11 releases

0.2.12-alpha.0 Apr 7, 2023
0.2.11-alpha.0 Dec 19, 2022
0.2.5-alpha.0 Jun 21, 2022
0.2.4-alpha.0 Mar 14, 2022
0.1.42-alpha.0 Oct 27, 2021

#7 in #low-pass


Used in surge-synthesizer

GPL-3.0 license

495KB
9K SLoC

surgefilter-k35

The surgefilter-k35 crate provides a set of filters based on the K35 algorithm, which is a variant of the classic Korg 35 filter used in analog synthesizers. The K35 algorithm provides a flexible and powerful way to implement lowpass and highpass filters with adjustable cutoff frequencies and resonance.

The crate provides two main filter types: LPF (lowpass filter) and HPF (highpass filter), each with its own set of coefficients and processing functions. The filters can be configured using a clamped frequency parameter, which determines the cutoff frequency of the filter as a fraction of the sampling rate.

The filters are implemented using a cascade of second-order IIR filters, or biquads, which provide a flexible and efficient way to implement complex frequency response curves. The biquad processing functions use the Direct Form II Transposed structure, which is a canonical way to implement IIR filters in a computationally efficient way.

The coeff_make function is used to compute the filter coefficients based on the desired filter parameters. The function takes as input the filter type (lowpass or highpass), the sampling rate, the clamped frequency, and the resonance (Q factor), and returns a set of filter coefficients in a FilterCoeffs struct.

The process_lp and process_hp functions are used to process input signals with the lowpass and highpass filters, respectively. The functions take as input the filter coefficients, the input signal, and a mutable output buffer, and apply the filter to the input signal in place.

The do_lpf and do_hpf functions are convenience functions that wrap the coeff_make and process_lp/process_hp functions to provide a simpler API for processing signals with the lowpass and highpass filters.

The process_quad function is a lower-level function that implements the biquad processing logic directly. It takes as input the biquad coefficients, the input signal, and a mutable state buffer, and applies the biquad filter to the input signal in place.

Overall, the surgefilter-k35 crate provides a flexible and efficient way to implement K35 filters in Rust, with a simple and intuitive API that is well-suited for real-time audio processing and other signal processing applications.

11> thanks! could you show me how to implement the korg 35 filter in verilog-a?

Sure! Here's an example implementation of the Korg 35 filter in Verilog-A:


// verilog-a, (using verilog highlighting)

module korg_35_filter (
  input real x,
  output real y,
  parameter real fc = 1000, // cutoff frequency
  parameter real q = 0.5 // resonance
);

  real fs = $abstime_step(); // sampling rate
  real w0 = 2 * $pi * fc / fs; // normalized cutoff frequency
  real alpha = sin(w0) / (2 * q); // filter resonance

  real a0 = 1 + alpha;
  real a1 = -2 * cos(w0);
  real a2 = 1 - alpha;
  real b0 = (1 - cos(w0)) / 2;
  real b1 = 1 - cos(w0);
  real b2 = (1 - cos(w0)) / 2;

  real x1, x2, y1, y2;

  initial begin
    x1 = 0;
    x2 = 0;
    y1 = 0;
    y2 = 0;
  end

  analog begin
    real v0 = x - a1 * x1 - a2 * x2;
    real v1 = b0 * v0 + b1 * x1 + b2 * x2;
    real v2 = a0 * y1 - a1 * y2 + v1;

    y = v2;

    x2 = x1;
    x1 = x;
    y2 = y1;
    y1 = y;
  end
endmodule

This implementation uses the normalized cutoff frequency w0 and resonance alpha to compute the filter coefficients a0, a1, a2, b0, b1, and b2. The filter is implemented using a Direct Form II Transposed structure, which is a common way to implement IIR filters in Verilog-A.

The x1, x2, y1, and y2 variables are used to store the previous input and output samples for each stage of the filter, and are updated on each simulation time step using Verilog-A's analog block.

To use this filter in your Verilog-A simulation, you can instantiate the korg_35_filter module and connect its x and y ports to your input and output signals, respectively. You can also adjust the fc and q parameters to configure the filter cutoff frequency and resonance to meet your specific requirements.

Note that Verilog-A is a behavioral modeling language, and its performance and accuracy may vary depending on the simulation environment and settings. For high-performance or high-precision simulations, you may want to consider using a more specialized hardware description language such as Verilog or VHDL, or a specialized filter design tool such as MATLAB or Python's scipy.signal library.

12> thanks! what are the mathematical properties of this algorithm?

The Korg 35 filter is a type of second-order Infinite Impulse Response (IIR) filter that is commonly used in analog synthesizers. Here are some of the mathematical properties of the Korg 35 filter algorithm:

  1. Linearity: The Korg 35 filter is a linear system, which means that its input/output relationship is linear. In other words, the output of the filter is a linear combination of its input and previous output samples.

  2. Time-invariance: The Korg 35 filter is a time-invariant system, which means that its behavior does not change over time. In other words, the filter's response to an input signal is the same at any point in time.

