Tencent Technology (shenzhen) Company Limited

Tencent Technology Company Limited

Shuai Yue

Xiang Zhang

Li Hui Lu

Bo Song Chen

Feng Rao

Eryu Wang

Haibo Liu

Lou Li

Lu Li

Duling Lu

Jian Hua Liu

Dadong Xie

Jianxiong Ma

Linghui Kong

Bo Chen

Song Liu

Tong Cheng

Qiuge Liu

Qiang Cheng

Zongyao Tang

Lu Ll

A method is performed at a computer for automatically correcting typographical errors. The computer selects a target word in a target sentence and identifies a target word therein as having a typographical error and first and second sequences of words separated by the target word as context. After identifying, among a database of grammatically correct sentences, a set of sentences having the first and second sequences of words, each sentence including a replacement word, the computer selects a set of candidate grammatically correct sentences whose corresponding replacement words have similarities to the target word above a pre-set threshold, Finally, the computer chooses, among the set of candidate grammatically correct sentences, a fittest grammatically correct sentence according to a linguistic model and replaces the target word in the target sentence with the replacement word within the fittest grammatically correct sentence.

Model-based automatic correction of typographical errors

The present application discloses a method, an electronic system and a non-transitory computer readable storage medium for recognizing audio commands in an electronic device. The electronic device obtains audio data based on an audio signal provided by a user and extracts characteristic audio fingerprint features from the audio data. The electronic device further determines whether the corresponding audio signal is generated by an authorized user by comparing the characteristic audio fingerprint features with an audio fingerprint model for the authorized user and with a universal background model that represents user-independent audio fingerprint features, respectively. When the corresponding audio signal is generated by the authorized user of the electronic device, an audio command is extracted from the audio data, and an operation is performed according to the audio command.

Systems and methods for audio command recognition with speaker authentication

A method is performed at a device having one or more processors and memory. The device establishes a first-level Deep Neural Network (DNN) model based on unlabeled speech data, the unlabeled speech data containing no speaker labels and the first-level DNN model specifying a plurality of basic voiceprint features for the unlabeled speech data. The device establishes a second-level DNN model by tuning the first-level DNN model based on labeled speech data, the labeled speech data containing speech samples with respective speaker labels, wherein the second-level DNN model specifies a plurality of high-level voiceprint features. Using the second-level DNN model, registers a first high-level voiceprint feature sequence for a user based on a registration speech sample received from the user. The device performs speaker verification for the user based on the first high-level voiceprint feature sequence registered for the user.

Method and device for voiceprint recognition

A method of processing information content based on a Chinese language model is performed at a computer, the method including: identifying a plurality of expressions in the information content extracted from a speech input through speech recognition that is queued to be processed; dividing the expressions into a plurality of characteristic units according to semantic features and predetermined characteristics associated with each characteristic unit, each including a subset of the expressions and the predetermined characteristics at least including a respective integer number of expressions that are included in the characteristic unit; extracting, from the Chinese language model, a plurality of probabilities for punctuation marks associated with each characteristic unit; and in accordance with the probabilities, associating a respective punctuation mark with each characteristic unit included in the information content. The method further comprises adding punctuation marks based on a weight determined for each punctuation mark.

Method and system of adding punctuation and establishing language model using a punctuation weighting applied to chinese speech recognized text

A method of recognizing speech commands includes generating a background acoustic model for a sound using a first sound sample, the background acoustic model characterized by a first precision metric. A foreground acoustic model is generated for the sound using a second sound sample, the foreground acoustic model characterized by a second precision metric. A third sound sample is received and decoded by assigning a weight to the third sound sample corresponding to a probability that the sound sample originated in a foreground using the foreground acoustic model and the background acoustic model. The method further includes determining if the weight meets predefined criteria for assigning the third sound sample to the foreground and, when the weight meets the predefined criteria, interpreting the third sound sample as a portion of a speech command. Otherwise, recognition of the third sound sample as a portion of a speech command is forgone.

Method and system for recognizing speech commands using background and foreground acoustic models

Systems and methods are provided for adding punctuations. For example, one or more first feature units are identified in a voice file taken as a whole; the voice file is divided into multiple segments by detecting silences in the voice file; one or more second feature units are identified in the voice file; a first aggregate weight of first punctuation states of the voice file and a second aggregate weight of second punctuation states of the voice file are determined, using a language model established based on word separation and third semantic features; a weighted calculation is performed to generate a third aggregate weight based on a linear combination associated with the first aggregate weight and the second aggregate weight; and one or more final punctuations are added to the voice file based on at least information associated with the third aggregate weight.

Systems and methods for adding punctuations by detecting silences in a voice using plurality of aggregate weights which obey a linear relationship

The present invention, pertaining to the field of speech recognition, discloses a reminder setting method and apparatus. The method includes: acquiring speech signals; acquiring time information in speech signals by using keyword recognition, and determining reminder time for reminder setting according to the time information; acquiring text sequence corresponding to the speech signals by using continuous speech recognition, and determining reminder content for reminder setting according to the time information and the text sequence; and setting a reminder according to the reminder time and the reminder content. According to the present invention, acquiring time information in speech signals by using keyword recognition ensures correctness of time information extraction, and achieves an effect that correct time information is still acquired by keyword recognition to set a reminder even in the case that a recognized text sequence is incorrect due to poor precision in whole text recognition in the speech recognition.

