Abstract: A system and method relate to a processing device implementing a master artificial intelligence (AI) engine to receive, from each of one or more real-time AI engines, a machine learning algorithm, parameters associated with the machine learning algorithm, and features employed to train the parameters, receive labeled data used to train the parameters associated with the machine learning algorithm, and construct, based on a combination rule, a master machine learning model using the features, the machine learning algorithm, and the parameters associated with the machine learning algorithm received from each of the one or more real-time AI engines.

Abstract: A generation apparatus 100 includes: an argumentative scheme adding unit 10 which adds an argumentative scheme with respect to pair data constituted by an input utterance and a counter utterance 121 that voices a negative opinion with respect to the input utterance and which generates argumentative scheme-added pair data 122; a generation model learning unit 20 which learns a generation model for generating a counter utterance from an input utterance in consideration of the argumentative scheme by using the argumentative scheme-added pair data 122 as learning data and which generates a learned counter utterance generation model 123; and a counter utterance generating unit 30 which acquires an input utterance of a user and a designated argumentative scheme and which outputs a counter utterance using the counter utterance generation model 123.

Abstract: A Peripheral Component Interconnect Express (PCIe)-based data transmission method includes that a first node obtains a transaction layer packet (TLP), where the TLP includes data, a type field, and at least one reserved bit, the type field and the at least one reserved bit indicate a first parameter set, and the first parameter set includes a data type of the data, and the first node sends the TLP to a second node.

Abstract: This application discloses a peripheral component interconnect express (PCIe)-based data transmission method and apparatus. The method includes: A first node encapsulates data into a transaction layer packet (TLP) and then sends the TLP to a second node. The TLP includes a packet header and an extension header. The packet header includes a first field and a second field. The first field, the second field, and the extension header are used to indicate first encapsulation information. The first encapsulation information includes a data type of the data and at least one encapsulation parameter corresponding to the data type. In some embodiments, the first field, the second field, and the extension header are used to indicate the information required for transmitting the data.

Abstract: Operations include obtaining a binary source data set and determining a decimal value that represents the source data set. In addition, the operations include determining a Kinetic Data Primer (KDP) that represents the decimal value. The KDP may include a mathematical expression that represents the decimal value. Further, the operations may include storing the KDP as a compressed version of the source data set.

Abstract: In an embodiment, a computing system can include one or more processors and one or more non-transitory computer-readable media that store instructions that, when executed by the one or more processors, cause the computing system to perform operations. The operations can include: receiving an internal encoder state of an encoder running on a first computing device being used to participate in a video conference currently in progress; receiving data indicative of a second computing device being used to join the video conference; compressing, based at least in part on receipt of the data, the internal encoder state to generate a compressed internal encoder state of the encoder; and/or transmitting the compressed internal encoder state to the second computing device to synchronize the internal encoder state of the encoder running on the first computing device with an internal decoder state of a decoder running on the second computing device.

Abstract: Examples of the disclosure relate to an apparatus comprising means for: using a radiofrequency beam having a wavelength below approximately 10 mm to interrogate one or more acoustic reporters in an audio environment; analysing one or more sound signals reported by the one or more acoustic reporters to determine positions of one or more sound sources providing the one or more sound signals; and using the positions of the one or more sound sources to determine one or more sound propagation paths within the audio environment.

Abstract: A real-time name mispronunciation detection feature can enable a user to receive instant feedback anytime they have mispronounced another person's name in an online meeting. The feature can receive audio input of a speaker and obtain a transcript of the audio input; identify a name from text of the transcript based on names of meeting participants; and extract a portion of the audio input corresponding to the name identified from the text of the transcript. The feature can obtain a reference pronunciation for the name using a user identifier associated with the name; and can obtain a pronunciation score for the name based on a comparison between the reference pronunciation for the name and the portion of the audio input corresponding to the name. The feature can then determine whether the pronunciation score is below a threshold; and in response, notify the speaker of a pronunciation error.

Abstract: Processor(s) of a client device can: receive sensor data that captures environmental attributes of an environment of the client device; process the sensor data using a machine learning model to generate a predicted output that dictates whether one or more currently dormant automated assistant functions are activated; making a decision as to whether to trigger the one or more currently dormant automated assistant functions; subsequent to making the decision, determining that the decision was incorrect; and in response to determining that the determination was incorrect, generating a gradient based on comparing the predicted output to ground truth output. In some implementations, the generated gradient is used, by processor(s) of the client device, to update weights of the on-device speech recognition model. In some implementations, the generated gradient is additionally or alternatively transmitted to a remote system for use in remote updating of global weights of a global speech recognition model.

