Generating topic-specific language models

Abstract

Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.

Description

BACKGROUND

Automated speech recognition uses a language model to identify the most likely candidate matching a word or expression used in a natural language context. In many instances, the language model used is built using a generic corpus of text and might not offer the most accurate or optimal representation of natural language for a given topic. For example, in a scientific context, the word “star” may be less likely to follow the phrase “country music” than in an entertainment context. Accordingly, when evaluating an audio signal relating to science, a speech recognition system may achieve more accurate results using a language model specific to the topic of science, rather than a generic language model.

BRIEF SUMMARY

The following presents a simplified summary of the disclosure in order to provide a basic understanding of some aspects. It is not intended to identify key or critical elements or to delineate the scope. The following summary merely presents some concepts of the disclosure in a simplified form as a prelude to the more detailed description provided below.

According to one or more aspects, a speech recognition system may automatically generate a topic specific language model and recognize words in a speech signal using the generated model. For example, a speech recognition system may initially determine words in a audio speech signal using a basic or generic language model. A language model, as used herein, generally refers to a construct that defines probabilities of words appearing after another word or set of words (or within a predefined proximity of another word). The speech recognition system may use the determined words to identify one or more topics associated with the speech signal and use the identified topics to obtain a corpus of text relating to those topics. The corpus of text allows the speech recognition system to create a topic specific language model by, in one example, modifying or adapting the basic or generic language model according to the probabilities and language structure presented in the topic specific corpus of text. A second speech recognition pass may then be performed using the topic specific language model to enhance the accuracy of speech recognition. In one or more arrangements, the topic specific language model may be generated on-the-fly, thereby eliminating the need to pre-generate language models prior to receiving or beginning processing of an audio signal.

According to another aspect, collecting a corpus of topic specific text may include generating one or more search queries and using those search queries to identify articles, publications, websites and other documents and files. In one example, the search queries may be entered into a search engine such as GOOGLE or PUBMED. Text may then be extracted from each of the results returned from the search. In one or more arrangements, a corpus collection module may further clean the text by removing extraneous or irrelevant data such as bylines, advertisements, images, formatting codes and information and the like. The corpus collection module may continue to collect text until a specified threshold has been reached.

According to another aspect, multiple queries may be generated for corpus collection. For example, a speech recognition system or text collection module may generate multiple queries for a single topic to increase the amount of text returned. Alternatively or additionally, an audio signal may include multiple topics. Accordingly, at least one query may be generated for each of the multiple topics to insure that the corpus of text collected is representative of the audio signal.

According to yet another aspect, the corpus of text collected may be representative of a distribution of topics associated with the speech signal. Stated differently, a speech signal may include a variety of topics, each topic having a degree of emphasis or significance in that speech signal. The corpus of text may include amounts of text that have been collected based on that distribution of topic significance or emphasis. In one example, the number of words or phrases associated with a topic may be used as a measure of its significance in a speech signal. A threshold number of words may then be divided according to the significance.

The details of these and other embodiments are set forth in the accompanying drawings and the description below. Other features and advantages will be apparent from the description and drawings, and from the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

The present disclosure is illustrated by way of example and not limited in the accompanying figures in which like reference numerals indicate similar elements and in which:

FIG. 1 illustrates an example network distribution system in which content items may be provided to subscribing clients.

FIG. 2 illustrates an example speech recognition system configured to identify words in an audio signal based on a topic specific language model according to one or more aspects described herein.

FIG. 3 illustrates an example segment of an audio signal that may be processed using a speech recognition system according to one or more aspects described herein.

FIG. 4 illustrates an example listing of meaningful words according to one or more aspects described herein.

FIG. 5 illustrates an example keyword table according to one or more aspects described herein.

FIG. 6 is a flowchart illustrating an example method for creating a topic specific language model and using the topic specific language model to perform speech recognition on an audio signal according to one or more aspects described herein.

FIG. 7 is a flowchart illustrating an example method for collecting a corpus of text for creating a topic specific language model according to one or more aspects described herein.

DETAILED DESCRIPTION

FIG. 1 illustrates a content processing and distribution system 100 that may be used in connection with one or more aspects described herein. The distribution system 100 may include a headend 102, a network 104, set top boxes (STB) 106 and corresponding receiving devices (e.g., receiver, transceiver, etc.) 108. The distribution system 100 may be used as a media service provider/subscriber system wherein the provider (or vendor) generally operates the headend 102 and the network 104 and also provides a subscriber (e.g., client, customer, service purchaser, user, etc.) with the STB 106.

