Baidu Online Network Technology (Beijing) Co., Ltd.

Xiangang Li

Chao Li

Bing Jiang

Jue Sun

Wei Zou

Xuewei Zhang

Bin Huang

Jun Huang

Mingming Chen

Xiaokong Ma

Weiwei Cui

Jingyuan Hu

Ke Ding

Yiping Peng

A speech recognition and processing method, a device and a non-volatile computer storage medium are provided. The method comprises: performing training on a pre-set processing model according to speech sample data from all areas of a country to generate a general acoustic model for common speech (S); and performing self-adaptive training on the general acoustic model according to speech sample data of respective province to generate an acoustic model for common speech with dialectal accent corresponding to the respective province (S).

Voice recognition processing method, device and computer storage medium

Disclosed are a speech recognition method, a device and a computer readable storage medium. The speech recognition method comprises: performing acoustic characteristic extraction on an input voice, so as to obtain an acoustic characteristic (S); acquiring an acoustic model, a parameter of the acoustic model being a binarization parameter (S); and according to the acoustic characteristic and the acoustic model, performing speech recognition (S).

Voice recognition method, device and computer storage medium

A method and apparatus of training an acoustic feature extracting model, a device and a computer storage medium. The method comprises: considering a first acoustic feature extracted respectively from speech data corresponding to user identifiers as training data; training an initial model based on a deep neural network based on a criterion of a minimum classification error, until a preset first stop condition is reached; using a triplet loss layer to replace a Softmax layer in the initial model to constitute an acoustic feature extracting model, and continuing to train the acoustic feature extracting model until a preset second stop condition is reached, the acoustic feature extracting model being used to output a second acoustic feature of the speech data; wherein the triplet loss layer is used to maximize similarity between the second acoustic features of the same user, and minimize similarity between the second acoustic features of different users.

Method and apparatus of training acoustic feature extracting model, device and computer storage medium

Embodiments of the present disclosure provide a speech noise reduction method and a speech noise reduction device based on artificial intelligence and a computer device. The method includes the followings. A first noisy speech to be processed is received. The first noisy speech to be processed is pre-processed, to obtain the first noisy speech in a preset format. The first noisy speech in the preset format is sampled according to a sampling rate indicated by the preset format, to obtain first sampling point information of the first noisy speech. A noise reduction is performed on the first sampling point information through a deep-learning noise reduction model, to generate noise-reduced first sampling point information. A first clean speech is generated according to the noise-reduced first sampling point information.

Speech noise reduction method and device based on artificial intelligence and computer device

Embodiments of the present disclosure disclose a method and apparatus for switching multiple speech recognition models. The method includes: acquiring at least one piece of speech information in user input speech; recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree; and switching a currently used speech recognition model to a speech recognition model corresponding to the target linguistic category. The embodiments of the present disclosure determine the corresponding target linguistic category based on the matching degree by recognizing the speech information and matching the linguistic category for the speech information, and switch the currently used speech recognition model to the speech recognition model corresponding to the target linguistic category.

Multiple voice recognition model switching method and apparatus, and storage medium

An artificial intelligence-based cross-language speech transcription method and apparatus, a device and a readable medium. The method includes pre-processing to-be-transcribed speech data to obtain multiple acoustic features, the to-be-transcribed speech data being represented in a first language; predicting a corresponding translation text after transcription of the speech data according to the multiple acoustic features and a pre-trained cross-language transcription model; wherein the translation text is represented in a second language which is different from the first language. According to the technical solution, it is unnecessary, upon cross-language speech transcription, to perform speech recognition first and then perform machine translation, but to directly perform cross-language transcription according to the pre-trained cross-language transcription model. The technical solution can overcome the problem of error accumulation in the two-step cross-language transcription manner in the prior art, and can effectively improve accuracy and efficiency of the cross-language speech transcription as compared with the prior art.

Artificial intelligence-based cross-language speech transcription method and apparatus, device and readable medium using Fbank40 acoustic feature format

A speaker adaption method and a speaker adaption apparatus, a device and a storage medium are provided. The method includes: acquiring first speech data of a target speaker; inputting the first speech data to a pre-trained batch normalization (BN) network to be subjected to an adaptive training to acquire a speech recognition model including a speech parameter of the target speaker.

Speaker adaption method and apparatus, and storage medium

The present disclosure provides a method and a device for extracting an acoustic feature based on a convolution neural network and a terminal device. The method includes: arranging speech to be recognized into a speech spectrogram with a predetermined dimension number; and recognizing the speech spectrogram with the predetermined dimension number by the convolution neural network to obtain the acoustic feature of the speech to be recognized.