Abstract: A method for managing a memory buffer, a memory control circuit unit, and a memory storage apparatus are provided. The method includes the following steps. Multiple consecutive first commands are received from a host system. A command ratio of read command among the first commands is calculated. The memory storage apparatus is being configured in a first mode or a second mode according to the command ratio and a ratio threshold. A first buffer is configured in a buffer memory to temporarily store a logical-to-physical address mapping table in response to the memory storage device being configured in the first mode, in which the first buffer has a first capacity. A second buffer is configured in the buffer memory in response to the memory storage device being configured in the second mode, in which the second buffer has a second capacity, which is greater than the first capacity.

Abstract: Various embodiments of a system and associated method for detecting and localizing gunshots are disclosed herein.

Abstract: A conversation design is received for a conversation bot that enables the conversation bot to provide a service using a conversation flow specified at least in part by the conversation design. The conversation design specifies in a first human language at least a portion of a message content to be provided by the conversation bot. It is identified that an end-user of the conversation bot prefers to converse in a second human language different from the first human language. In response to a determination that the message content is to be provided by the conversation bot to the end-user, the message content of the conversation design is dynamically translated for the end-user from the first human language to the second human language. The translated message content is provided to the end-user in a message from the conversation bot.

Abstract: Techniques for performing audio-based device location determinations are described. A system may send, to a first device, a command to output audio requesting a location of the first device be determined. A second device may receive the audio and send, to the system, data representing the second device received the audio, where the received data includes spectral energy data representing a spectral energy of the audio as received by the second device. The system may, using the spectral energy data, determine attenuation data representing an attenuation experienced by the audio as it traveled from the first device to the second device. The system may generate, based on the attenuation data, spatial relationship data representing a spatial relationship between the first device and the second device, where the spatial relationship data is usable to determine a device for outputting a response to a subsequently received user input.

Abstract: The present disclosure describes techniques for presenting information associated with content creators. The techniques comprise receiving information about a first subset of users selected based on information about a first users, displaying information about a second user among the first subset of users in a first area of a user interface, displaying information about a plurality of users among a second subset of users in a second area of the user interface while displaying the information about the second user in the first area, determining that the first user has a desire to review information about a third user among the first subset of users based on user input, displaying information about the third user in the first area, and displaying information about a plurality of users among a third subset of users in the second area while displaying the information about the third user in the first area.

Abstract: A parametric stereo upmix method for generating a left signal and a right signal from a mono downmix signal based on spatial parameters includes predicting a difference signal comprising a difference between the left signal and the right signal based on the mono downmix signal scaled with a prediction coefficient. The prediction coefficient is derived from the spatial parameters. The method further includes deriving the left signal and the right signal based on a sum and a difference of the mono downmix signal and said difference signal.

Abstract: A device capable of autonomous motion may move in an environment and may receive audio data from a microphone. A model may be trained to process the audio data to suppress noise from the audio data. The model may include an encoder that includes one or more convolutional layers, one or more recurrent layers, and a decoder that includes one or more convolutional layers.

Abstract: Various embodiments comprise apparatuses and methods including a communications subsystem having an interface module and a protocol module with the communications subsystem being configured to be coupled to an antenna. An applications subsystem includes a software applications module and an abstraction module. The software applications module is to execute an operating system and user applications; the abstraction module is to provide an interface with the software applications module. A controller interface module is coupled to the abstraction module and the interface module and is to convert signals from the applications subsystem into signals that are executable by the communications subsystem. Additional apparatuses and methods are described.

Abstract: Systems and methods are provided for providing content to a user device. Content is provided to a user via an e-book transmission channel via a network for display on a first application, wherein pre-defined metadata associated with the content identifies a content event trigger at a point in the content, wherein the content event trigger is associated with a user accessing a pre-specified point of the e-book. When the content event trigger is reached, a trigger signal is received via the network and transmitting supplemental content that was not previously accessible on the device over the network from a server to the device for access on a second mobile device application that is different from the first mobile device application.

