Abstract: Techniques disclosed herein include systems and methods for open-domain voice-enabled searching that is speaker sensitive. Techniques include using speech information, speaker information, and information associated with a spoken query to enhance open voice search results. This includes integrating a textual index with a voice index to support the entire search cycle. Given a voice query, the system can execute two matching processes simultaneously. This can include a text matching process based on the output of speech recognition, as well as a voice matching process based on characteristics of a caller or user voicing a query. Characteristics of the caller can include output of voice feature extraction and metadata about the call. The system clusters callers according to these characteristics. The system can use specific voice and text clusters to modify speech recognition results, as well as modifying search results.

Abstract: Methods and apparatus for selectively performing speech processing in a hybrid speech processing system. The hybrid speech processing system includes at least one mobile electronic device and a network-connected server remotely located from the at least one mobile electronic device. The mobile electronic device is configured to use an embedded speech recognizer to process at least a portion of input audio to produce recognized text. A controller on the mobile electronic device determines whether to send information from the mobile electronic device to the server for speech processing. The determination of whether to send the information is based, at least in part, on an analysis of the input audio, the recognized text, or a semantic category associated with the recognized text.

Abstract: In some embodiments, recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential errors. In some embodiments, the indications of potential errors may include discrepancies between recognition results that are meaningful for a domain, such as medically-meaningful discrepancies. The evaluation of the recognition results may be carried out using any suitable criteria, including one or more criteria that differ from criteria used by an ASR system in determining the top recognition result and the alternative recognition results from the speech input. In some embodiments, a recognition result may additionally or alternatively be processed to determine whether the recognition result includes a word or phrase that is unlikely to appear in a domain to which speech input relates.

Abstract: Techniques for improved speech recognition disclosed herein include applying a statistical language model to a free-text input utterance to obtain a plurality of candidate word sequences for automatic speech recognition of the input utterance, each of the plurality of candidate word sequences having a corresponding initial score generated by the statistical language model. For one or more of the plurality of candidate word sequences, each of the one or more candidate word sequences may be analyzed to generate one or more hypotheses for a semantic class of at least one token in the respective candidate word sequence. The initial scores generated by the statistical language model for at least the one or more candidate word sequences may be revised based at least in part on the one or more hypotheses for the semantic class of the at least one token in each of the one or more candidate word sequences.

Abstract: According to some aspects, a method of monitoring an acoustic environment of a mobile device, at least one computer readable medium encoded with instructions that, when executed, perform such a method and/or a mobile device configured to perform such a method is provided. The method comprises receiving, by the mobile device, acoustic input from the environment of the mobile device, detecting whether the acoustic input includes a voice command from a user without requiring receipt of an explicit trigger from the user, and initiating responding to the detected voice command.

Abstract: A mobile device is described which is adapted for automatic speech recognition (ASR). A speech input receives an unknown speech input signal from a user. A local controller determines if a remote ASR processing condition is met, transforms the speech input signal into a selected one of multiple different speech representation types, and sends the transformed speech input signal to a remote server for remote ASR processing. A local ASR arrangement performs local ASR processing of the speech input including processing any speech recognition results received from the remote server.

Abstract: In some embodiments, recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential errors. In some embodiments, the indications of potential errors may include discrepancies between recognition results that are meaningful for a domain, such as medically-meaningful discrepancies. The evaluation of the recognition results may be carried out using any suitable criteria, including one or more criteria that differ from criteria used by an ASR system in determining the top recognition result and the alternative recognition results from the speech input. In some embodiments, a recognition result may additionally or alternatively be processed to determine whether the recognition result includes a word or phrase that is unlikely to appear in a domain to which speech input relates.

Abstract: A mobile device is adapted for automatic speech recognition (ASR). A user interface for interaction with a user includes an input microphone for obtaining speech inputs from the user for automatic speech recognition, and an output interface for system output to the user based on ASR results that correspond to the speech input. A local controller obtains a sample of non-ASR audio from the input microphone for ASR-adaptation to channel-specific ASR characteristics, and then provides a representation of the non-ASR audio to a remote ASR server for server-side adaptation to the channel-specific ASR characteristics, and then provides a representation of an unknown ASR speech input from the input microphone to the remote ASR server for determining ASR results corresponding to the unknown ASR speech input, and then provides the system output to the output interface.

Abstract: In many speech-enabled applications, adaptation of speech recognition and language understanding tools for different users are employed. With such adaptation, identifying the particular user precedes applying the speech recognition and language understanding tools. According to at least one example embodiment, a method and corresponding apparatus of identifying a user includes comparing personal information data received from a user network device against personal information accessible by the server; and identifying a speech profile specific to the user based on the results of comparing the personal information data retrieved from the first user network device against the personal information accessible by the server. The identified speech profile is used in processing a speech of the user. Through use of the method or corresponding apparatus, a user can proceed directly to the use of the speech recognition or other applications and bypassing a login sequence.

Abstract: In some embodiments, the recognition results produced by a speech processing system (which may include a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for the domain. In some embodiments, one or more of the recognition results may be evaluated to determine whether the result(s) include one or more words or phrases that, when included in a result, would change a meaning of the result in a manner that would be significant for the domain.

