322 results about "Voice search" patented technology

Disclosed is a speech search device including a recognizer 2 that refers to an acoustic model and language models having different learning data and performs voice recognition on an input speech, to acquire a recognized character string for each language model, a character string comparator 6 that compares the recognized character string for each language models with the character strings of search target words stored in a character string dictionary, and calculates a character string matching score showing the degree of matching of the recognized character string with respect to each of the character strings of the search target words, to acquire both a character string having the highest character string matching score and this character string matching score for each recognized character strings, and a search result determinator 8 that refers to the acquired score and outputs one or more search target words in descending order of the scores.

A method implemented on a mobile device that includes speech recognition functionality involves presenting to a user of the mobile device a voice-control interface that supports two types of commands at a common level of the interface, the two types of commands including a first type and a second type, the first type being command and control commands and the second type being search request commands. The method further involves: receiving an utterance from the user that corresponds to a command of either of the first type or the second type; recognizing the utterance; if the received utterance is a command of the first type, performing a corresponding command and control function; and if the received utterance is a command of the second type, generating a representation of a corresponding search request and then using the representation to request a search that is responsive to the search request.

Methods and devices for providing a user of a mobile communications device with mobile voice-mediated search capability. The methods and devices involve receiving an utterance from a user of the mobile device, the utterance including a search request; using the speech recognition functionality to recognize that the utterance includes a search request; as a result of recognizing that the utterance includes a search request, establishing a wireless data connection to a remote server; sending a representation of the search request to the remote server over the wireless data connection; receiving search results that are responsive to the search request; and presenting the search results on the mobile device.

The invention provides a method and device for carrying out error correction on texts after speech recognition. The method for carrying out error correction on texts after speech recognition comprises the following steps of: preprocessing a text after speech recognition; recognizing a search intention of the preprocessed text; determining to-be-extracted attribute information according to the recognized search intention and extracting attribute information from the preprocessed text; and calculating the similarity between the attribute information and any candidate word in a candidate lexicon, and carrying out error correction on the extracted attribute information according to the similarity. Through the method and device, the free man-machine interaction is realized, the problem that the speech recognition is incorrect in speech search is effectively solved, the speech recognition correctness is improved, the enterprise search demands are satisfied and the user experience is enhanced.

Embodiments of the invention provide a voice search method and device and electronic equipment, and relates to the technical field of audio processing. The method comprises the following steps of: receiving a to-be-identified voice; carrying out intention identification on the to-be-identified voice so as to obtain a search intention of a target user that issues the to-be-identified voice; obtaining a vocal print feature of the to-be-identified voice and taking the vocal print feature as a to-be-identified vocal print feature; identifying the target user through the to-be-identified vocal print feature; and carrying out search on the basis of the target user by utilizing the search intention so as to obtain a search result. By using the method provided by the embodiments to carry out voice search, the correctness of voice search results can be improved.

A system and method for providing automatic voice recognition and voice response product location information in a store while using a personal mobile phone or any phone connected to a telecommunications or data communications network such as and including the Internet and an automatic speech recognition system. The system 403&404 asks a user and / or customer 300 a series of automated questions to help the user and / or customer 300 locate products in stores. In the embodiment of the invention, the user and / or customer 300 only needs to dial the toll free or dial in number 302 from any phone to use the system in order to receive the requested product location information or other available information by the automated response system. This invention creates the product location assistance (PLA) system to be used in locating products in stores, creating new efficiencies in customer service for retailers, businesses and organizations.

The invention discloses a method and device for achieving voice search. The method comprises the steps that a voice signal input by a voice search user is acquired; the voice signal is sent to a voice conversion server; corresponding character information returned after the voice signal is recognized by the voice conversion server is received; the character information is adopted as a search term, and a search request is sent to a search server; a search result returned by the search server is received and displayed in a loaded mode. According to the technical scheme, through interaction with the voice conversion server and interaction with the search server, the process that the character information corresponding to the voice signal input by the user is searched for, and the search result is shown to the user is completed, a complete and effective voice search scheme is formed, and compared with traditional manual character search, the operation process is simplified, search efficiency is improved, and more convenient and perfect experience is provided for the user.

