Abstract: A discourse-level text translation method and device, the method comprising: acquiring a text to be translated, the text to be translated being a unit text in a discourse-level text to be translated (S101); acquiring an associated text of the text to be translated, the associated text including at least one of a preceding source text, a following source text, and a preceding target text (S102); and translating, according to the associated text, the text to be translated (S103).

Abstract: A speech recognition method and related products are provided. The method includes acquiring a to-be-recognized speech and a configured hot word library; determining, based on the to-be-recognized speech and the hot word library, an audio-related feature used at a current decoding time instant; determining, based on the audio-related feature, a hot word-related feature used at the current decoding time instant from the hot word library; and determining, based on the audio-related feature and the hot word-related feature, a recognition result of the to-be-recognized speech at the current decoding time instant.

Abstract: A method and a system for end-to-end modeling are provided. The method includes: determining a topological structure of a target-based end-to-end model, where the topological structure includes an input layer, an encoding layer, an code enhancement layer, a filtering layer, a decoding layer and an output layer; the code enhancement layer adds information of a target unit to a feature sequence outputted by the encoding layer, the filtering layer filters a feature sequence added with the information of the target unit; collecting multiple pieces of training data; and training parameters of the target-based end-to-end model by using the multiple pieces of the training data.

Abstract: A speech recognition method and related products are provided. The method includes acquiring text contents and text-associated time information transmitted by a plurality of terminals in a preset scenario and determining a shared text for the preset scenario based on the text contents and the text-associated time information, obtaining a customized language model for the preset scenario based on the shared text, and performing speech recognition for the preset scenario with the customized language model. The method provides improved speech recognition for the preset scenario due to the correlation between the customized language model and the preset scenario.

Abstract: A speech recognition error correction method and device, and a readable storage medium are provided. The method includes: acquiring to-be-recognized speech data and a first recognition result of the speech data, re-recognizing the speech data with reference to context information in the first recognition result to obtain a second recognition result, and determining a final recognition result based on the second recognition result. In the method, the speech data is re-recognized with reference to context information in the first recognition result, which fully considers context information in the recognition result and the application scenario of the speech data. If any error occurs in the first recognition result, the first recognition result is corrected based on the second recognition. Therefore, the accuracy of speech recognition can be improved.

Abstract: A method for constructing a decoding network, a speech recognition method, a device, an apparatus, and a storage medium are provided. The method for constructing a decoding network includes: acquiring a general language model, a domain language model, and a general decoding network generated based on the general language model; generating a domain decoding network based on the domain language model and the general language model; and integrating the domain decoding network with the general decoding network to obtain a target decoding network. The speech recognition method includes: decoding to-be-recognized speech data by using a target decoding network to obtain a decoding path for the to-be-recognized speech data; and determining a speech recognition result for the to-be-recognized speech data based on the decoding path for the to-be-recognized speech data.

Abstract: A method, an apparatus and a device for converting a whispered speech, and a readable storage medium are provided. The method is implemented based on the whispered speech converting model. The whispered speech converting model is trained in advance by using recognition results and whispered speech training acoustic features of whispered speech training data as samples and using normal speech acoustic features of normal speech data parallel to the whispered speech training data as sample labels. A whispered speech acoustic feature and a preliminary recognition result of whispered speech data are acquired, then the whispered speech acoustic feature and the preliminary recognition result are inputted into a preset whispered speech converting model to acquire a normal speech acoustic feature outputted by the model. In this way, the whispered speech can be converted to a normal speech.

Abstract: A target voice detection method and a target voice detection apparatus are provided. The method includes: receiving sound signals collected by a microphone array; performing a beamforming process on the sound signals to obtain beams in different directions; extracting a detection feature of each frame based on the sound signals and the beams in different directions; inputting an extracted detection feature of a current frame into a pre-constructed target voice detection model to obtain a model output result; and obtaining a target voice detection result of the current frame based on the model output result.

Abstract: A microphone array-based target voice acquisition method and device, said method comprising: receiving voice signals acquired on the basis of a microphone array (101); determining a pre-selected target voice signal and a direction thereof (102); performing strong directional gain and weak directional gain on the pre-selected target voice signal, so as to obtain a strong gain signal and a weak gain signal (103); performing an endpoint detection on the basis of the strong gain signal, so as to obtain an endpoint detection result (104); and performing endpoint processing on the weak gain signal according to the endpoint detection result, so as to obtain a final target voice signal (105). The present invention can obtain an accurate and reliable target voice signal, thereby avoiding an adverse effect of the target voice quality on subsequent target voice processing.