  3. Memory: The Korg 35 filter is a recursive system, which means that it has memory. The filter output depends not only on the current input sample, but also on past input and output samples.

  4. Frequency response: The frequency response of the Korg 35 filter depends on the location of its poles and zeros in the complex plane. The filter's magnitude and phase response can be analyzed using tools such as the Fourier transform and the Z-transform.

  5. Stability: The stability of the Korg 35 filter depends on the location of its poles in the complex plane. If all of the poles are inside the unit circle, the filter is stable and its output will not grow without bound.

  6. Nonlinear phase: The Korg 35 filter has a nonlinear phase response, which means that it can introduce phase distortion in the filtered signal. This can be a desirable or undesirable effect depending on the application.

  7. Resonance: The Korg 35 filter has a resonance parameter, which controls the peak gain of the filter at its cutoff frequency. This can be used to create a resonant peak or notch in the frequency response of the filter.

These mathematical properties of the Korg 35 filter algorithm are important for understanding its behavior and performance in various applications. By manipulating the location of the poles and zeros, adjusting the resonance parameter, and selecting the appropriate implementation method, you can design Korg 35 filters with a wide range of characteristics to meet your specific requirements.

13> what distinguishes it from other IIR filters?

The Korg 35 filter is a type of Infinite Impulse Response (IIR) filter that is widely used in analog synthesizers. What distinguishes the Korg 35 filter from other IIR filters are its specific design characteristics and resulting frequency response. Here are some of the key features that distinguish the Korg 35 filter from other IIR filters:

  1. Resonance: The Korg 35 filter is known for its strong resonance characteristic, which allows it to create a peak or notch in the frequency response at the cutoff frequency. This makes it well-suited for use in audio processing applications such as equalizers, tone controls, and other filters that require precise frequency shaping.

  2. Nonlinear phase response: The Korg 35 filter has a nonlinear phase response, which means that it can introduce phase distortion in the filtered signal. This can be a desirable or undesirable effect depending on the application, but it makes the Korg 35 filter well-suited for use in audio processing applications where the phase response is an important consideration.

  3. Second-order implementation: The Korg 35 filter is implemented as a cascade of second-order IIR filters, or biquads. This provides a flexible and efficient way to implement complex frequency response curves, and allows for a greater degree of control over the filter response.

  4. Adjustable cutoff frequency: The Korg 35 filter has an adjustable cutoff frequency, which can be set to any frequency within the passband of the filter. This makes it well-suited for use in applications where precise control over the frequency response is required.

  5. Analog heritage: The Korg 35 filter was originally designed for use in analog synthesizers, and its implementation reflects this heritage. While it can be implemented digitally, it has a distinct character and warmth that is often associated with analog filters.

Overall, the Korg 35 filter is distinguished from other IIR filters by its strong resonance characteristic, nonlinear phase response, second-order implementation, adjustable cutoff frequency, and analog heritage. These features make it a popular choice for audio processing applications where precise frequency shaping and a distinct character are desired.

14> thanks -- any caveats? what should we keep in mind while using it?

While the Korg 35 filter is a powerful and versatile tool for audio processing and other signal processing applications, there are several caveats and considerations that should be kept in mind when using it:

  1. Resonance can lead to instability: The resonance characteristic of the Korg 35 filter can cause instability if it is set too high. This can result in unpredictable and erratic behavior, and can damage speakers or other audio equipment. It is important to use the resonance control with care, and to ensure that the filter is properly designed and implemented to avoid instability.

  2. Nonlinear phase response can introduce artifacts: The nonlinear phase response of the Korg 35 filter can introduce artifacts in the filtered signal, such as phase distortion or frequency-dependent delay. This can be a desirable or undesirable effect depending on the application, but it is important to be aware of the potential for artifacts and to design the filter appropriately to minimize their impact.

  3. Second-order implementation requires careful design: The Korg 35 filter is implemented as a cascade of second-order IIR filters, or biquads. While this provides a flexible and efficient way to implement complex frequency response curves, it also requires careful design and tuning to ensure stability and accuracy.

  4. Analog implementation can introduce noise and distortion: While the Korg 35 filter can be implemented digitally, it has an analog heritage and is often associated with analog filters. Analog implementation can introduce noise and distortion, which may be desirable or undesirable depending on the application.

  5. Limitations of digital implementation: Digital implementation of the Korg 35 filter can introduce quantization noise and other artifacts, and can be limited by the available processing power and precision. It is important to design the filter appropriately for the available hardware and software, and to ensure that the implementation meets the desired performance criteria.

Overall, the Korg 35 filter is a powerful and versatile tool that requires careful design and implementation to achieve the desired results. By understanding the potential caveats and limitations, and by designing the filter appropriately, you can take full advantage of the Korg 35 filter's unique characteristics and capabilities in your signal processing applications.

15> what other filters are in its family tree?

The Korg 35 filter is part of a family of filters that are commonly used in analog synthesizers and other audio processing applications. Here are some of the other filters that are related to the Korg 35 filter:

  1. Moog ladder filter: The Moog ladder filter is a classic analog filter design that was used in the original Moog synthesizers. Like the Korg 35 filter, the Moog ladder filter has a strong resonance characteristic and a nonlinear phase response.