Abstract: An audio signal processing method receives, by a terminal, a backtalk input instruction from a performer, obtains, by a microphone connected to the terminal, voice information from the performer, and outputs, in a case where the backtalk input instruction has been received by the terminal, a backtalk signal corresponding to the voice information obtained by the microphone connected to the terminal to a monitor bus of a mixer.

Abstract: A system for controlling automation includes a machine which collects data generated by performance of an operation by the machine. A user device displays a machine control interface (MCI) corresponding to the machine. The MCI displays the collected data to a touch interface of the user device, and defines at least one touch activated user interface element (UIE) for manipulating the data. The user device can be enabled as an automation human machine interface (HMI) device for controlling an operation performed by the machine, such that a touch action applied to a UIE of the MCI controls the operation. A prerequisite condition to enabling the user device as an automation HMI device can include activation of an enabling switch selectively connected to the user device. The MCI can be stored in a memory of the enabling switch and retrieved from the enabling switch by the user device.

Abstract: A computer device (100), configured to encode identifiers by providing audio identifiers therefrom, is described. The computer device (100) is configured to provide a set of audio signals as respective bitstreams. Each audio signal of the set of audio signals is defined based, at least in part, on audio signal information including at least one of a type, a fundamental frequency, a time signature and a time. Each audio signal comprises a set of audio segments. Each audio segment of the set of audio segments is defined based, at least in part, on audio segment information including at least one of a frequency, an amplitude, a transform, a time duration and an envelope. The computer device (100) is configured to receive an identifier and select a subset of audio signals from the set of audio signals according to the received identifier based, at least in part, on the audio signal information and/or the audio segment information.

Abstract: A communications system between a source and a destination includes a transmitter at the source and a communication connectivity. The transmitter comprises a preprocessor and a candidate envelope folder to provide M known a priori digital envelopes, M?1. The preprocessor has N input ports and N output ports, N>M, performs at least one wavefront multiplexing (WFM) transform on N inputs received at the N input ports to generate N outputs at the N output ports. The preprocessor performs the at least one WFM transform by calculating, for each of the N outputs, a linear combination of the N inputs using one of the M digital envelopes such that a digital format of one of the N outputs appears to human sensors as having features substantially identical to a digital format of the one of the M digital envelopes.

Abstract: System and methods are provided for detecting impairment of an individual. The method involves operating a processor to: receive at least one image associated with the individual; and identify at least one feature in each image. The method further involves operating the processor to, for each feature: generate an intensity representation for that feature; apply at least one impairment analytical model to the intensity representation to determine a respective impairment likelihood; and determine a confidence level for each impairment likelihood based on characteristics associated with at least the applied impairment analytical model and that feature. The method further involves operating the processor to: define the impairment of the individual based on at least one impairment likelihood and the respective confidence level.

Abstract: A User Equipment (UE) is operative to generate CN (Comfort Noise) control parameters, e.g., as part of audio-decoding processing by the UE. A buffer of a predetermined size implemented in the UE is configured to store CN parameters for SID (Silence Insertion Descriptor) frames and active hangover frames. Processing circuitry of the UE is configured to determine a CN parameter subset relevant for SID frames based on the age of the stored CN parameters and on residual energies, and use the determined CN parameter subset to determine CN control parameters for a first SID frame following an active signal frame.

Abstract: An apparatus includes an interface for microphones, a separated source processor configured to analyze channels from the microphones, and a voice activity detector (VAD) circuit. The VAD circuit is configured to generate a voice estimate (VE) value. The VE value is to indicate a likelihood of human speech received by the microphones. Generating the VE value includes adjusting the VE value based upon a delay between two of the microphones. The VAD circuit is configured to provide the VE value to the separated source processor.

Abstract: The present disclosure provides a communication method, apparatus, and system for a digital enhanced cordless telecommunications (DECT) base station. The method includes: determining, based on a communication connection request sent by a handset, whether a base station satisfies a wideband (WB) voice communication requirement of the handset, and returning communication acknowledgment information; and enabling the base station to perform WB voice communication with the handset if the communication acknowledgment information is a positive acknowledgment, or enabling the base station to perform narrowband (NB) voice communication with the handset if the communication acknowledgment information is a negative acknowledgment. The present disclosure can implement WB voice communication between a DECT base station and more than six handsets.

