Symbol n_q

The passage around this formula

…shown to outperform prior codecs at comparable bitrates [ 7 ] . The mechanism gives a concrete, computable token rate. For a signal sampled at $f_s$ hertz, encoded with hop length h samples per frame, and quantized with $n_q$ residual stages of codebook size K each, the bitrate is $R = \frac{f_s}{h} \cdot n_q \cdot \log_2 K \text{ bits per second.}$. Every added quantizer stage buys reconstruction fidelity at a fixed, computable token-rate cost — the audio-codec analogue of the video tokenizer’s frame-versus-resolution trade, and just as unavoidable.

Read this part in the article →