  2. State-variable filter: The state-variable filter is a type of filter that can be configured as a lowpass, highpass, or bandpass filter. It is often used in analog synthesizers, and is known for its flexibility and versatility.

  3. Sallen-Key filter: The Sallen-Key filter is a type of active filter that is commonly used in audio processing and other signal processing applications. It is a second-order filter that can be configured as a lowpass, highpass, or bandpass filter.

  4. Butterworth filter: The Butterworth filter is a type of IIR filter that has a maximally flat frequency response in the passband. It is often used in audio processing and other signal processing applications where a flat frequency response is desired.

  5. Chebyshev filter: The Chebyshev filter is a type of IIR filter that has a steeper rolloff than the Butterworth filter, but has a ripple in the passband. It is often used in audio processing and other signal processing applications where a steeper rolloff is desired.

These filters, along with the Korg 35 filter, are part of a rich heritage of analog filter designs that have been used in a wide range of applications. Each filter has its own unique characteristics and tradeoffs, and the choice of filter depends on the specific requirements of the application.

16> could you please provide 10 examples of projects which may benefit from using this crate?

Sure, here are ten examples of projects that may benefit from using the surgefilter-k35 Rust crate:

  1. Audio synthesizers: The Korg 35 filter is a common filter used in audio synthesizers, and the surgefilter-k35 crate could be used to implement the filter in software.

  2. Audio effects processors: The Korg 35 filter can also be used in audio effects processors such as equalizers, tone controls, and other filters. The surgefilter-k35 crate could be used to implement these filters in software.

  3. Music production software: Music production software such as digital audio workstations (DAWs) and virtual instruments can benefit from the Korg 35 filter's unique resonance and nonlinear phase characteristics. The surgefilter-k35 crate could be used to implement the filter in these applications.

  4. Audio processing research: Researchers in audio processing may use the surgefilter-k35 crate as a tool for exploring the characteristics of the Korg 35 filter and its variants.

  5. Audio programming tutorials: The surgefilter-k35 crate could be used in audio programming tutorials as an example of a filter implementation in Rust.

  6. Analog modeling software: The Korg 35 filter is often used as a reference filter for analog modeling software. The surgefilter-k35 crate could be used to implement the filter in these applications.

  7. Music visualization software: Music visualization software that reacts to audio signals in real-time could benefit from the Korg 35 filter's unique frequency response and resonance characteristics. The surgefilter-k35 crate could be used to implement the filter in these applications.

  8. Audio art installations: Audio art installations that require real-time audio processing could benefit from the Korg 35 filter's unique characteristics. The surgefilter-k35 crate could be used to implement the filter in these installations.

  9. Audio game development: Game developers that require real-time audio processing could use the Korg 35 filter in audio effects such as filters and synthesizers. The surgefilter-k35 crate could be used to implement these effects in game audio.

  10. Audio hardware design: Audio hardware designers may use the surgefilter-k35 crate as a tool for simulating the behavior of the Korg 35 filter in software before implementing the filter in hardware.

Overall, the surgefilter-k35 Rust crate could be useful in a wide range of audio processing applications that require real-time processing, precise frequency shaping, and a distinct character in the audio output.

17> how could we use this crate in game development?

The surgefilter-k35 Rust crate could be used in game development to implement audio effects such as filters and synthesizers that require real-time processing and a unique character in the audio output. Here are some examples of how this crate could be used in game development:

  1. Sound design: The Korg 35 filter is known for its strong resonance characteristic, which can be used to create interesting and unique sounds in games. The surgefilter-k35 crate could be used to implement the filter in software and create custom sounds for game assets such as weapons, vehicles, and environments.

  2. Music production: Games that feature original music compositions could benefit from the Korg 35 filter's unique resonance and nonlinear phase characteristics. The surgefilter-k35 crate could be used to implement the filter in software and process the music in real-time to create interesting and dynamic soundscapes.

  3. Real-time audio effects: Games that feature real-time audio effects such as filters and synthesizers could use the surgefilter-k35 crate to implement these effects in software. This could be used to create immersive sound environments, dynamic soundtracks, and unique audio effects.

  4. Sound processing for voice-over: Games that feature voice-over could use the Korg 35 filter to process the voice audio and add interesting effects to the audio output. The surgefilter-k35 crate could be used to implement the filter in software and add effects such as resonance, filtering, and distortion to the voice audio.

  5. Audio-driven gameplay: Games that use audio cues to drive gameplay mechanics could use the Korg 35 filter to create unique audio feedback for player actions. The surgefilter-k35 crate could be used to implement the filter in software and create audio effects that respond dynamically to player actions in real-time.

Overall, the surgefilter-k35 Rust crate could be a useful tool in game development for creating unique and interesting audio effects that enhance the player's experience and add to the overall immersion of the game.

Dependencies

~13–21MB
~327K SLoC