The STB 106 is generally located at the subscriber location such as a subscriber's home, a tavern, a hotel room, a business, etc., and the receiving device 108 is generally provided by the subscribing client. The receiving device 108 may include a television, high definition television (HDTV), monitor, host viewing device, MP3 player, audio receiver, radio, communication device, personal computer, media player, digital video recorder, game playing device, etc. The device 108 may be implemented as a transceiver having interactive capability in connection with the STB 106, the headend 102 or both the STB 106 and the headend 102. Alternatively, STB 106 may include a cable modem for computers for access over cable.

The headend 102 is generally electrically coupled to the network 104, the network 104 is generally electrically coupled to the STB 106, and each STB 106 is generally electrically coupled to the respective device 108. The electrical coupling may be implemented as any appropriate hard-wired (e.g., twisted pair, untwisted conductors, coaxial cable, fiber optic cable, hybrid fiber cable, etc.) or wireless (e.g., radio frequency, microwave, infrared, etc.) coupling and protocol (e.g., Home Plug, HomePNA, IEEE 802.11(a-b), Bluetooth, HomeRF, etc.) to meet the design criteria of a particular application. While the distribution system 100 is illustrated showing one STB 106 coupled to one respective receiving device 108, each STB 106 may be configured with having the capability of coupling more than one device 108.

The headend 102 may include a plurality of devices 110 (e.g., devices 110a-110n) such as data servers, computers, processors, security encryption and decryption apparatuses or systems, and the like configured to provide video and audio data (e.g., movies, music, television programming, games, and the like), processing equipment (e.g., provider operated subscriber account processing servers), television service transceivers (e.g., transceivers for standard broadcast television and radio, digital television, HDTV, audio, MP3, text messaging, gaming, etc.), and the like. At least one of the devices 110 (e.g., a sender security device 110x), may include a security system.

In one or more embodiments, network 104 may further provide access to a wide area network (WAN) 112 such as the Internet. Accordingly, STB 106 or headend 102 may have access to content and data on the wide area network. Content items may include audio, video, text and/or combinations thereof. In one example, a service provider may allow a subscriber to access websites 114 and content providers 116 connected to the Internet (e.g., WAN 112) using the STB 106. Websites 114 may include news sites, social networking sites, personal webpages and the like. In another example, a service provider (e.g., a media provider) may supplement or customize media data sent to a subscriber's STB 106 using data from the WAN 112.

Alternatively or additionally, one or more other computing devices 118 may be used to access either media distribution network 104 or wide area network 112.

Using networks such as those illustrated and described with respect to FIG. 1, a speech recognition device and/or system may access a corpus of information that relates to a specific topic or set of topics to refine and build a topic specific language model. The topic specific language model may be better honed to identify the spoken words used in natural language associated with the identified topic or topics. In one or more examples, a speech recognition device may search for articles and other textual material relating to a topic from various content sources such as content providers 116 and websites 114 of FIG. 1. The speech recognition device may then generate a language model based thereon, as described in further detail herein.

FIG. 2 illustrates an example speech recognition device configured to generate a language model based on a particular topic. Initially, natural language data such as audio is received by speech recognizer module 205 of speech recognition device 200 to identify an initial set of words contained in the audio based on a generic language model stored in database 210. A generic language model may be created using a generic corpus of text and might not be specific to any particular topic. Speech recognizer module 205 may include software, hardware, firmware and/or combinations thereof such as SCANSOFT's DRAGON NATURALLY SPEAKING speech recognition software.

From the initial set of identified words, topic extractor 215 is configured to identify one or more topics associated with the natural language data. Topics may be identified from the initial set of words in a variety of ways including by determining a frequency of words used, identification of meaningful vs. non-meaningful words, determining a type of word (e.g., noun, verb, etc.) and/or combinations thereof. For example, words that are used most frequently might be treated as being indicative of a topic of the audio. In another example, meaningful words might be predefined and identified in the natural language data. Accordingly, topic extractor 215 may eliminate non-meaningful words such as “the” or “of” from topic consideration even if such words appear relatively frequently. In one example, stop word lists or noise word lists may be used to filter out non-meaningful words. Stop word lists and other types of word filtering lists may be topic-specific or may be universal for all topics.

