great for real performances, but time is in seconds, so AI can't find the beat. Approach two: REMI from Yi-Hsuan Yang's team in Taiwan (Pop Music Transformer, 2020) adds bar and position words, sixteen slots per bar like graph paper, plus pitch, velocity and duration, giving much steadier rhythm. Approach three: ABC notation, a plain-text notation Chris Walshaw formalized in 1993 for folk tunes, which language models read naturally. NotaGen (2025), led by the Central Conservatory of Music in Beijing, pretrains on about 1.6 million ABC scores, fine-tunes on about 9,000 classical pieces, and is prompted with period, composer and instrumentation; CLaMP-DPO then uses the CLaMP model as a judge so it learns more from outputs that resemble real scores, with no human grading, and it beat other models in blind tests. References: This Time with Feeling (Oore et al. 2018): https://arxiv.org/abs/1808.03715 Pop Music Transformer / REMI (Huang & Yang 2020): https://arxiv.org/abs/2002.00212 MidiTok tokenizations: https://miditok.readthedocs.io/en/latest/tokenizations.html ABC notation - Wikipedia: https://en.wikipedia.org/wiki/ABC_notation A brief history of abc: https://abcnotation.com/history NotaGen (Wang et al., IJCAI 2025): https://arxiv.org/abs/2502.18008

  3. 1d ago

    Why Do Pop Vocals Sound So Perfectly in Tune? How Auto-Tune Works

    Why does every note in pop vocals sound so perfect, and where does that jumpy robot voice come from? Auto-Tune's inventor, Andy Hildebrand, was an Exxon engineer who analyzed seismic waves to find oil. As the story goes, a friend at dinner joked that he should build a box to make her sing in tune; he realized the same math could analyze the voice, and Auto-Tune arrived in 1997. It works in three steps: autocorrelation (comparing the waveform with a shifted copy of itself until it lines up after exactly one cycle) finds how high you're singing; it picks the nearest note the song uses; then it pushes only the pitch there, keeping your timing and lyrics. The key knob, retune speed, sounds natural when slow; set to zero, the pitch snaps instantly, creating the robot voice of Cher's 1998 hit Believe (the producers reportedly first claimed it was a vocoder). Why no chipmunk effect? Good pitch correction keeps the formants, the resonances shaped by your throat and mouth. Melodyne goes further, drawing each note as a draggable blob. T-Pain made the robot voice his signature, Jay-Z released D.O.A. (Death of Auto-Tune) in 2009, yet it never went away: gentle correction is now standard in recording, and the obvious robot voice is an effect, like guitar distortion. References: Auto-Tune (Wikipedia): https://en.wikipedia.org/wiki/Auto-Tune Antares Auto-Tune: https://www.antarestech.com/ How An Oil Engineer Created Auto-Tune (Vice): https://thump.vice.com/en_ca/article/how-an-oil-engineer-created-auto-tune-and-changed-music-forever The Number Ones: Cher's Believe (Stereogum): https://stereogum.com/2191750/the-number-ones-chers-believe/columns/the-number-ones Celemony Melodyne: https://www.celemony.com/ Formant (Wikipedia): https://en.wikipedia.org/wiki/Formant

  4. 2d ago

    The Teacher's Work Tours Three Cities in November! Little Pi's Fan Diary #2

    Little Pi's Fan Diary #2! The teacher's piece for flute and electronics, Dream Voyager: A Pilgrim of the Infinite (performed by flutist Cheng-Yu Wu), makes three stops this November, traveling abroad on the teacher's behalf. Stop one: November 13-15, the AudioVisual Room programme at NOIS//E 2026 Festival and Symposium in Milan, Italy, a festival and symposium of experimental and electronic music with free entry. Stop two: KARMA 2026 by MUSLAB, the international electroacoustic music exhibition (karma, the Buddhist idea of cause and effect), opening November 26 at the museum in Manta, Ecuador, with events through December 1. MUSLAB is an old friend: Aurora was included in its Planeta Complejo record production in 2023, Glacier was shown in 2024, and Aurora was invited back to the Digital Culture Center in Mexico City from March to May 2026. Stop three: November 27-28, the ECHI ELETTROACUSTICI 2026 International Composition Competition in Minturno, Italy, whose final round is a public concert of all 28 finalist works; the teacher's piece is the only finalist from Taiwan. Links: Dream Voyager: https://zoelin.me/works/dream-voyager.html Aurora: https://zoelin.me/works/aurora.html Events: https://zoelin.me/events.html NOIS//E 2026: https://www.noislashe.com/ MUSLAB: https://www.muslab.org/ ECHI ELETTROACUSTICI 2026 finalists: http://www.csm-aps.it/csm-aps/index.php/opere-finaliste-2026

