Vocabulary recognition method and device based on voice model, electronic equipment and medium

Abstract

The embodiment of the invention provides a vocabulary recognition method and device based on a voice model, electronic equipment and a medium, and belongs to the technical field of financial science and technology. The method comprises the following steps: acquiring a to-be-recognized audio and a target audio; performing text conversion on the target audio to obtain a hot word text corresponding to the target hot word audio; obtaining a prefix sequence of the voice model, inputting the to-be-recognized audio and the target audio into the voice model for feature splicing, and outputting a spliced feature sequence; adding the target hot word audio to the splicing feature sequence to obtain a target audio sequence, and adding the hot word text to a prefix sequence to obtain a target prefix sequence; inputting the target audio sequence and the target prefix sequence into a voice model to perform hot word recognition on the to-be-recognized audio, and outputting a recognized hot word audio; and performing text conversion on the to-be-recognized audio and the recognized hot word audio to obtain a target audio text. According to the embodiment of the invention, the hot words can be accurately recognized, and the hot word recognition accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a vocabulary recognition method, device, electronic device and medium based on a speech model. Background Art

[0002] Speech recognition is one of the most promising technologies in the 21st century. It has been widely used in many fields, including artificial intelligence, natural language processing, and machine translation. With the continuous development of artificial intelligence technology, speech recognition technology has also made great progress. Traditional speech recognition mainly relies on manual input, which is inefficient and costly. The speech recognition big model is trained with a large amount of Internet speech data and can recognize speech in multiple languages ​​naturally, which greatly improves the efficiency and cost of speech recognition.

[0003] The hot word technology of the speech recognition large model is based on the existing pre-trained model, and further optimizes specific words to improve the model's recognition accuracy for certain proper nouns (such as place names, names of people, product names, etc.). In the current speech recognition large model's vocabulary recognition process, while optimizing specific words, it is easy to cause misrecognition of other words, resulting in low hot word recognition accuracy. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a vocabulary recognition method, device, electronic device and medium based on a speech model, which can achieve accurate recognition of hot words and improve the accuracy of hot word recognition.

[0005] To achieve the above object, a first aspect of an embodiment of the present application proposes a vocabulary recognition method based on a speech model, the method comprising: Acquire the audio to be recognized and the target audio, wherein the target audio includes at least one target hot word audio; Performing text conversion on the target audio to obtain a hot word text corresponding to the target hot word audio; Obtaining a prefix sequence of the speech model, and inputting the audio to be recognized and the target audio into the speech model for feature splicing, and outputting a spliced ​​feature sequence; Add the target hot word audio to the concatenated feature sequence to obtain a target audio sequence, and add the hot word text to the prefix sequence to obtain a target prefix sequence; Input the target audio sequence and the target prefix sequence into the speech model, so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, and outputs the recognized hot word audio; The audio to be recognized and the recognized hot word audio are converted into text to obtain a target audio text.

[0006] In some embodiments, the target audio is obtained by the following steps: Obtaining artificial audio and target hot word vocabulary, and counting the number of vocabulary of the target hot word vocabulary, wherein the artificial audio is obtained by artificial recording; Performing audio quality analysis on the artificial audio to obtain an audio quality score, wherein the audio quality score is used to characterize the sound quality and fluency of the artificial audio; When the number of the vocabulary is less than a preset number and the audio quality score is greater than or equal to a first preset score, taking the artificial audio as the target audio; When the number of words is greater than or equal to a preset number or the audio quality score is less than a first preset score, audio synthesis is performed on the target hot word vocabulary through a preset deep learning model to obtain the target audio.

[0007] In some embodiments, performing audio quality analysis on the artificial audio to obtain an audio quality score includes: Performing time-frequency transformation on the artificial audio, and extracting features from the artificial audio after the time domain transformation to obtain artificial audio features; Performing sound quality detection on the artificial audio based on the artificial audio feature; When the artificial audio has noise, determining a second preset score as the audio quality score, wherein the second preset score is less than the first preset score; When there is no noise in the artificial audio, the clarity of the artificial audio is detected based on the artificial audio features to obtain an audio quality score.

[0008] In some embodiments, the step of synthesizing the target hot word vocabulary through a preset deep learning model to obtain the target audio includes: Inputting the target hot word vocabulary into a preset deep learning model, so that the deep learning model performs phoneme analysis on the target hot word vocabulary and outputs a spectrogram; Performing audio conversion on the spectrogram through a preset vocoder to obtain an audio waveform; Generate target audio according to the audio waveform.

[0009] In some embodiments, converting the target audio into text to obtain a hot word text corresponding to the target hot word audio includes: Extracting features of the target audio to obtain target audio features corresponding to the target audio; Performing feature mapping on the target audio feature through a preset acoustic model to obtain a target candidate sequence of the target audio feature; Inputting the target candidate sequence into a preset language model, so that the language model analyzes the contextual relationship of the target audio based on the target candidate sequence and outputs a target text sequence; The target text sequence is decoded to obtain a hot word text corresponding to the target hot word audio.

