Methods, apparatus, systems and articles of manufacture are disclosed to adjust audio playback settings. Example apparatus disclosed herein include an equalization (EQ) model query generator to generate a query to a neural network, the query including a representation of a sample of an audio signal; an EQ filter settings analyzer to: access a plurality of audio playback settings determined by the neural network based on the query; and determine a filter coefficient to apply to the audio signal based on the plurality of audio playback settings; an EQ personalization manager to; generate a personalized EQ setting; and an EQ adjustment implementor to: blend the personalized EQ setting and the filter coefficient to generate a blended equalization; and apply the blended equalization to the audio signal in a first duration.

A system and method for digital processing including a gain element to process an input audio signal, a high pass filter to then filter the signal and create a high pass signal, a first filter module to filter the high pass signal and create a first filtered signal and a splitter to split the high pass signal into two high pass signals. The first filter module filters one high pass signals before a first compressor modulates the signal or a high pass signal to create a modulated signal. A second filter module filters the modulated signal to create a second filtered signal that is processed by a first processing module including a band splitter that splits the signal into low and high band signals that are then modulated by compressors. A second processing module processes the modulated low and high band signals to create an output signal.

The invention provides a method and apparatus for filtering a temporal signal. A target magnitude frequency response H.sub.T(f) is specified (101,201) of frequency f in terms of a column vector l of K weights l.sub.k where log H.sub.T(f)=l.sup.TW(f) and W(f) is a column vector of K magnitude basis functions W.sub.k(f). A constrained frequency response H.sub.c(f) is computed (102,214) defined by log H.sub.c(f)=g.sup.TV(f) , where V(f) is a column vector of N constrained basis functions V.sub.n(f) for which each exp g.sub.nV.sub.n(f) satisfies a constraint preserved by concatenation, and g is a column vector of N coefficients satisfying a matching criterion between l.sup.TW(f) and g.sup.TV(f). An input temporal signal is received (103,212) and filtered (104,210) with the constrained frequency response H.sub.c(f) to form a filtered temporal signal; and the filtered temporal signal is output (105,211).

Environmental sound is recorded using one or more microphones. A source of the recorded environmental sound is classified. The recorded environmental sound is weighted based on the classification of the source and the source media sound using a weighting mode to determine whether to mix the recorded environmental. The recorded environmental sound is mixed with source media sound to produce a mixed sound based on the determination. The mixed sound is played over one or more speakers.

Various embodiments are disclosed for (possibly simultaneously) applying EQ and DRC to audio signals. In an embodiment, a method comprises: dividing an input audio signal into n frames, where n is a positive integer greater than one; dividing each frame of the input audio signal into Nb frequency bands, where Nb is a positive integer greater than one; for each frame n: computing an input level of the input audio signal in each band f, resulting in a input audio level distribution for the input audio signal; computing a gain for each band f based at least in part on a mapping of one or more properties of the input audio level distribution to a reference N audio level distribution computed from one or more reference audio signals; and applying each computed gain for each band f to each

Embodiments described herein provide for smart configuration of audio settings for a playback device. According to an embodiment, while a playback device is a part of a first zone group that includes the playback device and at least one first playback device, the playback device applies a first audio setting. The embodiment also includes the playback device joining a second zone group that includes the playback device and at least one second playback device. The embodiment further includes the playback device applying a second audio setting based on an audio content profile corresponding to the second zone group.

A variable-resolution graphic equalizer providing an improved interface for controlling gain values across the entire audio spectrum using many narrow-band filters (e.g., 120). It allows user selection of a frequency range for graphic equalization and automatically maps a reduced and fixed number of sliders to the selected range based on the number of filter bands falling within the selected range. In an audio processing system, specific user interface regions are highlighted to display selected frequency ranges and corresponding selected sliders to allow for rapid and precise equalization of the full audio spectrum using the many narrow-band filters.

The present invention provides for methods and systems for digitally processing an audio signal to reproduce high quality sounds on various materials. In various embodiments, a method comprises filtering the signal with a low shelf filter and/or high shelf filter, passing the signal through a first compressor that, filtering the signal again with a low shelf filter and/or high shelf filter, processing the signal with a graphic equalizer based on a selected material profile, passing the signal through a second compressor, and outputting the signal to a transducer.

The invention provides a method and apparatus for filtering a temporal signal. A target magnitude frequency response H.sub.T(f) is specified (101,201) of frequency f in terms of a column vector l of K weights l.sub.k where log H.sub.T(f)=l.sup.TW(f) and W(f) is a column vector of K magnitude basis functions W.sub.k(f). A constrained frequency response H.sub.c(f) is computed (102,214) defined by log H.sub.c(f)=g.sup.TV(f) , where V(f) is a column vector of N constrained basis functions V.sub.n(f) for which each exp g.sub.nV.sub.n(f) satisfies a constraint preserved by concatenation, and g is a column vector of N coefficients satisfying a matching criterion between l.sup.TW(f) and g.sup.TV(f). An input temporal signal is received (103,212) and filtered (104,210) with the constrained frequency response H.sub.c(f) to form a filtered temporal signal; and the filtered temporal signal is output (105,211).

There is provided a method of determining filter coefficients for an audio filter system including a number, N≥2, of filter paths for enabling processing of N audio channels, one filter path per channel, wherein each filter path includes at least one audio filter for performing the processing of the corresponding channel. The method includes providing a common set of filter design parameters for a pair of audio filters belonging to different filter paths, including phase difference information representing an inter-channel phase difference and frequency information representing a frequency value as filter design parameters; and determining filter coefficients for the pair of audio filters at least partly based on the common set of filter design parameters.