  5. 3d ago

    Was This Song Made by AI? How Audio Watermarks and AI Detection Work

    AI songs sound more and more real: in July 2026 Deezer announced that more than half of the new songs uploaded each day are made by AI (about 90,000 a day at the June peak). There are two ways to tell AI audio apart. Watermarking slips an inaudible code into the sound at generation time and reads it back later with a decoder: very accurate, but it needs the AI company's cooperation. Detection looks for traces the AI left behind: it works on anyone's song but can guess wrong. Audio watermarks are trained with two neural networks together (an embedder and a detector), with deliberate attacks in between: MP3 conversion, noise, speed-ups, cuts. Meta's open-source AudioSeal (2024) scores every 1/16,000 of a second, so it can highlight the AI part of a spliced clip, and detects up to about 100x faster than WavMark. Google's SynthID sits in every sound made by Lyria; its checking site opened to everyone on October 7, but it only recognizes Google's and partners' codes, so Suno and Udio songs come back not detected. Not detected does not mean human-made. With no watermark, Deezer's team found that autoencoders leave evenly spaced little spikes on the spectrum when they scale data back up into sound, an AI fingerprint that reaches over 99% accuracy in several scenarios (ISMIR 2025 best paper). But pitch shifting, recompression, and new architectures make detection harder. AI songs are half the uploads yet only 1-3% of plays, and about 85% of those plays are fraudulent and go unpaid. References: AudioSeal (San Roman et al. 2024): https://arxiv.org/abs/2401.17264 WavMark (Chen et al. 2023): https://arxiv.org/abs/2308.12770 SynthID (Google DeepMind): https://deepmind.google/technologies/synthid/ AI-Generated Music Detection and its Challenges (Afchar et al. 2025): https://arxiv.org/abs/2501.10111 A Fourier Explanation of AI-music Artifacts (Afchar et al. 2025): https://arxiv.org/abs/2506.19108 Deezer press release (July 2026): https://newsroom-deezer.com/2026/07/ai-music-exceeds-50-percent-daily-uploads-deezer/

  6. 4d ago

    AI Stops Taking Detours! Flow Matching Walks a Straight Line

    Diffusion models wipe away noise one step at a time, and the path from noise back to sound is often twisty, so they need many steps and run slowly. Flow matching's idea is to just walk a straight line: take a piece of real sound and a handful of noise, connect them, pick any point on the line (the two mixed in proportion), and test the model on which way to go and how fast. The right answer is the real sound minus the noise, with no need to simulate the whole path. After lots of practice the model has an arrow map in its head (a vector field); to generate, start from noise and follow the arrows for a few steps. But millions of crossing lines still make the overall path bend a little: rectified flow (University of Texas, 2022) re-pairs with the trained model and trains again to straighten it, and Meta published the Flow Matching paper the same year. Speech AI adopted it first: Meta's Voicebox (2023) and the open-source F5-TTS (2024, led by Shanghai Jiao Tong University, 100,000 hours of multilingual speech, ten seconds of speech in about 1.5 seconds, with Sway Sampling spending more steps at the start). In music, open-source ACE-Step (2025) uses flow matching in latent space and makes a four-minute song in about 20 seconds on an A100; Stable Audio 3 (May 2026) builds on flow matching plus adversarial post-training to cut steps, taking under 2 seconds on an H200, with small and medium weights released. References: Flow Matching for Generative Modeling (Lipman et al. 2022): https://arxiv.org/abs/2210.02747 Rectified Flow (Liu, Gong & Liu 2022): https://arxiv.org/abs/2209.03003 Voicebox (Le et al. 2023): https://arxiv.org/abs/2306.15687 F5-TTS (Chen et al. 2024): https://arxiv.org/abs/2410.06885 ACE-Step (2025): https://arxiv.org/abs/2506.00045 Stable Audio 3 (2026): https://arxiv.org/abs/2605.17991