[0010] In some embodiments, the step of inputting the to-be-recognized audio and the target audio into a speech model for feature splicing and outputting a spliced ​​feature sequence includes: Extracting a first concatenated feature sequence of the audio to be recognized and a second concatenated feature sequence of the target audio through the speech model; Feature splicing is performed on the first splicing feature sequence and the second splicing feature sequence to obtain a splicing feature sequence.

[0011] In some embodiments, the step of inputting the to-be-recognized audio and the target audio into a speech model for feature concatenation and outputting a concatenated feature sequence further includes: Performing audio splicing on the audio to be recognized and the target audio to obtain a spliced ​​audio; The audio feature sequence of the concatenated audio is extracted through the speech model.

[0012] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a vocabulary recognition device based on a speech model, the device comprising: An audio acquisition module, used to acquire the audio to be recognized and the target audio, wherein the target audio includes at least one target hot word audio; A text conversion module, used for performing text conversion on the target audio to obtain a hot word text corresponding to the target hot word audio; A feature splicing module, used to obtain a prefix sequence of the speech model, input the audio to be recognized and the target audio into the speech model for feature splicing, and output a spliced ​​feature sequence; A sequence splicing module, used for adding the target hot word audio to the splicing feature sequence to obtain a target audio sequence, and adding the hot word text to the prefix sequence to obtain a target prefix sequence; A hot word recognition module, used for inputting the target audio sequence and the target prefix sequence into the speech model, so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, and outputs the recognized hot word audio; The target conversion module is used to perform text conversion on the audio to be recognized and the recognized hot word audio to obtain a target audio text.

[0013] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the speech model-based vocabulary recognition method as described in the first aspect when executing the computer program.

[0014] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the vocabulary recognition method based on the speech model as described in the first aspect.

[0015] The speech model-based vocabulary recognition method, device, electronic device and storage medium proposed in the present application first obtain the audio to be recognized and the target audio, and the target audio includes at least one target hot word audio, that is, the audio corresponding to the hot word that needs to be recognized, and then convert the target audio into text to obtain the hot word text corresponding to the target hot word audio, so as to realize the textual display of the target hot word audio, thereby improving the accuracy of information recognition, and then obtain the prefix sequence of the speech model to facilitate the subsequent decoding of the audio by the speech model, and input the audio to be recognized and the target audio into the speech model for feature splicing, and output the spliced ​​feature sequence, thereby improving the recognition accuracy of the speech, eliminating irrelevant or redundant features, reducing the complexity of the model, and avoiding The risk of overfitting, the target hot word audio is added to the splicing feature sequence to obtain the target audio sequence, and the hot word text is added to the prefix sequence to obtain the target prefix sequence, so that the target audio sequence and the target prefix sequence can be combined with the hot word and the hot word text corresponding to the hot word, and the hot word prefix is ​​added. Then the target audio sequence and the target prefix sequence are input into the speech model, so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, outputs the recognized hot word audio, and realizes accurate recognition of the audio corresponding to the hot word, improves the recognition accuracy of the hot word audio, and finally, the audio to be recognized and the recognized hot word audio are converted into text to obtain the target audio text, thereby improving the recognition accuracy of the hot words in the target audio text. The embodiment of the present application utilizes the contextual reasoning ability and autoregressive generation mechanism in the speech model, adds the target hot word audio to the splicing feature sequence during the model processing, and adds the hot word text to the prefix sequence to increase the hot word prefix, so that the accuracy of the hot word recognition of the speech model can be improved by combining the input hot word audio sequence with the text, and the accurate recognition of the hot words can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of a vocabulary recognition method based on a speech model provided by an embodiment of the present application; Figure 2 This is a flowchart of obtaining target audio provided by an embodiment of the present application; Figure 3 yes Figure 2 Flow chart of step S202 in FIG. Figure 4 yes Figure 2 Flow chart of step S204 in FIG. Figure 5 yes Figure 1 Flow chart of step S102 in FIG. Figure 6 A flow chart of a method for inputting the audio to be recognized and the target audio into a speech model for feature splicing provided in an embodiment of the present application; Figure 7 A flow chart of a method for inputting a to-be-recognized audio and a target audio into a speech model for feature splicing provided in another embodiment of the present application; Figure 8 It is a structural diagram of a vocabulary recognition device based on a speech model provided in an embodiment of the present application; Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0020] First, some nouns involved in this application are analyzed: Natural Language Processing (NLP): NLP uses computers to process, understand, and apply human languages ​​(such as Chinese, English, etc.). NLP is a branch of artificial intelligence and an interdisciplinary subject between computer science and linguistics. It is often referred to as computational linguistics. Natural language processing includes grammatical analysis, semantic analysis, and text understanding. Natural language processing is commonly used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis, and opinion mining. It involves data mining related to language processing, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computing.

[0021] Text-to-Speech (TTS): TTS technology refers to the technology of converting text information into audible speech, which is widely used in speech synthesis, voice assistants, e-readers and other fields.

[0022] Hidden Markov Model (HMM): Hidden Markov Model is a statistical model used to describe a Markov process with hidden unknown parameters. It is widely used in speech recognition, natural language processing and other fields.

[0023] Fast Fourier Transform (FFT): FFT is an algorithm for efficiently calculating discrete Fourier transform and its inverse transform, and is widely used in signal processing, image analysis, audio processing and other fields.

