Intelligent cockpit voice assistant self-adaptive voice enhancement method, device, system, computer equipment and medium

Abstract

The application discloses an intelligent cockpit voice assistant adaptive voice enhancement method, device, system, computer equipment and medium, and relates to the technical field of voice recognition. The implementation of the method comprises the following steps: extracting a current state from the current environment, wherein the current state comprises noise characteristics, current voice characteristics, filter state and user feedback; selecting an action based on the current state and a strategy to adjust filter parameters or voice enhancement model weights; processing the current voice signal using the adjusted voice enhancement model to obtain a recognition result, calculating a reward based on the recognition result of the voice enhancement model and the user feedback; and using the current state, action, reward and next time state as samples to train a neural network to update the strategy. The application can solve the problems of low voice recognition accuracy and poor user experience of the traditional intelligent cockpit voice assistant system when facing complex and variable in-vehicle environments.

Description

Technical Field

[0001] This application relates to the field of speech recognition technology, specifically to an adaptive speech enhancement method, device, system, computer equipment, and medium for an intelligent cockpit voice assistant. Background Technology

[0002] Traditional voice assistant systems typically use fixed-parameter filters and voice enhancement models to process in-vehicle voice signals. These systems perform voice enhancement and noise suppression based on preset environmental noise models. However, due to the complexity and variability of the in-vehicle environment, traditional fixed-parameter methods often cannot cope with various noise scenarios, resulting in low voice recognition accuracy, especially in noisy environments, leading to a poor user experience.

[0003] Based on this, some intelligent voice assistant systems have begun to introduce adaptive filtering technology, using environmental noise sensors to detect in-vehicle noise in real time and adjust filter parameters to enhance the voice signal. Although adaptive filtering technology can improve the quality of the voice signal to some extent, existing adaptive technologies often only consider the amplitude characteristics of the noise signal and lack consideration for temporal characteristics and user feedback, resulting in insufficient adaptive capabilities and personalized services.

[0004] In summary, existing technologies lack effective adaptive and self-learning mechanisms, making it impossible to optimize system performance in real time based on environmental changes and user feedback. Summary of the Invention

[0005] This application provides an adaptive voice enhancement method, device, system, computer equipment, and medium for an intelligent cockpit voice assistant. It not only considers the limitations of traditional adaptive filters but also achieves more intelligent and personalized voice recognition processing by introducing user feedback and noise timing features.

[0006] In a first aspect, this application provides an adaptive voice enhancement method for a smart cockpit voice assistant, including:

[0007] Extract the current state from the current environment, wherein the current state includes: noise features, current speech features, filter state, and user feedback;

[0008] Based on the current state and policy, select actions to adjust filter parameters or speech enhancement model weights;

[0009] The current speech signal is processed using the adjusted speech enhancement model to obtain the recognition result. Based on the recognition result of the speech enhancement model and user feedback, the reward is calculated.

[0010] The current state, action, reward, and next state are used as samples to train the neural network to update the policy.

[0011] In some instances, extracting the current state from the current environment includes:

[0012] Extract the temporal features of in-vehicle noise as a noise state vector, extract the features of the current speech signal, generate a speech state vector, obtain the parameter configuration of the current adaptive filter, and obtain user feedback.

[0013] The current state is composed of the noise state vector, the speech state vector, the parameter configuration of the current adaptive filter, and user feedback.

[0014] In some instances, LSTM networks are used to extract the temporal features of in-vehicle noise as the noise state vector; and the MFCC features of the current speech signal are extracted as the speech state vector.

[0015] In some instances, R(t) = λ1·recognition result + λ2·user feedback is used, where λ1 and λ2 are weight parameters.

[0016] In some instances, training the neural network using the current state, action, reward, and next-time state as samples to update the policy includes:

[0017] The current state, action, reward, and next state are used as samples to train the Q-network, which continuously updates the Q-value function. This allows the network to adopt the best filtering parameters and speech enhancement strategies under different noise environments, enabling it to select the optimal action to maximize the cumulative reward given the current state.

[0018] In some instances, by The Q-value update function is defined as follows: S(t) is the current state, A(t) is the action, α is the learning rate, γ is the discount factor, and A... ′ S(t+1) represents the next possible action and the state at the next moment.