In some arrangements, speech recognizer module 205 might not perform a first pass on the natural language to identify the initial set of words. Instead, topic extractor 215 may be configured to identify topics associated with the natural language based on other information such as metadata. For example, if speech recognition device 200 is processing audio stored in an audio file, topic extractor 215 may extract topics from metadata included in the audio file such as a genre, artist, subject and title. If the audio file is located on a webpage, topic extractor 215 may use page or site data extracted from the webpage for topic determination. Alternatively or additionally, a combination of metadata and the initial set of recognized words may be used to identify topics to which the audio relates. A topic may include any number of words and in some instances, may include phrases.

Once topic extractor 215 has outputted the topic(s) of the natural language data, a query generator 225 of a corpus collector module 220 is configured to create search queries for obtaining a corpus of text relating to the identified topics. In one example, the query generator 225 may create search queries for a search engine 235 such as GOOGLE. In another example, query generator 225 may formulate queries for identifying publications in a database such as PUBMED. Queries may be formed using the identified topic words or phrases in a keyword search. Alternatively or additionally, speech recognition device 200 may maintain a definition or meaning table in database 210 to provide further keywords that may be used in a search query. For example, the word “rocket” may be associated with additional key words and phrases “weapon,” “propulsion,” “space shuttle” and the like. Accordingly, multiple search query strings may be formed using various combinations of the topic words and associated keywords.

Articles and other text identified through the search query may then be fed from corpus collector module 220 into a language model generator 230 that creates a language model specific to the topic or topics identified by topic extractor 215. Language models, as used herein, generally refer to data constructs configured to represent a probability of a sequence of words appearing together. Various types of language models may include n-gram language models which specify the probability of a set of n words appearing together (sometimes in a certain sequence). In one example, a language model may indicate that the probability of the word “friend” appearing immediately after the word “best” is more likely than “friend” appearing immediately after the word “chest” in a n-gram language model, where n=2. Accordingly, a speech recognition device such as device 200 may be able to ascertain whether an utterance (e.g., a spoken word or sound in an audio signal) corresponds to the word “chest” or “best” based on the following word (e.g., “friend”). Thus, a language model allows a device or a user to determine the odds that a speech signal includes word or phase x.

To create the topic specific language model, language model generator 230 may modify a basic language model in accordance with the probabilities determined from the text collected by corpus collector 220 (as discussed in further detail herein). Thus, probabilities of certain word combinations or n-grams may be modified based on their frequency of occurrence in the collected corpus of text. Using this topic specific language model, speech recognition device 200 may perform a second pass on the natural language to identify the words used in the speech.

FIG. 3 illustrates an example segment of an audio speech signal from which one or more topics may be extracted. Segment 300 may represent a speech signal from a television show or some other audio clip, for instance. From segment 300, topics such as movies, Actor X and sci-fi may be extracted based on frequency of words associated with those topics, definition of meaningful vs. non-meaningful words and the like. FIG. 4, for example, illustrates a list 400 of predefined meaningful words that may be evaluated in determining a topic of speech. Accordingly, because “movie” appears in segment 300, a speech recognition device (e.g., device 200 of FIG. 2) may evaluate whether movies is a topic of segment 300. Words or phrases not in list 400 might be discarded from topic consideration.

Frequency, on the other hand, corresponds to the number of times a word or topic appears in a segment of speech. In some instances, a topic may correspond to multiple words. Accordingly, even though segment 300 includes only 1 mention of the word “movie,” a frequency assigned to the topic of movies may have a value of 2 in view of the use of the phrase “big screen,” a known colloquialism for movies. In one or more configurations, a word or phrase may be extracted as a topic if the determined frequency is above a certain threshold. The threshold may be defined manually, automatically or a combination thereof. In one example, topics may be identified from the three words or phrases used most frequently in segment 300. Thus, the threshold may be defined as the frequency of the least frequent word or phrase of the top three most frequently used words or phrases. According to one or more arrangements, frequency might only be evaluated upon determining that a word or phrase falls into the category of a meaningful word or phrase.

FIG. 5 illustrates an example of a keyword table storing lists of keywords in association with various topic words. Topic words 501 may be listed in one section of table 500, while associated keywords 503 may be provided in another section. Example topic words 501 may include “food,” “sports,” “football,” and “photography.” Topic word food 501a may be associated with keywords or key phrases 503a such as “meal,” “lunch,” “dinner,” and “hot dogs.” Topic word sports 501b, on the other hand, may be associated with keywords or phrases 503b that include “athletic activity,” “competition,” “football,” “hockey” and the like. Using the keywords and key phrases specified in table 500, search queries may be formed for retrieving text corresponding to a particular topic. In one example, if a speech recognition device wants to retrieve articles associated with sports, the device may generate a search string such as “athletic activity competition articles.” Note that in this example, the word articles may be tacked onto the end of the query to limit the types of results returned (e.g., articles rather than photo galleries).