[0024] Short Time Fourier Transform (STFT): STFT is a method of decomposing a signal into different frequency components that vary over time. It is particularly suitable for spectral analysis of non-stationary signals and is an important tool in speech signal processing.

[0025] Based on this, the embodiments of the present application provide a vocabulary recognition method and device, an electronic device and a storage medium based on a speech model, which can achieve accurate recognition of hot words and improve the accuracy of hot word recognition.

[0026] The speech model-based vocabulary recognition method and device, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the speech model-based vocabulary recognition method in the embodiments of the present application is described.

[0027] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0028] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include computer vision technology, robotics technology, biometrics technology, module management technology of online meeting systems, natural language processing technology, and machine learning / deep learning.

[0029] The speech model-based vocabulary recognition method provided in the embodiment of the present application relates to the field of financial technology. The speech model-based vocabulary recognition method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements a speech model-based vocabulary recognition method, etc., but is not limited to the above forms.

[0030] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0031] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with the relevant laws, regulations, and standards of the relevant countries and regions. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0032] Speech recognition is one of the most promising technologies in the 21st century. It has been widely used in many fields, including artificial intelligence, natural language processing, and machine translation. With the continuous development of artificial intelligence technology, speech recognition technology has also made great progress. Traditional speech recognition mainly relies on manual input, which is inefficient and costly. The speech recognition big model is trained with a large amount of Internet speech data and can recognize speech in multiple languages ​​naturally, which greatly improves the efficiency and cost of speech recognition.

[0033] The hot word technology of the speech recognition large model is based on the existing pre-trained model, and further optimizes specific words to improve the model's recognition accuracy for certain proper nouns (such as place names, names of people, product names, etc.). In the current speech recognition large model's vocabulary recognition process, while optimizing specific words, it is easy to cause misrecognition of other words, resulting in low hot word recognition accuracy.

[0034] In order to solve the above problems, the present embodiment provides a vocabulary recognition method, device, electronic device and storage medium based on a speech model. First, the audio to be recognized and the target audio are obtained, and the target audio includes at least one target hot word audio, that is, the audio corresponding to the hot word that needs to be recognized. Then, the target audio is converted into text to obtain the hot word text corresponding to the target hot word audio, and the textual display of the target hot word audio is realized, thereby improving the accuracy of information recognition. After that, the prefix sequence of the speech model is obtained to facilitate the subsequent decoding of the audio by the speech model, and the audio to be recognized and the target audio are input into the speech model for feature splicing, and the spliced ​​feature sequence is output, thereby improving the recognition accuracy of the speech, eliminating irrelevant or redundant features, and reducing the complexity of the model. The target audio word is added to the concatenated feature sequence to obtain the target audio sequence, and the hot word text is added to the prefix sequence to obtain the target prefix sequence, so that the target audio sequence and the target prefix sequence can be combined with the hot word and the hot word text corresponding to the hot word, and the hot word prefix is ​​added. Then the target audio sequence and the target prefix sequence are input into the speech model, so that the speech model can perform hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, output the recognized hot word audio, and realize accurate recognition of the audio corresponding to the hot word, and improve the recognition accuracy of the hot word audio. Finally, the audio to be recognized and the recognized hot word audio are converted into text to obtain the target audio text, thereby improving the recognition accuracy of the hot words in the target audio text. The embodiment of the present application utilizes the contextual reasoning ability and autoregressive generation mechanism in the speech model, and adds the target hot word audio to the concatenated feature sequence during the model processing, and adds the hot word text to the prefix sequence to increase the hot word prefix, so that the accuracy of the hot word recognition of the speech model can be improved by combining the input hot word audio sequence with the text, and the accurate recognition of the hot word can be realized.

[0035] The following is a detailed description with reference to the accompanying drawings.

[0036] Figure 1 is an optional flow chart of a vocabulary recognition method based on a speech model provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0037] Step S101, obtaining the audio to be recognized and the target audio, wherein the target audio includes at least one target hot word audio.

[0038] In step S101 of some embodiments, audio to be recognized and target audio are obtained, wherein the target audio includes at least one target hot word audio. Specifically, the target hot word audio may be a place name, a person's name, a company name, etc., to facilitate the subsequent recognition of hot words corresponding to the target hot word audio in the audio to be recognized.

[0039] It is understandable that the audio to be identified in the embodiment of the present application can be obtained by manual recording or extracted from an open source database, and the embodiment of the present application does not make any specific limitations.

[0040] Step S102, convert the target audio into text to obtain a hot word text corresponding to the target hot word audio.

[0041] In step S102 of some embodiments, the target audio is converted into text, the contextual relationship of words in the sentence is predicted, the recognition accuracy is improved through the contextual information, and the hot word text corresponding to the target hot word audio is obtained. The automated speech-to-text operation can greatly save the time of manual input, making it easier to use the hot word text as a prefix of the prefix sequence.

[0042] Step S103, obtaining a prefix sequence of the speech model, and inputting the audio to be recognized and the target audio into the speech model for feature splicing, and outputting a spliced ​​feature sequence.