[0019] Secondly, this application provides an adaptive voice enhancement device for a smart cockpit voice assistant, comprising:

[0020] The state design module is used to extract the current state from the current environment, wherein the current state includes: noise features, current speech features, filter state, and user feedback;

[0021] The action design module is used to select actions based on the current state and policy to adjust filter parameters or speech enhancement model weights;

[0022] The reward design module is used to process the current speech signal using the adjusted speech enhancement model to obtain the recognition result, and calculate the reward based on the recognition result of the speech enhancement model and user feedback.

[0023] The policy optimization module is used to train the neural network with the current state, action, reward, and next state as samples to update the policy.

[0024] Thirdly, this application provides an intelligent cockpit system including the aforementioned intelligent cockpit voice assistant adaptive voice enhancement device.

[0025] Fourthly, this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0026] Fifthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0027] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0028] (1) Enhanced dynamic adaptability: It can adjust system parameters in real time to cope with complex and ever-changing in-vehicle environment and significantly improve the accuracy of voice recognition.

[0029] (2) User-driven self-learning mechanism: Optimize the system through user feedback, improve the level of personalized service, and enhance user experience.

[0030] (3) Lightweight design: Optimize the algorithm to ensure real-time performance and efficiency in the embedded environment. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This is a schematic diagram of the adaptive voice enhancement method for intelligent cockpit voice assistant provided in an embodiment of this application;

[0033] Figure 2 This is a schematic diagram of the adaptive voice enhancement device for the intelligent cockpit voice assistant provided in the embodiments of this application;

[0034] Figure 3 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0035] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0036] In the following description, specific embodiments of this application will be illustrated with reference to steps and symbols performed by one or more computers, unless otherwise stated. Therefore, these steps and operations will be referred to several times as being performed by a computer, and computer execution as referred to herein includes operations by a computer processing unit representing electronic signals of data in a structured format. This operation transforms the data or maintains it at a location in the computer's memory system, which can be reconfigured or otherwise alter the operation of the computer in a manner well known to those skilled in the art. The data structure maintained by the data is the physical location of the memory, which has specific characteristics defined by the data format. However, the principles of this application are described in the foregoing text, which is not intended to be limiting, and those skilled in the art will understand that many of the following steps and operations can also be implemented in hardware.

[0037] The terms "module" or "unit" as used herein can be considered as software objects executing on the computing system. Different components, modules, engines, and services described herein can be considered as implementations on the computing system. The apparatus and methods described herein are preferably implemented in software, but can also be implemented in hardware, both of which are within the scope of this application.

[0038] Those skilled in the art will understand that, unless explicitly stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in the specification of this application means the presence of features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0039] Firstly, this application provides an adaptive voice enhancement method for intelligent cockpit voice assistants, aiming to provide a voice feature enhancement technology that can adapt to complex environments in real time, such as... Figure 1 As shown, it includes the following steps:

[0040] S101: Extract the current state from the current environment, where the current state includes: noise features, current speech features, filter state, and user feedback;

[0041] S102: Select an action based on the current state and policy to adjust filter parameters or speech enhancement model weights;

[0042] One can use a deep Q-network to select an action, namely, adjusting filter parameters or model weights.

[0043] S103: Process the current speech signal using the adjusted speech enhancement model to obtain the recognition result, and calculate the reward based on the recognition result of the speech enhancement model and user feedback;

[0044] S104: Train the neural network using the current state, action, reward, and next-time state as samples to update the policy.

[0045] Furthermore, after the current execution is completed, proceed to the next time step "t+1" and repeat steps S101 to S104 until convergence or the specified number of training rounds is reached.

[0046] In another specific example, the state space is the foundation of the algorithm, defining the system's environmental awareness capability at each time point. In this embodiment, the state space consists of the following parts:

[0047] Noise characteristics: Long Short-Term Memory (LSTM) network is used to extract the temporal characteristics of in-vehicle noise and generate a noise state vector N(t);

[0048] Speech features: Extract the Mel Frequency Cepstrum Coefficient (MFCC) features of the current speech signal to generate the speech state vector V(t);

[0049] Filter state: The parameter configuration F(t) of the current adaptive filter;

[0050] User feedback: Historical feedback data U(t-1) contains user feedback information from the previous moment.

[0051] Therefore, the complete state space is defined as: S(t)={N(t),V(t),F(t),U(t-1)}.

[0052] In another specific example, the action space defines the adjustment strategies that the system can take at each point in time. The action space in this embodiment includes:

[0053] Adjusting filter parameters: such as changing filter coefficients, increasing or decreasing certain parameters to adapt to the current noise characteristics;

[0054] Update the speech enhancement model: Enhance speech feature processing capabilities by adjusting the weights of the LSTM network or the parameters of the feedforward network.