FIG. 6 illustrates an example method for building a topic specific language model and performing speech recognition using the topic specific language model. In step 600, a speech recognition system may receive a speech signal from an audio source. The audio source may include an audio data file, an audio/video file that includes an audio track, a line-in input (e.g., a microphone input device) and the like. In step 605, the speech recognition system subsequently performs a first speech recognition pass over the received audio/speech signal using a generic or basic language model. In some instances, the first speech recognition pass might only return words that have been recognized with a specified level of confidence (e.g., 95%, 99% or the like). The speech recognition system may then determine topics from the returned words recognized from the first pass over the audio signal in step 610.

Using the determined topics, the speech recognition may subsequently generate one or more search queries to identify a corpus of text relevant to the determined topics in step 615. For example, search queries may be created by assembling known keywords associated with or describing the specified topic, as described herein. In response to the search query, the speech recognition system may receive a plurality of search results in step 620. These search results may include multiple types of information including articles, blogs, text from images, metadata, and text from a webpage and may be received from various databases and search engines. Text from each of the search results may then be extracted and collected in step 625. In step 630, the system may determine whether a sufficient number of words has been collected from the search results. The determination may be made by comparing the number of words collected with a specified threshold number of words. The threshold number of words may be, for example, 100,000, 200,000, 1,000,000 or 10,000,000. If the collector module has collected an insufficient number of words, the module may repeat steps 615-625 to obtain more words. For instance, the collector module may generate a new search query or, alternatively or additionally, extract words from additional search results not considered in the first pass.

If, on the other hand, the collector module has obtained a sufficient number of words from the search results, the system may generate a topic specific language model in step 635 using the corpus of text collected. The system may, for example, adapt or revise a basic or generic language model based on the corpus of topic specific text retrieved. By way of example, assuming that a generic or initial language model shows that the probability of the word “dust” immediately following the word “cosmic” at 30% and the probability of the word “dust” immediately following the word “house” at 70%. Assuming that at least one of the topics in the corpus collection and, correspondingly, the speech to be recognized is space, the corpus of topic specific text may show that the probability that the word “dust” appears immediately after the word “cosmic” is 80% versus 20% for “dust” immediately appearing after “house.” Accordingly, the speech recognition system may modify the language model to reflect the probabilities determined based on the corpus of topic specific text. Alternatively, the speech recognition system may average the percentages. For example, the average of the two probabilities of “dust” following “cosmic” may result in a 55% probability while the average for “dust” following “house” may average out to 45%. Other algorithms and methods for adjusting a basic language model to produce the topic specific language model may be used. The above example is merely used to illustrate some aspects of the disclosure and is simplified. Language models generally include a greater number of possible word combinations (e.g., many other words may immediately precede the word “dust”) and probabilities than discussed in the example above.

Once the topic specific language model has been created, the speech recognition system may perform a second pass over the speech to make a final identification of the words spoken in step 640. The words identified in the second pass may be used for a variety of purposes including automatic transcription of recorded audio, creating a document by speaking the words rather than by typing, data entry and the like.

FIG. 7 illustrates an example method for collecting a corpus of topic specific text. In step 700, a topic specific query may be created. In step 705, the query may be executed in a search engine to identify one or more groups of text such as articles, websites, press releases and the like. In step 710, the corpus collection module may extract and enqueue a source identifier or location (e.g., a URI or URL) of the text files or documents matching the search query. In step 715, the corpus collection module may extract text from each document or file identified in the search in accordance with the queue and convert the text into raw text. Raw text may include the characters forming the words and phrases with formatting and other extraneous information such as metadata removed. In step 720, the raw text may be cleaned. In particular, words or text that does not form a part of the content of the document or article may be removed. For example, HTML files usually include several text tags or markup elements such as <BODY> </BODY> and the like. Because those headers are not part of the content of the web page or HTML site, the headers may be removed so as not to pollute the corpus of text being used to build a topic specific language model. The corpus collection module may use a dictionary of extraneous text to clean the raw text.