The invention provides a voice search method, a voice search device and a voice search system. The voice search method comprises the following steps: receiving a voice search request from a user; performing intent resolution on the voice search request so as to acquire the search intent of the user; acquiring a search result according to the search intent of the user; generating a voice dialogue result of the voice search request according to the search result and the search intent of the user and supplying the voice dialogue result to the user. According to the voice search method provided by the invention, simple voice broadcast for the search result is not performed, but a dialogue form corresponds to the input voice search request, so that the device and the system are more intelligent. Furthermore, the search intent of the user can be analyzed, the corresponding search result is acquired so as to generate the voice dialogue result, user requirements can be met more accurately, and the result is more accurate, individualized and humanized.

A method, system and communication device for enabling voice-to-voice searching and ordered content retrieval via audio tags assigned to individual content, which tags generate uniterms that are matched against components of a voice query. The method includes storing content and tagging at least one of the content with an audio tag. The method further includes receiving a voice query to retrieve content stored on the device. When the voice query is received, the method completes a voice-to-voice search utilizing uniterms of the audio tag, scored against the phoneme latent lattice model generated by the voice query to identify matching terms within the audio tags and corresponding stored content. The retrieved content(s) associated with the identified audio tags having uniterms that score within the phoneme lattice model are outputted in an order corresponding to an order in which the uniterms are structured within the voice query.

The invention relates to the speech recognition field, in particular to a voice-on-demand method and a device thereof. With a view to facilitating the voice-on-demand of users, a plurality of tags are constructed in the media, each segment is provided with a corresponding key word and search voice information and the key word are compared through recognizing the voice search information of users; if a matching item is found, media content related to the key word is played directly. The method and device of the invention have the advantages of reducing the time needed by users during frame by frame and segment by segment search when playing audio and video files and being capable of reducing network load and the communication expenses of users when applied to communication or the Internet.

A system and associated methods are disclosed for improving voice recognition accuracy when a user conducts a search by voice. One method involves prompting the user to enter a set of characters of the query (e.g., the first N letters of a query term), and then using these letters to execute a preliminary search. The results of the preliminary search are then used to generate a dynamic grammar for interpreting the full voice query. The grammar may alternatively be retrieved from a cache or other memory that stores the grammars for various combinations of letters. In one embodiment, the user enters the characters by selecting the corresponding keys on a standard telephone keypad (one depression per letter) and then saying the letters, and the keypad entries are used to reduce the number of possible interpretations of each character utterance. Another method, which is useful for search refinement, involves generating a dynamic grammar from a set of search results (e.g., when the number of hits is large), and then using this grammar to interpret utterances of additional query terms to be added to the query.

The invention provides a voice search method, which includes the steps: recognizing received voice search messages as text messages, and performing participle processing for the text messages; performing sentence pattern match and semantic analysis for the text messages subjected to participle processing, so as to obtain search engine keywords and search keywords; submitting the search keywords to a search engine corresponding to the search engine keywords for search; and informing a user of a search result received from the search engine. By the aid of the method, one-step search can be realized by the aid of simple voice commands, and search on an electronic commerce website with the search engine can be directly realized without using a specific search engine provided with a service provider.

The invention provides a method for detecting speech endpoints and a system, which relate to the technical field of computers and are used for solving the problem of poor performances of existing speech endpoint detection technology. The method includes A1, searching for various frames in an inputted audio band, and utilizing a characteristic value of a current frame to update a current threshold value if the characteristic value of the current frame is larger than or equal to the current threshold value; A2, judging that a second speech endpoint of the audio band is detected if characteristic values of N continuous frames are smaller than the current threshold value, and stopping a first direction search process; and A3, starting search from the second speech endpoint according to a second-direction sequence, and utilizing the characteristic values of the N continuous frames to detect a first speech endpoint of the audio band. The N is a preset frame number. The system comprises a first forward-direction search and threshold self-adaptive unit, a finishing point position detecting unit and a reverse-direction search and starting point position detecting unit. The method for detecting speech endpoints and the system are applicable to all audio search environments.