Abstract: Provided are a voice denoising method and apparatus, a server and a storage medium. The voice denoising method comprises: acquiring voice signals synchronously collected by an acoustic microphone and a non-acoustic microphone (S100); carrying out voice activity detection according to the voice signal collected by the non-acoustic microphone to obtain a voice activity detection result (S110); and according to the voice activity detection result, denoising the voice signal collected by the acoustic microphone to obtain a denoised voice signal (S120). The effect of denoising can be enhanced, and the quality of voice signals can be improved.

Abstract: A discourse-level text translation method and device, the method comprising: acquiring a text to be translated, the text to be translated being a unit text in a discourse-level text to be translated (S101); acquiring an associated text of the text to be translated, the associated text including at least one of a preceding source text, a following source text, and a preceding target text (S102); and translating, according to the associated text, the text to be translated (S103).

Abstract: A method, a device and a storage medium for evaluating speech quality include: receiving speech data to be evaluated; extracting evaluation features of the speech data to be evaluated; performing quality evaluation to the speech data to be evaluated according to the evaluation features of the speech data to be evaluated and a predetermined speech quality evaluation model, in which the speech quality evaluation model is an indication of a relationship between evaluation features of single-ended speech data and quality information of the single-ended speech data.

Abstract: A method for recognizing a character includes: obtaining a character; converting the character into a radical based character recognition result, where the radical based character recognition result comprises symbols indicating radicals of the character and a structure of the radicals of the character; and recognizing the character based on the radical based character recognition result.

Abstract: An echo cancellation method based on delay estimation is provided. In the method, a microphone signal and a reference signal are received and preprocessed. In the preprocessed microphone signal and the preprocessed reference signal, frequency point signals with non-linearity in a current echo cancellation scenario are determined. A current delay estimation value is calculated based on frequency point signals without non-linearity in the microphone signal and the reference signal. The reference signal is shifted based on the current delay estimation value. An adaptive filter is updated based on the preprocessed microphone signal and the shifted reference signal, to perform echo cancellation.

Abstract: Provided are a voice denoising method and apparatus, a server and a storage medium. The voice denoising method comprises: acquiring voice signals synchronously collected by an acoustic microphone and a non-acoustic microphone (S100); carrying out voice activity detection according to the voice signal collected by the non-acoustic microphone to obtain a voice activity detection result (S110); and according to the voice activity detection result, denoising the voice signal collected by the acoustic microphone to obtain a denoised voice signal (S120). The effect of denoising can be enhanced, and the quality of voice signals can be improved.

Abstract: A target voice detection method and a target voice detection apparatus are provided. The method includes: receiving sound signals collected by a microphone array; performing a beamforming process on the sound signals to obtain beams in different directions; extracting a detection feature of each frame based on the sound signals and the beams in different directions; inputting an extracted detection feature of a current frame into a pre-constructed target voice detection model to obtain a model output result; and obtaining a target voice detection result of the current frame based on the model output result.

Abstract: A microphone array-based target voice acquisition method and device, said method comprising: receiving voice signals acquired on the basis of a microphone array (101); determining a pre-selected target voice signal and a direction thereof (102); performing strong directional gain and weak directional gain on the pre-selected target voice signal, so as to obtain a strong gain signal and a weak gain signal (103); performing an endpoint detection on the basis of the strong gain signal, so as to obtain an endpoint detection result (104); and performing endpoint processing on the weak gain signal according to the endpoint detection result, so as to obtain a final target voice signal (105). The present invention can obtain an accurate and reliable target voice signal, thereby avoiding an adverse effect of the target voice quality on subsequent target voice processing.

Abstract: A method, an apparatus and a device for converting a whispered speech, and a readable storage medium are provided. The method is implemented based on the whispered speech converting model. The whispered speech converting model is trained in advance by using recognition results and whispered speech training acoustic features of whispered speech training data as samples and using normal speech acoustic features of normal speech data parallel to the whispered speech training data as sample labels. A whispered speech acoustic feature and a preliminary recognition result of whispered speech data are acquired, then the whispered speech acoustic feature and the preliminary recognition result are inputted into a preset whispered speech converting model to acquire a normal speech acoustic feature outputted by the model. In this way, the whispered speech can be converted to a normal speech.

Abstract: A method for recognizing a character includes: obtaining a character; converting the character into a radical based character recognition result, where the radical based character recognition result comprises symbols indicating radicals of the character and a structure of the radicals of the character; and recognizing the character based on the radical based character recognition result.

Abstract: A method and a system for end-to-end modeling are provided. The method includes: determining a topological structure of a target-based end-to-end model, where the topological structure includes an input layer, an encoding layer, an code enhancement layer, a filtering layer, a decoding layer and an output layer; the code enhancement layer adds information of a target unit to a feature sequence outputted by the encoding layer, the filtering layer filters a feature sequence added with the information of the target unit collecting multiple pieces of training data; and training parameters of the target-based end-to-end model by using the multiple pieces of the training data.