Method and device extracting acoustic feature based on convolution neural network and terminal device

Embodiments of the present disclosure provide a method and a device for extracting a speech feature based on artificial intelligence. The method includes performing a spectrum analysis on a speech to be recognized, to obtain a spectrum program of the speech; and extracting features of the spectrum program by using an Inception convolution structure of an image recognition algorithm, to obtain the speech feature of the speech. In embodiments, by performing the spectrum analysis on the speech to be recognized, the consecutive speech to be recognized is converted into the spectrum diagram. As the Inception convolution structure is an effective image recognition manner being able to accurately recognize features of an image, the spectrum program is recognized with the Inception convolution structure to extract the relative accurate speech feature from the speech to be recognized. Thus, the accuracy rate of the speech recognition is improved.

Method and device for extracting speech feature based on artificial intelligence

Embodiments of the present disclosure provide a method and a device for recognizing a speech based on a Chinese-English mixed dictionary. The method includes acquiring a Chinese-English mixed dictionary marked by an international phonetic alphabet, in which, the Chinese-English mixed dictionary includes a Chinese dictionary and an English dictionary revised by Chinglish; by taking the Chinese-English mixed dictionary as a training dictionary, taking a one-layer Convolutional Neural Network and a five-layer Long Short-Term Memory as a model, taking syllables or words as a target and taking a connectionist temporal classifier as a training criterion, training the model to obtain a trained CTC acoustic model; and performing a speech recognition on a Chinese-English mixed language based on the trained CTC acoustic model.

Method and device for recognizing speech based on Chinese-English mixed dictionary

Embodiments of the present disclosure provide a method and a device for recognizing a speech based on a Chinese-English mixed dictionary. The method includes acquiring a Chinese-English mixed dictionary marked by an international phonetic alphabet, in which, the Chinese-English mixed dictionary includes a Chinese dictionary and an English dictionary revised by Chinglish; by taking the Chinese-English mixed dictionary as a training dictionary, taking a one-layer Convolutional Neural Network and a five-layer Long Short-Term Memory as a model, taking a state of the IPA as a target and taking a connectionist temporal classifier as a training criterion, training the model to obtain a trained CTC acoustic model; and performing a speech recognition on a Chinese-English mixed language based on the trained CTC acoustic model.

Embodiments of the present disclosure provide a speech recognition method based on artificial intelligence, and a terminal. The method includes obtaining speech data to be recognized; performing a processing on the speech data to be recognized using a trained sub-band energy normalized acoustic model, to determine an normalized energy feature corresponding to each time-frequency unit in the speech data to be recognized; and determining text data corresponding to the speech data to be recognized according to the normalized energy feature corresponding to each time-frequency unit.

Speech recognition method based on artificial intelligence and terminal

Embodiments of the present disclosure provide a method and a device for training an acoustic model, a computer device and a storage medium. The method includes obtaining supervised speech data and unsupervised speech data, in which, the supervised speech data is speech data with manual annotation and the unsupervised speech data is speech data with machine annotation; extracting speech features from the supervised speech data and the unsupervised speech data; and performing a multi-task learning having a supervised learning task and an unsupervised learning task on the speech features of the supervised speech data and the unsupervised speech data by using a deep learning network, to train and obtain the acoustic model.

Method and device for training acoustic model, computer device and storage medium

A method and apparatus of building an acoustic feature extracting model, and an acoustic feature extracting method and apparatus. The method of building an acoustic feature extracting model comprises: considering first acoustic features extracted respectively from speech data corresponding to user identifiers as training data; using the training data to train a deep neural network to obtain an acoustic feature extracting model; wherein a target of training the deep neural network is to maximize similarity between the same user's second acoustic features and minimize similarity between different users' second acoustic features. The acoustic feature extracting model according to the present disclosure can self-learn optimal acoustic features that achieves a training target. As compared with a conventional acoustic feature extracting manner with a preset feature type and transformation manner, the acoustic feature extracting manner of the present disclosure achieves better flexibility and higher accuracy.

Method and apparatus of building acoustic feature extracting model, and acoustic feature extracting method and apparatus

Embodiments of the present disclosure provide a method and a device for waking up via a speech based on AI and a computer device. The method includes the followings. A windowing and framing operation is performed on an online recorded speech, to obtain at least one speech frame. A feature extraction is performed on the at least one speech frame, to obtain speech features. A calculation is performed on a static speech feature contained in the at least one speech frame through a speech wake-up model based on convolutional neural network, to obtain a first posteriori probability matched with a category of non-wake-up words and a second posteriori probability matched with a category of wake-up words. It is determined that a wake-up word is contained in the online recorded speech, when the second posteriori probability is greater than or equal to a preset threshold.

Growing community of inventors

Beijing, China

Xiangang Li