[0043] In step S103 of some embodiments, a prefix sequence of the speech model is obtained, wherein the prefix sequence refers to the prior text information used by the model during decoding, which is used to initialize the decoding process of the model. The audio to be recognized and the target audio are input into the speech model for feature splicing, and a spliced ​​feature sequence is output. By splicing multiple feature sequences, a more comprehensive feature sequence can be constructed, which can capture complex patterns and subtle differences in the audio, thereby improving the performance of the audio processing task.

[0044] It should be noted that the speech model in the embodiment of the present application is a Whisper model.

[0045] It is understandable that the prefix sequence contains special tokens, such as task type (translation or transcription), language tag, and timestamp.

[0046] Step S104, adding the target hot word audio to the concatenated feature sequence to obtain a target audio sequence, and adding the hot word text to the prefix sequence to obtain a target prefix sequence.

[0047] In step S104 of some embodiments, the target hot word audio is added to the splicing feature sequence to obtain a target audio sequence, and the hot word text is added to the prefix sequence to obtain a target prefix sequence, so that the target audio sequence and the target prefix sequence can be combined with the hot word and the hot word text corresponding to the hot word, and the hot word prefix is ​​added to facilitate subsequent recognition of the hot word.

[0048] It is worth noting that, compared with the method of directly adding hot words in the prefix sequence Prompt, the embodiment of the present application combines the audio information corresponding to the hot words, avoiding the problem of misrecognition of other words caused by introducing hot words in Prompt; in addition, compared with the method of constructing a hot word model and jointly training a large speech model, the embodiment of the present application does not need to train the model, thereby speeding up the efficiency of hot word recognition and reducing the cost of model training.

[0049] Step S105, inputting the target audio sequence and the target prefix sequence into the speech model, so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, and outputs the recognized hot word audio.

[0050] In step S105 of some embodiments, the target audio sequence and the target prefix sequence are input into the speech model, so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, thereby improving the hot word recognition accuracy of the speech recognition model by combining the input hot word audio sequence with the text, outputting the recognized hot word audio, and improving the accuracy of the hot word audio recognition.

[0051] Step S106, converting the audio to be recognized and the recognized hot word audio into text to obtain the target audio text.

[0052] In step S106 of some embodiments, text conversion is performed on the audio to be recognized and the recognized hot word audio, and the recognized hot word audio in the audio to be recognized is recognized during the text conversion process to obtain the target audio text.

[0053] In some embodiments, the embodiments of the present application only need to replace the target hot word audio and hot word text when updating hot words, without retraining the voice model, thereby achieving rapid iterative update of hot words and reducing the cost of iterative update of hot words.

[0054] See also Figure 2 , Figure 2 is a flowchart of obtaining target audio provided by an embodiment of the present application, Figure 2 The method may include but is not limited to steps S201 to S204.

[0055] Step S201, obtaining artificial audio and target hot word vocabulary, and counting the number of vocabulary of the target hot word vocabulary.

[0056] It should be noted that artificial audio is obtained by manual recording.

[0057] Step S202: Perform audio quality analysis on the artificial audio to obtain an audio quality score.

[0058] It should be noted that the audio quality score is used to characterize the sound quality and fluency of artificial audio.

[0059] Step S203: When the number of words is less than a preset number and the audio quality score is greater than or equal to a first preset score, the artificial audio is used as the target audio.

[0060] In steps S201 to S203 of some embodiments, in the process of obtaining the target audio, the embodiment of the present application will first obtain artificial audio and target hot word vocabulary, wherein the artificial audio is obtained by artificial recording, the target hot word vocabulary is a hot word set or marked in advance, and the vocabulary number of the target hot word vocabulary is counted. Specifically, the embodiment of the present application can first classify the target hot word vocabulary to obtain the hot word classification, and then for each hot word classification, the number of hot words under each hot word classification is counted to obtain the target hot word vocabulary number, and then the audio quality analysis of the artificial audio is performed to detect whether the artificial audio has noise, whether it is smooth or clear, and the audio quality score is obtained to achieve the quality assessment of the artificial audio, so as to facilitate the subsequent selection of whether to select the artificial audio as the target audio. Then compare the vocabulary number with the preset number, and compare the audio quality score with the first preset score. When the vocabulary number is less than the preset number and the audio quality score is greater than or equal to the first preset score, it means that the number of target hot word vocabulary is small, and the artificial audio is relatively clear, without noise or unclear situation, and the artificial audio can be directly used as the target audio, thereby ensuring the quality and clarity of the target audio.

[0061] Step S204: When the number of words is greater than or equal to the preset number or the audio quality score is less than the first preset score, audio synthesis is performed on the target hot word vocabulary through a preset deep learning model to obtain the target audio.

[0062] In step S204 of some embodiments, when the number of words is greater than or equal to the preset number or the audio quality score is less than the first preset score, it means that the number of target hot word words is large, or the artificial audio has a lot of noise, the audio is unclear, or it is not smooth. At this time, it is necessary to perform audio synthesis on the target hot word words through a preset deep learning model to obtain the target audio, so as to ensure the integrity of the target audio, avoid the loss of the target hot word words, and improve the quality of the target audio.

