Embodiments are disclosed for automatic leveling of speech content. In an embodiment, a method comprises: receiving, using one or more processors, frames of an audio recording including speech and non-speech content; for each frame: determining, using the one or more processors, a speech probability; analyzing, using the one or more processors, a perceptual loudness of the frame; obtaining, using the one or more processors, a target loudness range for the frame; computing, using the one or more processors, gains to apply to the frame based on the target loudness range and the perceptual loudness analysis, where the gains include dynamic gains that change frame-by-frame and that are scaled based on the speech probability; and applying the gains to the frame so that a resulting loudness range of the speech content in the audio recording fits within the target loudness range.

Embodiments are disclosed for determining an answer to a query associated with a graphical representation of data. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including an unprocessed audio sequence and a request to perform an audio signal processing effect on the unprocessed audio sequence. The one or more embodiments further include analyzing, by a deep encoder, the unprocessed audio sequence to determine parameters for processing the unprocessed audio sequence. The one or more embodiments further include sending the unprocessed audio sequence and the parameters to one or more audio signal processing effects plugins to perform the requested audio signal processing effect using the parameters and outputting a processed audio sequence after processing of the unprocessed audio sequence using the parameters of the one or more audio signal processing effects plugins.

Embodiments are disclosed for determining an answer to a query associated with a graphical representation of data. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including an unprocessed audio sequence and a request to perform an audio signal processing effect on the unprocessed audio sequence. The one or more embodiments further include analyzing, by a deep encoder, the unprocessed audio sequence to determine parameters for processing the unprocessed audio sequence. The one or more embodiments further include sending the unprocessed audio sequence and the parameters to one or more audio signal processing effects plugins to perform the requested audio signal processing effect using the parameters and outputting a processed audio sequence after processing of the unprocessed audio sequence using the parameters of the one or more audio signal processing effects plugins.

Some embodiments of the invention are directed to enabling a user to easily identify the frequency range(s) at which sound masking occurs, and addressing the masking, if desired. In this respect, the extent to which a first stem is masked by one or more second stems in a frequency range may depend not only on the absolute value of the energy of the second stem(s) in the frequency range, but also on the relative energy of the first stem with respect to the second stem(s) in the frequency range. Accordingly, some embodiments are directed to modeling sound masking as a function of the energy of the stem being masked and of the relative energy of the masked stem with respect to the masking stem(s) in the frequency range, such as by modeling sound masking as loudness loss, a value indicative of the reduction in loudness of a stem of interest caused by the presence of one or more other stems in a frequency range.

Some embodiments of the invention are directed to enabling a user to easily identify the frequency range(s) at which sound masking occurs, and addressing the masking, if desired. In this respect, the extent to which a first stem is masked by one or more second stems in a frequency range may depend not only on the absolute value of the energy of the second stem(s) in the frequency range, but also on the relative energy of the first stem with respect to the second stem(s) in the frequency range. Accordingly, some embodiments are directed to modeling sound masking as a function of the energy of the stem being masked and of the relative energy of the masked stem with respect to the masking stem(s) in the frequency range, such as by modeling sound masking as loudness loss, a value indicative of the reduction in loudness of a stem of interest caused by the presence of one or more other stems in a frequency range.

Method includes receiving, through a plurality of channels, audio data corresponding to a plurality of frequency ranges; determining, for each channel's frequency ranges, speech audio and/or noise energy level using a model trained by machine learning; determining a speech signal with removed noise for each channel; determining one or more statistical values associated with an energy level of a channel's speech signal with the removed noise; determining a strongest channel that has highest statistical values associated with an energy level of a speech signal; determining that the one or more statistical values associated with the energy level of the strongest channel's speech signal satisfy a threshold condition; comparing statistical values associated with an energy level of a speech signal of each channel with those of the strongest channel; and determining whether to update a gain value for a channel based on the channel's statistical values associated with the energy level.

A method for processing an audio signal includes setting target loudness; receiving metadata of an audio signal from a server; and adjusting the loudness of the audio signal by using the received metadata, so that the loudness of the audio signal corresponds to the set target loudness.

A method for processing an audio signal includes setting target loudness; receiving metadata of an audio signal from a server; and adjusting the loudness of the audio signal by using the received metadata, so that the loudness of the audio signal corresponds to the set target loudness.

Example techniques relate to voice interaction in an environment with a media playback system that is playing back audio content. In an example implementation, while playing back first audio in a given environment at a given loudness: a playback device (a) detects that an event is anticipated in the given environment, the event involving playback of second audio and (b) determines a loudness of background noise in the given environment, the background noise comprising ambient noise in the given environment. The playback device ducks the first audio in proportion to a difference between the given loudness of the first audio and the determined loudness of the background noise and plays back the ducked first audio concurrently with the second audio.

Example techniques relate to voice interaction in an environment with a media playback system that is playing back audio content. In an example implementation, while playing back first audio in a given environment at a given loudness: a playback device (a) detects that an event is anticipated in the given environment, the event involving playback of second audio and (b) determines a loudness of background noise in the given environment, the background noise comprising ambient noise in the given environment. The playback device ducks the first audio in proportion to a difference between the given loudness of the first audio and the determined loudness of the background noise and plays back the ducked first audio concurrently with the second audio.