Abstract: Artificial intelligence is introduced into document review to identify content suggestions from input to generate suggested annotations for the reviewed document. An approach is provided for receiving an electronic document that contains original content from an original electronic document for review and electronic mark-ups provided by a first user. One or more electronic mark-ups that represent content suggestions proposed by the first user are identified from the electronic document. For each electronic mark-up of the one or more electronic mark-ups identified a document portion of the original content that corresponds to the electronic mark-up is identified, and an annotation is generated for the electronic mark-up comprising the electronic mark-up and a first user ID for the first user and associating the annotation to the document portion identified.

Abstract: The application relates to HFR (High Frequency Reconstruction/Regeneration) of audio signals. In particular, the application relates to a method and system for performing HFR of audio signals having large variations in energy level across the low frequency range which is used to reconstruct the high frequencies of the audio signal. A system configured to generate a plurality of high frequency subband signals covering a high frequency interval from a plurality of low frequency subband signals is described.

Abstract: A voice control method can be applied to a first terminal, and include: receiving a user's voice operation instruction after the first terminal is activated, the voice operation instruction being used for controlling the first terminal to perform a target operation; sending an instruction execution request to a server after the voice operation instruction is received, the instruction execution request being used for requesting the server to determine whether the first terminal is to respond to the voice operation instruction according to device information of the terminal in a device network, wherein the first terminal is located in the device network; and performing the target operation in a case where a response message is received from the server, the response message indicating that the first terminal is to respond to the voice operation instruction.

Abstract: An audio processing system may split frequency-domain processing between multiple DSP cores. Processing multi-channel audio data—e.g., from devices with multiple speakers—may require more computing power than available on a single DSP core. Such processing typically occurs in the frequency domain; DSP cores, however, typically communicate via ports configured for transferring data in the time-domain. Converting frequency-domain data into the time domain for transfer requires additional resources and introduces lag. Furthermore, transferring frequency-domain data may result in scheduling issues due to a mismatch between buffer size, bit rate, and the size of the frequency-domain data chunks transferred. However, the buffer size and bit rate may be artificially configured to transfer a chunk of frequency-domain data corresponding to a delay in the communication mechanism used by the DSP cores. In this manner, frequency-domain data can be transferred with a proper periodicity.

Abstract: An apparatus including an interface and a processor. The interface may be configured to receive video frames corresponding to an interior of a vehicle. The processor may be configured to perform video operations on the video frames to detect objects in the video frames, detect one or more passengers based on the objects detected in the video frames, determine a location of each of the passengers detected and generate a climate control signal for each of said passengers. The climate control signal may be implemented to control climate settings in a plurality of climate zones within the vehicle. The processor may correlate the location of each of the passengers to the climate zones.

Abstract: The disclosure describes one or more embodiments of an acoustic improvement system that accurately and efficiently determines and provides actionable acoustic improvement suggestions to users for digital audio recordings via an interactive graphical user interface. For example, the acoustic improvement system can assist users in creating high-quality digital audio recordings by providing a combination of acoustic quality metrics and actionable acoustic improvement suggestions within the interactive graphical user interface customized to each digital audio recording. In this manner, all users can easily and intuitively utilize the acoustic improvement system to improve the quality of digital audio recordings.

Abstract: A system and method configured to generate a simulated caller dialog including a caller intended issue for a scenario for testing a customer service representative (CSR). A simulated caller dialog is presented to the CSR and a CSR response to the simulated caller dialog is received and includes a CSR interpretation of the caller intended issue to the simulated caller dialog. An understanding determination result based on an intent determination recognition score is generated by an intent determination recognition model is generated in response to a comparison of the CSR interpretation of the caller intended issue matching the caller intended issue in the simulated caller dialog. A CSR score is generated for the scenario based on the understanding determination result. The CSR score is recorded to a database.

Abstract: A computer-implemented method for management of voicemail messages, performed at a portable electronic device with a touch screen display, includes: displaying a list of voicemail messages; detecting selection by a user of a respective voicemail message in the list; responding to the user selection of the respective voicemail message by initiating playback of the user-selected voicemail message; displaying a progress bar for the user-selected voicemail message, wherein the progress bar indicates the portion of the user-selected voicemail message that has been played; detecting movement of a finger of the user from a first position on the progress bar to a second position on the progress bar; and responding to the detection of the finger movement by restarting playback of the user-selected voicemail message at a position within the user-selected voicemail message corresponding substantially to the second position on the progress bar.