In step 725, the corpus collection module may determine whether a threshold number of words has been collected. If so, the corpus collection module may return the current set of words as a final corpus in step 730. If, however, the corpus collection module determines that the threshold number of words has not been collected, the corpus collection module may determine whether additional pages (e.g., a webpage) or groups of search results are available in step 735. If so, the corpus collection module may repeat steps 710-720 to process one or more additional pages or groups of search results. If, however, no additional search results are available, the corpus collection module may return to step 700 to obtain text using another search query in step 740.

The method of FIG. 7 may be repeated or used for each topic, topic word or topic phrase identified by a topic extractor (e.g., topic extractor 215 of FIG. 2). Each topic, topic word or topic phrase may have an associated threshold number of words that is to be collected. The threshold number for each topic, topic word or phrase may be determined by dividing a total number of words needed by the number of topics, topic words and topic phrases. Alternatively, the threshold for each query or topic may be determined based on an estimated significance of the topic so that the corpus of text is topically representative of the speech signal. Significance of a topic may be estimated, for example, by determining a number of words or phrases identified as being associated with the topic in the first speech recognition pass.

In one or more arrangements, a query may include phrases or words for multiple topics of the speech signal to insure that the results received are more likely to be relevant. For example, if a speech signal is related to the Battle of Bull Run, submitting queries using only a single word or phrase from the list of “bull,” “run,” “civil war,” “battle,” “Manassas,” and “Virginia” might produce search results that are entirely unrelated. For example, an article about anatomy of a bull may be returned. Alternatively or additionally, an article or movie review about Forest Gump might be returned using a query that was solely focused on the word “run.” Thus, a query such as “bull run” might be used instead to identify articles, documents and the like that are more likely to be relevant to the actual topic or topics of the speech signal.

The methods and systems described herein may be used in contexts and environments other than audio signals. For example, a topic specific language model may be used to aid in optical character recognition to improve the accuracy of the characters and words identified in a particular image or document.

The methods and features recited herein may further be implemented through any number of computer readable media that are able to store computer readable instructions. Examples of computer readable media that may be used include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, DVD or other optical disk storage, magnetic cassettes, magnetic tape, magnetic storage and the like.

Additionally or alternatively, in at least some embodiments, the methods and features recited herein may be implemented through one or more integrated circuits (IC s). An integrated circuit may, for example, be a microprocessor that accesses programming instructions or other data stored in a read only memory (ROM). In some such embodiments, the ROM stores programming instructions that cause the IC to perform operations according to one or more of the methods described herein. In at least some other embodiments, one or more of the methods described herein are hardwired into an IC. In other words, the IC is in such cases an application specific integrated circuit (ASIC) having gates and other logic dedicated to the calculations and other operations described herein. In still other embodiments, the IC may perform some operations based on execution of programming instructions read from ROM or RAM, with other operations hardwired into gates and other logic of IC. Further, the IC may output image data to a display buffer.

Although specific examples of carrying out the invention have been described, those skilled in the art will appreciate that there are numerous variations and permutations of the above-described systems and methods that are contained within the spirit and scope of the invention as set forth in the appended claims. Additionally, numerous other embodiments, modifications and variations within the scope and spirit of the appended claims will occur to persons of ordinary skill in the art from a review of this disclosure.

Claims

1. A method comprising: determining, based on a first speech recognition process associated with a first language model, a topic associated with an audio signal;performing a plurality of searches of a corpus to identify a plurality of terms related to the topic, wherein the corpus comprises a collection of text other than a transcript of the audio signal;in response to determining that the quantity of the plurality of terms identified by the searches as related to the topic matches or exceeds a threshold quantity: generating, based on the plurality of terms identified in the corpus, a second language model; anddetermining, based on a second speech recognition process associated with the generated second language model, the transcript of the audio signal.

2. The method of claim 1, further comprising at least one of: generating, based on the transcript, a closed-captioning feed for the audio signal:causing words of the transcript to be input into a computer application; ordetermining, based on the transcript, topic segments of the audio signal.

3. The method of claim 1, wherein the quantity of the plurality of terms is based on at least one of: a total quantity of terms needed to generate the second language model and a quantity of topics associated with the audio signal; ora respective significance, based on the first speech recognition process, for each of a plurality of topics associated with the audio signal.

4. The method of claim 1, wherein the second language model comprises a modification of the first language model.

5. The method of claim 1, wherein the determining the topic comprises: determining that a frequency of one or more terms, in the audio signal and associated with the topic, satisfies a frequency threshold.

6. The method of claim 1, wherein the determining the plurality of terms comprises continuing to perform searches to identify terms until corresponding search results matches or exceeds a threshold quantity.