An improved method and apparatus is disclosed which uses probabilistic techniques to map an input search string with a prestored audio file, and recognize certain portions of a search string phonetically. An improved interface is disclosed which permits users to input search strings, linguistics, phonetics, or a combination of both, and also allows logic functions to be specified by indicating how far separated specific phonemes are in time.

A method and system for providing social media ecosystem searching services. Cascading searching is used to locate a desired person in a social media ecosystem. Plural related micro-levels are created in cascading searching lists. The plural related micro-levels include one or more cross-connections between the plural cascading merged lists including cross-connections between the search categories, search subcategories or search keywords in the search categories and search subcategories. The cascading searching provides micro-level searching for a desired person in the social media ecosystem at a level not available with other searching techniques. The system includes voice search requests and automatic translation of search requests and communication requests once a desired person is located into plural different languages. The social media search ecosystem cascading searching services are provided on a cloud communications network for mobile and non-mobile devices.

The present invention relates to phonetic self-improving search engines. The search engine may include a phonetic database having a plurality of phonetic equivalent formulas stored therein, each of the phonetic equivalent formulas being associated with at least one respective pronounceable unit. After an initial query in a primary database fails to produce a positive result, an error memory database may be queried with a search string to obtain a positive result based on records of previously failed searches which ultimately found a positive result. If no record is found, the search string may be parsed into at least one pronounceable unit. Phonetically equivalent formulas may be applied to the at least one pronounceable unit to create at least one phonetic search string which is re-queried into the error memory database and the primary database. Successful positive results may be stored with the search string in the error memory database.

The invention provides a video clip playing method and a video clip playing device. The method comprises the steps of acquiring voice search information sent by a user, and resolving the voice search information to acquire corresponding text information; using a pre-trained deep neural network model to extract a search field, a search intention and a search intention satisfaction condition from the text information; if a video clip queried by the user is learned according to the search intention, querying a preset label library corresponding to the search field, and acquiring a video label successfully matched with the search intention satisfaction condition; and playing the target video clip corresponding to the video label to the user according to a pre-stored video playing parameter corresponding to the video label. Therefore, skipping to the target video clip can be accurately achieved via voice search, so that the operation is simple and convenient, the time is saved, the user can rapidly learn plot development of the whole video, utilization of the user is facilitated, and the user requirement is met.

The invention provides a child user searching method and device based on artificial intelligence. The method comprises the following steps: according to obtained search voice, and through a voiceprint recognition mode, identifying the type of a user sending the search voice; and when the identified type of the user is a child user, carrying out voice recognition on the search voice through a child speech recognition model to obtain search requirements described in the search voice; searching a target resource matched with the search requirements in a multimedia resource library; and on a search result page, presenting the target resource in a multimedia manner, thereby solving the technical problem that since children's language habits are greatly different from adult's language habits, in the voice search process, the presented search results are greatly different from the user requirements, and the child users read with difficulty.

The invention relates to a picture voice searching method. The picture voice searching method includes (101) receiving and judging whether a character tag is set on the picture by the aid of human-computer interaction when a picture is browsed or a photo is taken, performing the next step if the character tag is set on the picture, and otherwise, exiting a tag set step; (102) receiving and identifying a sentence input by a user through a voice receiving device; (103) analyzing the sentence and dividing the sentence into keyword or expression combinations; and (104) saving the combinations in the step (103) and the corresponding relation of the combinations and the picture into a picture data base. The picture voice searching method further correspondingly includes (201) receiving and identifying the sentence input by the user through the voice receiving device; (202) analyzing the sentence and dividing the sentence into the keyword or expression combinations; and (203) using the combinations in the step (202) to search the picture data base, judging whether eligible records exist, displaying pictures or a picture list corresponding to all eligible records if the eligible records exist, and otherwise, displaying null or prompting no eligible pictures.