Abstract: Method for providing assistance in conversation including recognizing, by recognition module, conversation between primary user and at least one secondary user, identifying, by recognition module, first and second context data for primary user and at least one secondary user based on conversation; generating, by response generation module, at least one response on behalf of primary user based on at least one of second context data derived from at least one secondary user, and first context data; analyzing, by determining module, at least one action of primary user in at least one response on second context data; determining, by determining module, intervening situation in conversation based on at least one action; selecting, by intervening response module, intervening response from at least one response for determined intervening situation based on at least one action; and delivering, by response delivery module, intervening response to at least one secondary user during determined intervening situation.

Abstract: For Type-II codebook compression, methods, apparatus, and systems are disclosed. One apparatus includes a transceiver that receives a reference signal and a processor that identifies a set of taps over a layer based on the reference signal, where the set of taps are selected from a set of Nsb indices, the value Nsb representing a number of sub-bands. The processor generates a combinatorial codeword representing the set of taps. The processor reports the combinatorial codeword for the set of taps as part of a CSI feedback report.

Abstract: An exemplary lighting system utilizes intelligent system elements, such as lighting devices, user interfaces for lighting control or the like and possibly sensors, and utilizes network communication amongst such intelligent system elements. Some processing functions performed within the system are implemented on a distributed processing basis, by two or more of the intelligent elements of the lighting system. Distributed processing, for example, may enable use of available processor and/or memory resources of a number of intelligent system elements to process a particular job. Another distributed processing approach might entail programming to configure two or more of the intelligent system elements to implement multiple instances of a server functionality with respect to client functionalities implemented on intelligent system elements.

Abstract: A method for voice translation includes: receiving a voice signal of a first language; obtaining a plurality of voice segments forming the voice signal; determining integrity of a first voice segment with respect to a second voice segment based on a voice feature of the first voice segment and a voice feature of the second voice segment; obtaining an output voice segment based on the integrity of the first voice segment with respect to the second voice segment; and outputting a text in a second language corresponding to the voice signal of the first language based on the output voice segment.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for speech recognition. The method includes: determining, based on an acoustic score of a speech frame in a speech signal, a non-silence frame in the speech signal; determining a buffer frame between adjacent non-silence frames based on the acoustic score of the speech frame, a modeling unit corresponding to the buffer frame characterizing a beginning or end of a sentence; and decoding a speech frame after removing the buffer frame from the speech signal, to obtain a speech recognition result.

Abstract: A system for controlling automation includes a machine which collects data generated by performance of an operation by the machine. A user device displays a machine control interface (MCI) corresponding to the machine. The MCI displays the collected data to a touch interface of the user device, and defines at least one touch activated user interface element (UIE) for manipulating the data. The user device can be enabled as an automation human machine interface (HMI) device for controlling an operation performed by the machine, such that a touch action applied to a UIE of the MCI controls the operation. A prerequisite condition to enabling the user device as an automation HMI device can include activation of an enabling switch selectively connected to the user device. The MCI can be stored in a memory of the enabling switch and retrieved from the enabling switch by the user device.

Abstract: Achieving voice utterance that can attract an interest of a target further effectively. There is provided an information processing apparatus that includes an utterance control unit that controls output of voice utterance. The utterance control unit determines a target on the basis of an analyzed context, and controls an output device to output an attracting utterance that attracts an interest of the target. Furthermore, there is provided an information processing method that includes executing, by a processor, output control of voice utterance. The execution of the output control further includes determining a target on the basis of an analyzed context and controlling an output device to output an attracting utterance that attracts an interest of the target.

Abstract: A disclosed example apparatus includes means for storing a logged media impression for a media identifier representative of media accessed via the Internet, means for communicating to send a third-party device identifier or a user identifier corresponding to the user to a database proprietor when a user has not elected to not participate in third-party tracking corresponding to online activities, and receive user information from the database proprietor based on the third-party device identifier or the user identifier, and means for processing to log a demographic impression based on the media impression and the user information, and generate an impression report corresponding to the media based on the demographic impression.

Abstract: Systems and methods are provided for systematically finding and fixing automatic speech recognition (ASR) mistranscriptions and natural language understanding (NLU) misinterpretations and labeling data for machine learning. High similarity of non-identical consecutive queries indicates ASR mistranscriptions. Consecutive queries with close vectors in a semantic embedding space indicates NLU misinterpretations. Key phrases and barge-in also indicate errors. Only queries within a short amount of time are considered.