[0063] It should be noted that the preset number in the embodiment of the present application can be set according to the needs of the user, for example, the preset number is set to 10, 20 or 15, etc. The first preset score is related to the audio quality and can be set according to the needs of the user, for example, the first preset score is set to 70 points, 80 points, 90 points, etc. The embodiment of the present application does not make any specific restrictions.

[0064] See also Figure 3In some embodiments, step S202 may also include but is not limited to steps S301 to S304.

[0065] Step S301, performing time-frequency transformation on the artificial audio, and extracting features from the artificial audio after the time domain transformation to obtain artificial audio features.

[0066] Step S302: Perform sound quality detection on the artificial audio based on the artificial audio features.

[0067] Step S303: When the artificial audio has noise, the second preset score is determined as the audio quality score.

[0068] It should be noted that the second preset score is smaller than the first preset score.

[0069] In steps S301 to S303 of some embodiments, in the process of performing audio quality analysis on artificial audio, the embodiment of the present application first performs time-frequency transformation on the artificial audio, for example, Fourier transform or short-time Fourier transform, converts the audio signal from the time domain to the frequency domain, so as to analyze its frequency components, and extracts features of the artificial audio after the time domain transformation. In the frequency domain, noise is identified by extracting the features of the audio signal to obtain artificial audio features, wherein the artificial audio features include but are not limited to the intensity, frequency distribution, cepstrum features, harmonic features and long-term information of the signal. Afterwards, the sound quality of the artificial audio is detected based on the artificial audio features. Specifically, the extracted features are used to determine whether there is noise in the signal by setting a threshold, a statistical model or a machine learning method. For example, it is possible to determine whether it is noise by comparing the power spectrum of the signal with the threshold, thereby reducing manual intervention and improving detection efficiency. When there is noise in the artificial audio, the second preset score is directly determined as the audio quality score, and the second preset score is less than the first preset score, so that it can be ensured that there is no noise in the target audio.

[0070] In some embodiments, in the process of detecting the sound quality of artificial audio based on artificial audio features, the embodiments of the present application will analyze the extracted artificial audio features, for example, statistical analysis, pattern recognition, etc., to identify specific patterns or anomalies in the audio and obtain analysis results. The audio quality is then classified according to the analysis results to determine whether there is noise interference in the artificial audio.

[0071] Step S304: When there is no noise in the artificial audio, the clarity of the artificial audio is detected based on the artificial audio features to obtain an audio quality score.

[0072] In step S304 of some embodiments, when there is no noise in the artificial audio, it means that the artificial audio at this time has no noise interference and is relatively pure. The clarity of the artificial audio can be directly detected based on the artificial audio features to obtain an audio quality score, which is convenient for subsequent determination of clear and clean target audio and further improves the accuracy of hot word recognition.

[0073] See also Figure 4 In some embodiments, step S204 may also include but is not limited to steps S401 to S403.

[0074] Step S401: input the target hot word vocabulary into a preset deep learning model, so that the deep learning model performs phoneme analysis on the target hot word vocabulary and outputs a spectrogram.

[0075] Step S402: Perform audio conversion on the spectrogram through a preset vocoder to obtain an audio waveform.

[0076] Step S403: Generate target audio according to the audio waveform.

[0077] In steps S401 to S403 of some embodiments, in the process of synthesizing the target hot word vocabulary through the preset deep learning model, the target hot word vocabulary is first input into the preset deep learning model so that the deep learning model performs phoneme analysis on the target hot word vocabulary, decomposes the target hot word vocabulary into phonemes, and determines the appropriate intonation pattern and the pause position in the sentence. Through the annotation of intonation and pauses, the synthesized speech sounds more natural and closer to the way humans speak, thereby avoiding pronunciation errors, and outputting a spectrogram, wherein the spectrogram contains the frequency and amplitude information of the speech, and the spectrogram provides the details of the synthesized speech, which facilitates the subsequent generation of clear and understandable speech. Afterwards, the spectrogram is converted into audio by a preset vocoder to obtain an audio waveform, thereby ensuring that the generated audio waveform is clear and can quickly generate an audio waveform. Finally, the audio waveform output by the vocoder is synthesized to generate a final audio file, i.e., the target audio. Through feature extraction and vocoder processing, high-quality speech can be generated to improve the intelligibility and naturalness of the speech.

[0078] It should be noted that the deep learning model in the embodiment of the present application can be a text-to-speech synthesis model, Google's Tacotron, DeepMind's WaveNet or open source ChatTTS, etc. The deep learning model in the embodiment of the present application is a text-to-speech synthesis model.

[0079] See also Figure 5 In some embodiments, step S102 may also include but is not limited to steps S501 to S504.

[0080] Step S501, extracting features of the target audio to obtain target audio features corresponding to the target audio.

[0081] Step S502: feature mapping is performed on the target audio features through a preset acoustic model to obtain a target candidate sequence of the target audio features.

[0082] Step S503: input the target candidate sequence into a preset language model, so that the language model analyzes the contextual relationship of the target audio based on the target candidate sequence and outputs a target text sequence.

[0083] Step S504, decoding the target text sequence to obtain the hot word text corresponding to the target hot word audio.