[0055] Therefore, the action space is represented as: A(t) = {adjust filter parameters, update model weights}.

[0056] In another specific example, the design of the reward function directly affects the performance of the reinforcement learning model. The reward function in this embodiment combines user feedback and recognition accuracy, and is defined as follows: R(t) = λ1·accuracy improvement + λ2·user feedback rating, where λ1 and λ2 are weight parameters used to balance the influence of the two parts.

[0057] In another specific example, in this embodiment of the application, a Deep Q-Network (DQN) is used to optimize the strategy, ensuring that the optimal action is selected to maximize the cumulative reward in a given state. By continuously updating the Q-value function, the system gradually learns to adopt the best filtering parameter adjustments and speech enhancement strategies under different noise environments.

[0058] In another specific example, the formula for updating the value is:

[0059]

[0060] Where α is the learning rate, γ is the discount factor, and A ′ This is for possible next steps.

[0061] In another specific example, at the beginning, parameters also need to be initialized, including initial filter parameters, weights of the deep learning model, and Q-network for reinforcement learning.

[0062] Secondly, to facilitate better implementation of the methods provided in the embodiments of this application, the embodiments of this application also provide an apparatus based on the above methods. The meanings of the terms used are the same as in the methods described above, and specific implementation details can be found in the descriptions within the method embodiments.

[0063] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of the device provided in the embodiments of this application, wherein the device 200 may include a state design module 201, an action design module 202, a reward design module 203, and a strategy optimization module 204, wherein:

[0064] The state design module 201 is used to extract the current state from the current environment, wherein the current state includes: noise features, current speech features, filter state and user feedback;

[0065] Action design module 202 is used to select actions based on the current state and strategy to adjust filter parameters or speech enhancement model weights;

[0066] The reward design module 203 is used to process the current speech signal using the adjusted speech enhancement model to obtain the recognition result, and calculate the reward based on the recognition result of the speech enhancement model and user feedback.

[0067] The policy optimization module 204 is used to train the neural network with the current state, action, reward and the next state as samples to update the policy.

[0068] In another specific example, the state design module 201 is specifically used for:

[0069] Extract the temporal features of in-vehicle noise as a noise state vector, extract the features of the current speech signal, generate a speech state vector, obtain the parameter configuration of the current adaptive filter, and obtain user feedback.

[0070] The current state is composed of the noise state vector, the speech state vector, the parameter configuration of the current adaptive filter, and user feedback.

[0071] Specifically, the LSTM network is used to extract the temporal features of the in-vehicle noise as the noise state vector; the MFCC features of the current speech signal are extracted as the speech state vector.

[0072] In another specific example, R(t) = λ1·recognition result + λ2·user feedback, where λ1 and λ2 are weight parameters.

[0073] In some instances, the policy optimization module 204 is specifically used to train the Q-network using the current state, action, reward, and next-time state as samples to continuously update the Q-value function, thereby adopting the best filtering parameters and speech enhancement strategies under different noise environments, so as to select the optimal action to maximize the cumulative reward in a given current state.

[0074] In some instances, by The Q-value update function is defined as follows: S(t) is the current state, A(t) is the action, α is the learning rate, γ is the discount factor, and A... ′ S(t+1) represents the next possible action and the state at the next moment.

[0075] Thirdly, this application also provides an intelligent cockpit system including the aforementioned intelligent cockpit voice assistant adaptive voice enhancement device 200. The main hardware requirements include a microphone array and an in-vehicle processor. During manufacturing, the arrangement of the microphone array needs to be optimized to ensure effective separation of noise and voice signals, while the computing power allocation of the in-vehicle processor needs to be optimized to support real-time adaptive voice feature enhancement processing.

[0076] In this embodiment, the vehicle-mounted processor can be a terminal device or a server.

[0077] In this embodiment, when the on-board processor is a server, the server can be a standalone server, a server network, or a server cluster. For example, the server described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing. In this embodiment, communication between the server and the client can be achieved through any communication method, including but not limited to mobile communication based on the 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), and Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on the TCP / IP Protocol Suite (TCP / IP) and User Datagram Protocol (UDP).