7. The method of claim 1, wherein the one or more searches comprise at least one of: a web search; or a publication database search.

8. The method of claim 1, further comprising: determining the second language model based on the first language model.

9. The method of claim 1, wherein, in response to the quantity of the plurality of terms related to topic not meeting a threshold quantity: conducting additional searches associated with the topic to determine additional plurality of terms related to the topic.

10. The method of claim 1, wherein, performing a plurality of searches of a corpus to identify a plurality of terms related to the topic further comprises, creating the plurality of searches by assembling known keywords associated with the topic.

11. An apparatus comprising: one or more processors; andmemory storing instructions that, when executed by the one or more processors, cause the apparatus to:determine, based on a first speech recognition process associated with a first language model, a topic associated with an audio signal;perform a plurality of searches of a corpus to identify a plurality of terms related to the topic, wherein the corpus comprises a collection of text other than a transcript of the audio signal;in response to determining that the quantity of the plurality of terms identified by the searches as related to the topic matches or exceeds a threshold quantity: generate, based on the plurality of terms identified in corpus, a second language model; anddetermine, based on a second speech recognition process associated with the generated second language model, the transcript of the audio signal.

12. The apparatus of claim 11, wherein the instructions, when executed by the one or more processors, further cause the apparatus to perform at least one of: generate, based on the transcript, a closed-captioning feed for the audio signal; cause words of the transcript to be input into a computer application; ordetermine, based on the transcript, topic segments of the audio signal.

13. The apparatus of claim 11, wherein the quantity of the plurality of terms is based on at least one of: a total quantity of terms needed to generate the second language model and a quantity of topics associated with the audio signal; ora respective significance, based on the first speech recognition process, for each of a plurality of topics associated with the audio signal.

14. The apparatus of claim 11, wherein the second language model comprises a modification of the first language model.

15. The apparatus of claim 11, wherein the instructions, when executed by the one or more processors, further cause the apparatus to determine the topic by determining that a frequency of one or more terms, in the audio signal and associated with the topic, satisfies a frequency threshold.

16. The apparatus of claim 11, wherein the instructions, when executed by the one or more processors, further cause the apparatus to determine the plurality of terms by continuing to perform searches until corresponding search results matches or exceeds a threshold quantity.

17. The apparatus of claim 11, wherein the one or more searches comprise at least one of: a web search; or a publication database search.

18. The apparatus of claim 11, wherein the instructions, when executed by the one or more processors, further cause the apparatus to: determine the second language model based on the first language model.

19. A non-transitory computer-readable medium storing instructions that, when executed, cause: determining, based on a first speech recognition process associated with a first language model, a topic associated with an audio signal;performing a plurality of searches of a corpus to identify a plurality of terms related to the topic, wherein the corpus comprises a collection of text other than a transcript of the audio signal;in response to determining that the quantity of the plurality of terms identified by the searches as related to the topic matches or exceeds a threshold quantity: generating, based on the plurality of terms identified in the corpus, a second language model; anddetermining, based on a second speech recognition process associated with the generated second language model, the transcript of the audio signal.

20. The non-transitory computer-readable storage medium of claim 19, wherein the instructions, when executed, further cause at least one of: generating, based on the transcript, a closed-captioning feed for the audio signal;causing words of the transcript to be input into a computer application; ordetermining, based on the transcript, topic segments of the audio signal.

21. The non-transitory computer-readable storage medium of claim 19, wherein the quantity of the plurality of terms is based on at least one of: a total quantity of terms needed to generate the second language model and a quantity of topics associated with the audio signal; ora respective significance, based on the first speech recognition process, for each of a plurality of topics associated with the audio signal.

22. The non-transitory computer-readable storage medium of claim 19, wherein the second language model comprises a modification of the first language model.

23. The non-transitory computer-readable storage medium of claim 19, wherein the determining the topic comprises: determining that a frequency of one or more terms, in the audio signal and associated with the topic, satisfies a frequency threshold.

24. The non-transitory computer-readable storage medium of claim 19, wherein the determining the plurality of terms comprises continuing to perform searches until corresponding search results matches or exceeds a threshold quantity.

25. The non-transitory computer-readable storage medium of claim 19, wherein the one or more searches comprise at least one of: a web search; or a publication database search.

26. The non-transitory computer-readable storage medium of claim 19, wherein the instructions, when executed, further cause: determining the second language model based on the first language model.