Abstract: In accordance with an aspect of the disclosure, an electronic device comprises a communication circuitry configured to establish a voice call with an external electronic device; a microphone; a memory configured to store a first sound quality enhancement parameter; and a processor, wherein the processor is configured to: obtain an audio signal associated with speech through the microphone, during the voice call; transmit, to a server, voice data based on the audio signal when the ratio is within a first range; transmit, to the server, noise data based on the audio signal, when the ratio is within a second range; receive an updated sound quality enhancement parameter from the server with the communication circuit during the voice call; and adjust the first sound quality enhancement parameter stored in the memory, based on the updated sound quality enhancement parameter received from the server.

Abstract: What is described is a system for outputting audio signals having a first output device for outputting audio signals having predeterminable parameter values of a first set of settable parameters, a data storage for storing parameter values, and an administration device. Thus, the administration device accesses the data storage and searches for stored parameter values for a set of parameters which is equal or similar to the first set of parameters. In addition, in case of having found stored parameter values, the administration device transfers the parameter values and/or parameter values determined therefrom to the first output device.

Abstract: The present invention proposes a new method and a new apparatus for enhancement of audio source coding systems utilising high frequency reconstruction (HFR). It utilises a detection mechanism on the encoder side to assess what parts of the spectrum will not be correctly reproduced by the HFR method in the decoder. Information on this is efficiently coded and sent to the decoder, where it is combined with the output of the HFR input.

Abstract: A device includes: a first acquiring unit to acquire context information corresponding to running operation among pieces of context information; a second acquiring unit to acquire detection information output from a detecting unit detecting a physical quantity of a target device; an extracting unit to extract, from the detection information, feature information indicating a feature of the detection information in an interval including a specific operation interval of the target device; a selecting unit to select reference feature information used as reference based on the feature information, and sequentially select pieces of target feature information; a calculating unit to calculate a likelihood of a process interval based on a comparison between the reference feature information and each piece of target feature information; a determining unit to determine whether the target feature information corresponding to the likelihood is included in the process interval based on the likelihood; and an estimating uni

Abstract: An audio decoder for providing a decoded audio information on the basis of an encoded audio information is disclosed. The audio decoder includes a linear-prediction-domain decoder configured to provide a first decoded audio information on the basis of an audio frame encoded in a linear prediction domain, a frequency domain decoder configured to provide a second decoded audio information on the basis of an audio frame encoded in a frequency domain, and a transition processor. The transition processor is configured to obtain a zero-input-response of a linear predictive filtering, wherein an initial state of the linear predictive filtering is defined depending on the first decoded audio information and the second decoded audio information, and modify the second decoded audio information depending on the zero-input-response, to obtain a smooth transition between the first and the modified second decoded audio information.

Abstract: CMOS-compatible high-speed and low power random number generator and techniques for use thereof are provided. In one aspect, a random number generator includes: a noise amplification unit configured to generate an amplified noise signal, wherein the noise amplification unit includes noise amplification unit transistors having a threshold voltage (Vt,amp) of about 0; and a computing unit configured to process the amplified noise signal from the noise amplification unit to generate a stream of random numbers, wherein the computing unit comprises computing unit transistors having absolute values of a Vt,compute that are larger than the Vt,amp of the noise amplification unit transistors in the noise amplification unit. For digital implementations, an analog-to-digital converter configured to digitize the amplified noise signal can be employed. For analog implementations, a sample and hold circuit configured to sample the amplified noise signal can be employed.

Abstract: An audio decoder for providing a decoded audio information on the basis of an encoded audio information is disclosed. The audio decoder includes a linear-prediction-domain decoder configured to provide a first decoded audio information on the basis of an audio frame encoded in a linear prediction domain, a frequency domain decoder configured to provide a second decoded audio information on the basis of an audio frame encoded in a frequency domain, and a transition processor. The transition processor is configured to obtain a zero-input-response of a linear predictive filtering, wherein an initial state of the linear predictive filtering is defined depending on the first decoded audio information and the second decoded audio information, and modify the second decoded audio information depending on the zero-input-response, to obtain a smooth transition between the first and the modified second decoded audio information.