[0078] It is understood that when the vehicle-mounted processor used in the embodiments of this application is a terminal device, the terminal device can be a device that includes both receiving hardware and transmitting hardware, that is, a device with receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a terminal device may include: cellular or other communication devices, which have a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the vehicle-mounted processor can be a desktop terminal or a mobile terminal, and the vehicle-mounted processor can be one of a mobile phone, tablet computer, laptop computer, etc.

[0079] Fourthly, embodiments of this application also provide a computer device, such as... Figure 3 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0080] The computer device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will understand that... Figure 3 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0081] The processor 301 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 302, and by calling data stored in the memory 302, it performs various functions of the computer device and processes data, thereby providing overall monitoring of the computer device. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operation of the storage medium, user interface, and application programs, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 301.

[0082] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and data processing by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store applications required for operating the storage medium and at least one function (such as sound playback function, image playback function, etc.); the data storage area may store data created according to the use of the computer device. In addition, the memory 302 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a controller to provide the processor 301 with access to the memory 302.

[0083] The computer device also includes a power supply 303 that supplies power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 via a power management storage medium, thereby enabling functions such as charging, discharging, and power consumption management through the power management storage medium. The power supply 303 may also include one or more DC or AC power supplies, recharge storage media, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0084] The computer device may also include an input unit 304, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0085] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the computer device loads the executable files corresponding to the processes of one or more applications into the memory 302 according to the following instructions, and the processor 301 runs the applications stored in the memory 302, thereby implementing the steps in the above method embodiment.

[0086] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0087] Therefore, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to execute the steps of any of the methods provided in embodiments of this application.

[0088] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0089] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0090] Since the computer program stored in the computer-readable storage medium can execute the steps of any of the methods provided in the embodiments of this application, the beneficial effects that any of the methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0091] The above provides a detailed description of an adaptive voice enhancement method, device, system, computer equipment, and medium for an intelligent cockpit voice assistant provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An adaptive voice enhancement method for an intelligent cockpit voice assistant, characterized in that, include: Extract the current state from the current environment, wherein the current state includes: noise features, current speech features, filter state, and user feedback; Actions are selected based on the current state and policy to adjust filter parameters or speech enhancement model weights; The current speech signal is processed using the adjusted speech enhancement model to obtain the recognition result. Based on the recognition result of the speech enhancement model and user feedback, the reward is calculated. The current state, action, reward, and next state are used as samples to train the neural network to update the policy; The step of training a neural network using the current state, action, reward, and next-time state as samples to update the policy includes: The current state, action, reward, and next state are used as samples to train the Q-network, which continuously updates the Q-value function. This allows the network to adopt the best filtering parameters and speech enhancement strategies under different noise environments, enabling it to select the optimal action to maximize the cumulative reward given the current state.

2. The method according to claim 1, characterized in that, Extracting the current state from the current environment includes: Extract the temporal features of in-vehicle noise as a noise state vector, extract the features of the current speech signal, generate a speech state vector, obtain the parameter configuration of the current adaptive filter, and obtain user feedback. The current state is composed of the noise state vector, the speech state vector, the parameter configuration of the current adaptive filter, and user feedback.

3. The method according to claim 2, characterized in that, The LSTM network is used to extract the temporal features of the in-vehicle noise as the noise state vector; the MFCC features of the current speech signal are extracted as the speech state vector.

4. The method according to any one of claims 1 to 3, characterized in that, Depend on Receive a reward ,in, and These are weight parameters.

5. The method according to claim 4, characterized in that, Depend on The function to update the Q-value, where, This is the current state. For action, It's the learning rate. It is a discount factor. For possible next steps, This is the state at the next moment.

6. An adaptive voice enhancement device for an intelligent cockpit voice assistant, characterized in that, include: The state design module is used to extract the current state from the current environment, wherein the current state includes: noise features, current speech features, filter state, and user feedback; The action design module is used to select actions based on the current state and policy to adjust filter parameters or speech enhancement model weights; The reward design module is used to process the current speech signal using the adjusted speech enhancement model to obtain the recognition result, and calculate the reward based on the recognition result of the speech enhancement model and user feedback. The strategy optimization module is used to train the Q-network by taking the current state, action, reward, and next state as samples to continuously update the Q-value function. This allows the network to adopt the best filtering parameters and speech enhancement strategies under different noise environments, so that the optimal action is selected in the given current state to maximize the cumulative reward.

7. An intelligent cockpit system including the intelligent cockpit voice assistant adaptive voice enhancement device as described in claim 6.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method of any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Images