[0084] In steps S501 to S504 of some embodiments, in the process of converting the target audio into text, feature extraction is performed on the audio to be recognized and the target audio. Specifically, the target audio is first preprocessed, including denoising, segmentation, silence removal, etc., to improve the quality of the speech signal. By removing background noise and unnecessary silence parts, the speech is made clearer and the recognition accuracy is improved. Features are then extracted from the preprocessed target audio, such as Mel-frequency cepstral coefficients, to obtain target audio features corresponding to the target audio. Thereafter, feature mapping is performed on the target audio features through a preset acoustic model. Specifically, the audio is resampled to ensure that its sampling rate is 16kHz, and then the acoustic patterns in the speech signal are identified, corresponding to specific phonemes or words, and then the phonemes or single words are classified according to the acoustic model. The target candidate sequence of the target audio features is generated by the word, and the target candidate sequence is then input into a preset language model, so that the language model analyzes the contextual relationship of the target audio based on the target candidate sequence, predicts the contextual relationship of the words in the sentence, adjusts the sequence according to the language rules and statistical information, and outputs the target text sequence. The recognition accuracy is improved through the context information. After that, the first text sequence is decoded, the outputs of the acoustic model and the language model are decoded into readable text to obtain the audio text of the audio to be recognized, and the target text sequence is decoded, the outputs of the acoustic model and the language model are decoded into readable text to obtain the hot word text corresponding to the target hot word audio. The automated speech-to-text operation can greatly save the time of manual input, which is convenient for the subsequent use of the hot word text as the prefix of the prefix sequence.

[0085] It should be noted that the acoustic model can be a hidden Markov model, a deep learning model, a Whisper model, etc., and the embodiments of the present application do not make specific limitations.

[0086] See also Figure 6 , Figure 6A flow chart of a method for inputting the audio to be recognized and the target audio into a speech model for feature splicing provided in an embodiment of the present application, the method including but not limited to steps S601 to S602.

[0087] Step S601: extracting a first concatenated feature sequence of the audio to be recognized and a second concatenated feature sequence of the target audio through a speech model.

[0088] Step S602, performing feature splicing on the first splicing feature sequence and the second splicing feature sequence to obtain a splicing feature sequence.

[0089] In steps S601 to S602 of some embodiments, in the process of inputting the audio to be recognized and the target audio into the speech model for feature splicing, the first splicing feature sequence of the audio to be recognized and the second splicing feature sequence of the target audio are first extracted through the speech model. Specifically, the embodiment of the present application takes the speech model as the Whisper model as an example for explanation. First, the audio to be recognized and the target audio are resampled through the Whisper model to ensure that its sampling rate is 16kHz, and then the resampled audio signal is converted into a Mel spectrum map, wherein the Mel spectrum map used by Whisper is calculated by short-time Fourier transform (STFT), and the spectrum map has 80 frequency bands. After that, a first splicing feature sequence and a second splicing feature sequence are obtained according to the Mel spectrum map. After obtaining the first splicing feature sequence and the second splicing feature sequence, feature splicing is performed on the first splicing feature sequence and the second splicing feature sequence to obtain a splicing feature sequence. By splicing multiple feature sequences, a more comprehensive feature sequence can be constructed, which can capture complex patterns and subtle differences in audio, thereby improving the performance of audio processing tasks.

[0090] See also Figure 7 , Figure 7 A flowchart of a method for inputting the audio to be recognized and the target audio into a speech model for feature splicing is provided in another embodiment of the present application. The method includes but is not limited to steps S701 to S702.

[0091] Step S701, performing audio splicing on the audio to be recognized and the target audio to obtain a spliced ​​audio.

[0092] Step S702: extracting an audio feature sequence of the concatenated audio using a speech model.

[0093] In steps S701 to S702 of some embodiments, in the process of inputting the audio to be recognized and the target audio into the speech model for feature splicing, the embodiments of the present application can also first perform audio splicing on the audio to be recognized and the target audio to obtain the spliced ​​audio, thereby reducing the volume of the original data, and then extract the audio feature sequence of the spliced ​​audio through the speech model, thereby eliminating irrelevant or redundant features, reducing the complexity of the model, avoiding the risk of overfitting, and improving the training efficiency and prediction performance of the model.

[0094] See also Figure 8 The embodiment of the present application also provides a vocabulary recognition device based on a speech model, the device comprising: The audio acquisition module 801 is used to acquire the audio to be recognized and the target audio, wherein the target audio includes at least one target hot word audio; A text conversion module 802 is used to perform text conversion on the target audio to obtain a hot word text corresponding to the target hot word audio; The feature concatenation module 803 is used to obtain a prefix sequence of the speech model, input the audio to be recognized and the target audio into the speech model for feature concatenation, and output a concatenated feature sequence; A sequence concatenation module 804 is used to add the target hot word audio to the concatenation feature sequence to obtain a target audio sequence, and to add the hot word text to the prefix sequence to obtain a target prefix sequence; A hot word recognition module 805 is used to input a target audio sequence and a target prefix sequence into a speech model so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, and outputs the recognized hot word audio; The target conversion module 806 is used to perform text conversion on the audio to be recognized and the recognized hot word audio to obtain the target audio text.