Reminder setting method and apparatus

An automatic speech recognition method includes at a computer having one or more processors and memory for storing one or more programs to be executed by the processors, obtaining a plurality of speech corpus categories through classifying and calculating raw speech corpus; obtaining a plurality of classified language models that respectively correspond to the plurality of speech corpus categories through a language model training applied on each speech corpus category; obtaining an interpolation language model through implementing a weighted interpolation on each classified language model and merging the interpolated plurality of classified language models; constructing a decoding resource in accordance with an acoustic model and the interpolation language model; and decoding input speech using the decoding resource, and outputting a character string with a highest probability as a recognition result of the input speech.

Method and system for building a topic specific language model for use in automatic speech recognition

Systems and methods are provided for speech recognition. For example, audio characteristics are extracted from acquired voice signals; a syllable confusion network is identified based on at least information associated with the audio characteristics; a word lattice is generated based on at least information associated with the syllable confusion network and a predetermined phonetic dictionary; and an optimal character sequence is calculated in the word lattice as a speech recognition result.

Systems and methods for speech recognition

A method and a device for training a DNN model includes: at a device including one or more processors and memory: establishing an initial DNN model; dividing a training data corpus into a plurality of disjoint data subsets; for each of the plurality of disjoint data subsets, providing the data subset to a respective training processing unit of a plurality of training processing units operating in parallel, wherein the respective training processing unit applies a Stochastic Gradient Descent (SGD) process to update the initial DNN model to generate a respective DNN sub-model based on the data subset; and merging the respective DNN sub-models generated by the plurality of training processing units to obtain an intermediate DNN model, wherein the intermediate DNN model is established as either the initial DNN model for a next training iteration or a final DNN model in accordance with a preset convergence condition.

Method and device for parallel processing in model training

A method and device for voiceprint recognition, include: establishing a first-level Deep Neural Network (DNN) model based on unlabeled speech data, the unlabeled speech data containing no speaker labels and the first-level DNN model specifying a plurality of basic voiceprint features for the unlabeled speech data; obtaining a plurality of high-level voiceprint features by tuning the first-level DNN model based on labeled speech data, the labeled speech data containing speech samples with respective speaker labels, and the tuning producing a second-level DNN model specifying the plurality of high-level voiceprint features; based on the second-level DNN model, registering a respective high-level voiceprint feature sequence for a user based on a registration speech sample received from the user; and performing speaker verification for the user based on the respective high-level voiceprint feature sequence registered for the user.

A method of recognizing speech is provided that includes generating a decoding network that includes a primary sub-network and a classification sub-network. The primary sub-network includes a classification node corresponding to the classification sub-network. The classification sub-network corresponds to a group of uncommon words. A speech input is received and decoded by instantiating a token in the primary sub-network and passing the token through the primary network. When the token reaches the classification node, the method includes transferring the token to the classification sub-network and passing the token through the classification sub-network. When the token reaches an accept node of the classification sub-network, the method includes returning a result of the token passing through the classification sub-network to the primary sub-network. The result includes one or more words in the group of uncommon words. A string corresponding to the speech input is output that includes the one or more words.

Method and system for automatic speech recognition

An electronic device with one or more processors and memory trains an acoustic model with an international phonetic alphabet (IPA) phoneme mapping collection and audio samples in different languages, where the acoustic model includes: a foreground model; and a background model. The device generates a phone decoder based on the trained acoustic model. The device collects keyword audio samples, decodes the keyword audio samples with the phone decoder to generate phoneme sequence candidates, and selects a keyword phoneme sequence from the phoneme sequence candidates. After obtaining the keyword phoneme sequence, the device detects one or more keywords in an input audio signal with the trained acoustic model, including: matching phonemic keyword portions of the input audio signal with phonemes in the keyword phoneme sequence with the foreground model; and filtering out phonemic non-keyword portions of the input audio signal with the background model.

Keyword detection with international phonetic alphabet by foreground model and background model

A method and system for adding punctuation to a voice file is disclosed. The method includes: utilizing silence or pause duration detection to divide a voice file into a plurality of speech segments for processing, the voice file includes a plurality of features units; identifying all features units that appear in the voice file according to every term or expression and semantics features of the every term or expression that form each of the plurality of speech segments; using a linguistic model to determine a sum of weight of various punctuation modes in the voice file according to all the feature units, the linguistic model is built upon semantics features of various parsed out terms or expressions from a body text of a spoken sentence according to a language library; and adding punctuations to the voice file based on the determined sum of weight of the various punctuation modes.

Method and system for adding punctuation to voice files

A method includes: acquiring data samples; performing categorized sentence mining in the acquired data samples to obtain categorized training samples for multiple categories; building a text classifier based on the categorized training samples; classifying the data samples using the text classifier to obtain a class vocabulary and a corpus for each category; mining the corpus for each category according to the class vocabulary for the category to obtain a respective set of high-frequency language templates; training on the templates for each category to obtain a template-based language model for the category; training on the corpus for each category to obtain a class-based language model for the category; training on the class vocabulary for each category to obtain a lexicon-based language model for the category; building a speech decoder according to an acoustic model, the class-based language model and the lexicon-based language model for any given field, and the data samples.

Growing community of inventors

Shenzhen, China

Shuai Yue