An embodiment of the invention discloses a method and an apparatus for voice search based on user feature, wherein the method comprises: receiving a voice search request of a user; identifying the user feature based on the voice search request of the user; searching based on the voice search request and the user feature to acquire search results; and sending the search results to back to the user. The embodiment of the invention provides the method and the apparatus for voice search based on the user feature; the problem that the existing method for voice search can't be fully utilized to identify the user feature is solved; the user feature can be identified based on the voice; more intelligent search can be realized based on the user feature; more reasonable recommendation can be provided for the user; at the same time, one-hand operation to a large-screen phone is supported; and the operation experience of the user is enhanced.

The invention provides a method and a device for establishing a linguistic model for voice recognition. The method includes a first step of utilizing recognition results of voice search queries to users as voice search linguistic data, carrying out linguistic model training to obtain a voice linguistic model, utilizing text search queries of the users as text search linguistic data, and carrying out linguistic model training to obtain a text linguistic model, and a second step of integrating the voice linguistic model and the text linguistic model to obtain a recognition linguistic model. The recognition linguistic model obtained through adoption of the method is capable of well reflecting wording preferences of the users in the voice input process and can be applied to voice recognition to improve accuracy of the voice recognition.

The invention provides methods and systems for establishing a language model of address book names and searching voice. The method for establishing the language model of the address book names comprises the following steps of: acquiring name information from a search log of text search; marking syllables for the acquired name information; training a name syllable language model by using syllable marking of the name information; and combining the name syllable language model and a digital probability model, setting the probability from syllables to digits and from digits to syllables to be 0, and thus obtaining the final language model. The method for searching the voice comprises the following steps of: receiving a voice request of a user and sending the voice request to a server by a client; identifying the voice request by using the name syllable language model or the final language model and returning the identified name syllables to the client by the server; and matching the name syllables returned by the server in a local address book and revealing the matching result to the user by the client. By the methods and the systems, the voice search accuracy of the address book can be improved.

The invention is applicable in the field of speech interaction and provides a speech interaction method and device. The speech interaction method comprises the following steps of: receiving speech data; recognizing the speech data to generate a semantic text; carrying out similarity matching on the semantic text and a generated history speech research record; taking the history speech research record with the similarity exceeding a specified threshold as a basic database; determining at least one text to be matched after carrying out screening treatment on the basic database; matching the semantic text with the determined at least one text to be matched; and executing corresponding operation according to a matching result. The embodiment of the invention can increase the accuracy rate and the success rate of speech interaction.

A method of identifying a location of a query string in an audio signal is provided. Under the method, a segment of the audio signal is selected. A score for a query string in the segment of the audio signal is determined by determining the product of probabilities of overlapping sequences of tokens. The score is then used to decide if the segment of the audio signal is likely to contain the query string.

The invention provides a method, a client and a system for searching voices in instant messaging, and belongs to the technical field of communication and software. The method comprises: step one, acquiring user voice information in a process in which users input data through interactive interface input columns of instant messaging interactive interfaces; and step two, searching the user voice information and acquiring searched results to serve as input contents to be loaded in the current interactive interface input columns. By means of the method, a client and a system for searching voice in instant messaging, instant messaging tools can be used in an input operation process to perform a voice searching function conveniently and insert searched results in the interactive interface input columns.

A voice search and analysis system comprises a voice transcription module, an index establishing module, a voice search module and a test analysis module. Keywords contained in voice, positions where the keywords appear and other characteristic information are searched for. Analysis can be effectively performed on massive voice recording files and audio files through voice analysis, knowledge exploration in the voice and rapid search on the voice files are achieved, and the problems that voice data are difficult to search for and analyze are solved.

The invention discloses a voice searching method and device. The voice searching method comprises the steps that voice information used for searching is recognized into text information; the text information is converted into first pinyin information; a searching result matched with the first pinyin information is obtained locally or from a server. According to the voice searching method and device, the technical problem that in the prior art, a correct searching result can not be obtained due to incorrect voice recognition is effectively solved, and the technical effect that correct searching results can be obtained is achieved.