[0095] The specific implementation of the speech model-based vocabulary recognition device is substantially the same as the specific implementation of the speech model-based vocabulary recognition method described above, and will not be described in detail herein.

[0096] In order to explain the above-mentioned speech model-based vocabulary recognition method, device, electronic device and medium more clearly and clearly, specific examples are given below for illustration.

[0097] Example 1: Taking the recognition of the target audio "I went to Jialian Payment Building today." as an example, the target hot word in the audio is "Jialian Payment Building". When the hot word technology of the embodiment of the present application is not used to directly input the model for transcription, it is easy to transcribe it into "I went to Jialian Zhifu Building today" or "I went to Jialian Payment Building today" and other incorrect results.

[0098] The specific steps of recognizing the audio in the embodiment of the present application are as follows: Step 1: Use artificial recording or a TTS model to synthesize the audio of the target hot word corresponding to "Jialian Payment Building".

[0099] Step 2: Extract the audio feature sequences of the target hot word audio and the target audio respectively and splice them (or splice the target hot word audio and the target audio first and then merge and extract the audio feature sequences, both methods are acceptable), input them into the model encoder, and at the same time add the target hot word text after the model prefix sequence text to obtain a prefix sequence in the style of "<|startoftranscript|><|zh|><|transcribe|><|notimestamps|>Jialian Payment Building". Then, convert it into tokens that can be processed by the model through the tokenizer and input it into the model decoder.

[0100] Step 3: The model performs autoregressive iterative decoding and gradually generates information such as "<|startoftranscript|><|zh|><|transcribe|><|notimestamps|>Jialian Payment Building I", "<|startoftranscript|><|zh|><|transcribe|><|notimestamps|>Jialian Payment Building I today", "<|startoftranscript|><|zh|><|transcribe|><|notimestamps|>I went to Jialian Payment Building today." based on the prefix sequence.

[0101] Step 4: After obtaining multiple target sentences in Step 3, remove the prefix sequence "<|startoftranscript|><|zh|><|transcribe|><|notimestamps|>Jialian Payment Building" from the model output to obtain the final result where the target hot word is correctly recognized: "I went to Jialian Payment Building today".

[0102] In the embodiment of this application, a voice prefix is added as a hot word optimization solution based on the Transformer structure of the voice model. This hot word technology makes full use of the context reasoning ability and autoregressive generation mechanism in the large voice recognition model, and adds hot word prefixes to the inputs of the encoder and decoder of the original model respectively. Without increasing the additional training cost and the risk of misrecognition, the embodiment of this application improves the hot word recognition accuracy of the large voice recognition model by combining the input of the hot word audio sequence and the text. At the same time, this solution only needs to use artificial recording or a TTS model to synthesize the hot word audio, and can achieve the rapid iterative update of hot words in actual production use.

[0103] The embodiment of the present application also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned vocabulary recognition method based on speech model. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0104] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes: The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the vocabulary recognition method based on the speech model in the embodiments of this application; Input / output interface 903, used to implement information input and output; Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.); A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904); The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0105] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned vocabulary recognition method based on the speech model is implemented.

[0106] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0107] The speech model-based vocabulary recognition method, device, electronic device and storage medium provided in the embodiments of the present application first obtain the audio to be recognized and the target audio, and the target audio includes at least one target hot word audio, that is, the audio corresponding to the hot word that needs to be recognized, and then perform text conversion on the audio to be recognized and the target audio to obtain the audio text corresponding to the audio to be recognized and the hot word text corresponding to the target hot word audio, so as to realize the textual display of the audio to be recognized and the target hot word audio, thereby improving the accuracy of information recognition, and then obtain the prefix sequence of the speech model to facilitate the subsequent decoding of the audio by the speech model, and input the audio to be recognized and the target audio into the speech model for feature splicing, and output the spliced ​​feature sequence, so as to improve the recognition accuracy of the speech and eliminate irrelevant or redundant Features, reduce the complexity of the model, avoid the risk of overfitting, add the target hot word audio to the splicing feature sequence to obtain the target audio sequence, and add the hot word text to the prefix sequence to obtain the target prefix sequence, so that the target audio sequence and the target prefix sequence can be combined with the hot word and the hot word text corresponding to the hot word, and the hot word prefix is ​​added, and then the target audio sequence and the target prefix sequence are input into the speech model, so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, outputs the recognized hot word audio, and realizes accurate recognition of the audio corresponding to the hot word, improves the recognition accuracy of the hot word audio, and finally, the audio to be recognized and the recognized hot word audio are converted into text to obtain the target audio text, thereby improving the recognition accuracy of the hot words in the target audio text. The embodiment of the present application utilizes the contextual reasoning ability and autoregressive generation mechanism in the speech model, adds the target hot word audio to the splicing feature sequence during the model processing, and adds the hot word text to the prefix sequence to increase the hot word prefix, so that the hot word recognition accuracy of the speech model can be improved by combining the input hot word audio sequence with the text, and the accurate recognition of the hot word can be realized.

[0108] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0109] It can be understood by those skilled in the art that Figure 1-7 The technical solutions shown in the figure do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figure, or a combination of certain steps, or different steps.