Abstract: A mobile device is adapted for automatic speech recognition (ASR). A user interface for interaction with a user includes an input microphone for obtaining speech inputs from the user for automatic speech recognition, and an output interface for system output to the user based on ASR results that correspond to the speech input. A local controller obtains a sample of non-ASR audio from the input microphone for ASR-adaptation to channel-specific ASR characteristics, and then provides a representation of the non-ASR audio to a remote ASR server for server-side adaptation to the channel-specific ASR characteristics, and then provides a representation of an unknown ASR speech input from the input microphone to the remote ASR server for determining ASR results corresponding to the unknown ASR speech input, and then provides the system output to the output interface.

Abstract: A method is described for improving the accuracy of a transcription generated by an automatic speech recognition (ASR) engine. A personal vocabulary is maintained that includes replacement words. The replacement words in the personal vocabulary are obtained from personal data associated with a user. A transcription is received of an audio recording. The transcription is generated by an ASR engine using an ASR vocabulary and includes a transcribed word that represents a spoken word in the audio recording. Data is received that is associated with the transcribed word. A replacement word from the personal vocabulary is identified, which is used to re-score the transcription and replace the transcribed word.

Abstract: Described herein are techniques for determining corresponding positions between different representations of a textual work. In some of the techniques, portions of one or more representations may be processed. A determination of a corresponding position may be made in response to a request received from a user, such as a reader that desires to switch between representations. The request may indicate a position in one representation and the representation to which the user would like to switch. In response to receiving the request, one or more portions of one or more representations of a textual work may be processed. In some techniques, a corresponding position between different representations may be determined without processing the entirety of one or more representations of the textual work. For example, a corresponding position may be determined without processing an entire audio representation.

Abstract: Described herein are techniques for determining corresponding positions between different representations of a textual work. In some of the techniques, portions of one or more representations may be processed. A determination of a corresponding position may be made in response to a request received from a user, such as a reader that desires to switch between representations. The request may indicate a position in one representation and the representation to which the user would like to switch. In response to receiving the request, one or more portions of one or more representations of a textual work may be processed. In some techniques, a corresponding position between different representations may be determined without processing the entirety of one or more representations of the textual work. For example, a corresponding position may be determined without processing an entire audio representation.

Abstract: In some embodiments, a recognition result produced by a speech processing system based on an analysis of a speech input is evaluated for indications of potential errors. In some embodiments, sets of words/phrases that may be acoustically similar or otherwise confusable, the misrecognition of which can be significant in the domain, may be used together with a language model to evaluate a recognition result to determine whether the recognition result includes such an indication. In some embodiments, a word/phrase of a set that appears in the result is iteratively replaced with each of the other words/phrases of the set. The result of the replacement may be evaluated using a language model to determine a likelihood of the newly-created string of words appearing in a language and/or domain. The likelihood may then be evaluated to determine whether the result of the replacement is sufficiently likely for an alert to be triggered.

Abstract: According to some aspects, a method of monitoring an acoustic environment of a mobile device, at least one computer readable medium encoded with instructions that, when executed, perform such a method and/or a mobile device configured to perform such a method is provided. The method comprises receiving acoustic input from the environment of the mobile device while the mobile device is operating in the low power mode, detecting whether the acoustic input includes a voice command based on performing a plurality of processing stages on the acoustic input, wherein at least one of the plurality of processing stages is performed while the mobile device is operating in the low power mode, and using at least one contextual cue to assist in detecting whether the acoustic input includes a voice command.

Abstract: Training speech recognizers, e.g., their language or acoustic models, using actual user data is useful, but retaining personally identifiable information may be restricted in certain environments due to regulations. Accordingly, a method or system is provided for enabling training of an acoustic model which includes dynamically shredding a speech corpus to produce text segments and depersonalized audio features corresponding to the text segments. The method further includes enabling a system to train an acoustic model using the text segments and the depersonalized audio features. Because the data is depersonalized, actual data may be used, enabling speech recognizers to keep up-to-date with user trends in speech and usage, among other benefits.

Abstract: Training speech recognizers, e.g., their language or acoustic models, using actual user data is useful, but retaining personally identifiable information may be restricted in certain environments due to regulations. Accordingly, a method or system is provided for enabling training of a language model which includes producing segments of text in a text corpus and counts corresponding to the segments of text, the text corpus being in a depersonalized state. The method further includes enabling a system to train a language model using the segments of text in the depersonalized state and the counts. Because the data is depersonalized, actual data may be used, enabling speech recognizers to keep up-to-date with user trends in speech and usage, among other benefits.

Abstract: A voicemail computer system transcribes a voicemail message into text that is presented to a calling party for approval. A calling party is able to approve, disapprove or edit a voicemail message prior to delivery to one or more called parties. The voicemail computer system may analyze a voicemail message to detect errors, omissions, or potentially offensive words. The voicemail computer may analyze a voicemail message to make suggestions as to tone, content or information contained within the voicemail message. The calling party can edit the voicemail message or approve it prior to providing a notification to one or more called parties that they have received the voicemail message.

Abstract: Speech recognition systems often process speech by employing models and analyzing audio data. An embodiment of the method and corresponding system described herein allow for passive monitoring of, for example, conversation between user(s) to determine context to use to prime model(s) for later speech recognition requests submitted to the speech recognition system. The embodiment improves the results of the speech recognition system by updating speech recognition model(s) with contextual information of the conversation. This increases the probability that the speech recognition system interprets the conversation to contextually relevant information.