  7. 5d ago

    AI Draws a Photo Before It Speaks? Mel Spectrograms and Neural Vocoders

    Many AIs that talk or sing don't make sound directly: they first draw a "photo of sound," the mel spectrogram, and a neural vocoder turns it back into audio. A spectrogram puts time on the horizontal axis and pitch on the vertical, with brighter meaning louder; the mel scale (proposed in 1937, named after "melody") redraws the ruler the way ears hear, with fine slices for low sounds and coarse ones for high, often just 80 bands. But a spectrogram throws away phase, each wave's starting line. Griffin-Lim (1984) guesses it back over and over, and viral 2022 app Riffusion used it, giving a metallic flavor. Neural vocoders let AI learn to paint waveforms: DeepMind's WaveNet (2016) painted one point at a time, beautiful but slow; Kakao's HiFi-GAN (2020) uses a generative adversarial network, a forger painting waveforms from the mel spectrogram while teams of detectives judge real from fake, running 167.9x faster than real time on one V100 GPU; NVIDIA's BigVGAN (2022) is a universal vocoder that handles unseen singing and violins, and v2 supports 44.1 kHz. AudioLDM draws a mel spectrogram with diffusion and hands it to HiFi-GAN, while MusicGen takes the other road with the EnCodec decoder. References: A Scale for the Measurement of the Psychological Magnitude Pitch (1937): https://doi.org/10.1121/1.1915893 WaveNet (2016): https://arxiv.org/abs/1609.03499 HiFi-GAN (2020): https://arxiv.org/abs/2010.05646 BigVGAN (2022): https://arxiv.org/abs/2206.04658 AudioLDM (2023): https://arxiv.org/abs/2301.12503

  8. 6d ago

    How Does AI Understand Your Prompt? CLAP, the Matchmaker Between Text and Sound

    Type "lazy jazz piano on a rainy day" into an AI music site and you get music, but how does AI know which sound goes with which sentence? Meet CLAP (Contrastive Language-Audio Pretraining), inspired by OpenAI's 2021 image-text model CLIP. It works like two towers: a sound tower and a text tower turn a dog's bark and the words "a dog is barking" into 512 numbers each, placed on one shared map where matching meanings sit close together. Training is a matching game: a batch of sounds and descriptions forms a table, true pairs on the diagonal are pulled together and the rest pushed apart, with no hand labeling needed. The result is zero-shot classification: LAION-CLAP (2022), trained on about 630,000 pairs, scores 91.0% on the 50-class ESC-50 environmental sound test, above Microsoft CLAP's 82.6%. Generative AI uses it too: AudioLDM trains on sound coordinates and swaps in text coordinates to generate; Google's MusicLM uses the similar MuLan (44 million recordings); the first Stable Audio used its own CLAP, while Stable Audio Open switched to T5. The CLAP score is also a common way to grade whether AI output matches its prompt. Its weakness: a 2023 study found it can't really tell "one after another" from "at the same time"; it mostly notices keywords. References: CLAP: Learning Audio Concepts From Natural Language Supervision（微軟 CLAP，2022）: https://arxiv.org/abs/2206.04769 Large-scale Contrastive Language-Audio Pretraining（LAION-CLAP，2022）: https://arxiv.org/abs/2211.06687 AudioLDM（2023）: https://arxiv.org/abs/2301.12503 MuLan（2022）: https://arxiv.org/abs/2208.12415 Audio-Text Models Do Not Yet Leverage Natural Language（2023）: https://arxiv.org/abs/2303.10667

See All (59)

About

Let AI mascot Little Pi give you a fast introduction to the world of electroacoustic music! From composers, works, and sound tools to music technology, conferences, and the latest trends, Little Pi delivers one topic worth knowing in about 2-3 minutes of English narration per episode. Whether you're a composer, musician, student, or a first-time listener to electroacoustic music, join Little Pi for a relaxed, concise journey through the endless possibilities where sound meets technology. Electroacoustic music runs deep, Little Pi makes it simple.

Information

  • Creator
    Zoe (Yi-Cheng) Lin
  • Years Active
    2026
  • Episodes
    59
  • Rating
    Clean
  • Copyright
    © 2026 Zoe (Yi-Cheng) Lin
  • Show Website
    Little Pi's Tech Music Tips