[0110] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0112] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0113] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0114] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0115] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0117] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0118] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A vocabulary recognition method based on a speech model, characterized in that: The method comprises: Acquire the audio to be recognized and the target audio, wherein the target audio includes at least one target hot word audio; Performing text conversion on the target audio to obtain a hot word text corresponding to the target hot word audio; Obtaining a prefix sequence of the speech model, and inputting the audio to be recognized and the target audio into the speech model for feature splicing, and outputting a spliced ​​feature sequence; Add the target hot word audio to the concatenated feature sequence to obtain a target audio sequence, and add the hot word text to the prefix sequence to obtain a target prefix sequence; Input the target audio sequence and the target prefix sequence into the speech model, so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, and outputs the recognized hot word audio; The audio to be recognized and the recognized hot word audio are converted into text to obtain a target audio text.

2. The method for vocabulary recognition based on speech model according to claim 1, characterized in that: The target audio is obtained by the following steps: Obtaining artificial audio and target hot word vocabulary, and counting the number of vocabulary of the target hot word vocabulary, wherein the artificial audio is obtained by artificial recording; Performing audio quality analysis on the artificial audio to obtain an audio quality score, wherein the audio quality score is used to characterize the sound quality and fluency of the artificial audio; When the number of the vocabulary is less than a preset number and the audio quality score is greater than or equal to a first preset score, taking the artificial audio as the target audio; When the number of words is greater than or equal to a preset number or the audio quality score is less than a first preset score, audio synthesis is performed on the target hot word vocabulary through a preset deep learning model to obtain the target audio.

3. The method for vocabulary recognition based on speech model according to claim 2, characterized in that: The performing audio quality analysis on the artificial audio to obtain an audio quality score includes: Performing time-frequency transformation on the artificial audio, and extracting features from the artificial audio after the time domain transformation to obtain artificial audio features; Performing sound quality detection on the artificial audio based on the artificial audio feature; When the artificial audio has noise, determining a second preset score as the audio quality score, wherein the second preset score is less than the first preset score; When there is no noise in the artificial audio, the clarity of the artificial audio is detected based on the artificial audio features to obtain an audio quality score.

4. The method for vocabulary recognition based on speech model according to claim 2, characterized in that: The method of synthesizing the target hot word vocabulary through a preset deep learning model to obtain the target audio includes: Inputting the target hot word vocabulary into a preset deep learning model, so that the deep learning model performs phoneme analysis on the target hot word vocabulary and outputs a spectrogram; Performing audio conversion on the spectrogram through a preset vocoder to obtain an audio waveform; Generate target audio according to the audio waveform.

5. The method for vocabulary recognition based on speech model according to claim 1, characterized in that: The step of converting the target audio into text to obtain a hot word text corresponding to the target hot word audio includes: Extracting features of the target audio to obtain target audio features corresponding to the target audio; Performing feature mapping on the target audio feature through a preset acoustic model to obtain a target candidate sequence of the target audio feature; Inputting the target candidate sequence into a preset language model, so that the language model analyzes the contextual relationship of the target audio based on the target candidate sequence and outputs a target text sequence; The target text sequence is decoded to obtain a hot word text corresponding to the target hot word audio.

6. The method for vocabulary recognition based on speech model according to claim 1, characterized in that: The step of inputting the audio to be recognized and the target audio into a speech model for feature splicing and outputting a spliced ​​feature sequence comprises: Extracting a first concatenated feature sequence of the audio to be recognized and a second concatenated feature sequence of the target audio through the speech model; Feature splicing is performed on the first splicing feature sequence and the second splicing feature sequence to obtain a splicing feature sequence.

7. The method for vocabulary recognition based on speech model according to claim 1, characterized in that: The step of inputting the to-be-recognized audio and the target audio into a speech model for feature splicing and outputting a spliced ​​feature sequence further includes: Performing audio splicing on the audio to be recognized and the target audio to obtain a spliced ​​audio; The audio feature sequence of the concatenated audio is extracted through the speech model.

8. A vocabulary recognition device based on a speech model, characterized in that: The device comprises: An audio acquisition module, used to acquire the audio to be recognized and the target audio, wherein the target audio includes at least one target hot word audio; A text conversion module, used for performing text conversion on the target audio to obtain a hot word text corresponding to the target hot word audio; A feature splicing module, used to obtain a prefix sequence of the speech model, input the audio to be recognized and the target audio into the speech model for feature splicing, and output a spliced ​​feature sequence; A sequence splicing module, used for adding the target hot word audio to the splicing feature sequence to obtain a target audio sequence, and adding the hot word text to the prefix sequence to obtain a target prefix sequence; A hot word recognition module, used for inputting the target audio sequence and the target prefix sequence into the speech model, so that the speech model performs hot word recognition on the audio to be recognized based on the target audio sequence and the target prefix sequence, and outputs the recognized hot word audio; The target conversion module is used to perform text conversion on the audio to be recognized and the recognized hot word audio to obtain a target audio text.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the speech model-based vocabulary recognition method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the speech model-based vocabulary recognition method according to any one of claims 1 to 7 is implemented.

Images