Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: A call from a caller to an interactive voice response (IVR) system may be serviced based on behavior by the caller in one or more prior calls to the IVR system. The call may be serviced by predicting information to be used in servicing the call. Predicting such information may include analyzing data reflecting behavior by the caller in one or more prior calls to the IVR system.

Abstract: A call from a caller to an interactive voice response (IVR) system may be serviced based on behavior by the caller in one or more prior calls to the IVR system. The call may be serviced by predicting information to be used in servicing the call. Predicting such information may include analyzing data reflecting behavior by the caller in one or more prior calls to the IVR system.

Abstract: A call from a caller to an interactive voice response (IVR) system may be serviced based on behavior by the caller in one or more prior calls to the IVR system. The call may be serviced by predicting information to be used in servicing the call. Predicting such information may include analyzing data reflecting behavior by the caller in one or more prior calls to the IVR system.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: A design interface is described for maintaining call information for creating a voice user interface. An initial set of sample call paths is defined for a dialog application. Each sample call path has associated call information including a sequence of system prompts and caller responses that model a user interaction through the dialog application for the sample call path. A call design database stores the call information. A set of subsequent call paths is defined for the dialog application using the call information in the call design database. The call information in the call design database is updated to reflect current versions of the call information for all the call paths.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: Real-time automatic capturing and storing is described for contact information such as a telephone number or other well-structured contact information spoken during a conversation over the mobile telephone. A user input is received to capture contact information contained in recent audio data processed by the mobile device. Speech in the recent audio data is identified that corresponds to the contact information. Then speech recognition is used to extract the contact information from the identified speech. The contact information is stored in mobile device memory storage.

Abstract: A design interface is described for maintaining call information for creating a voice user interface. An initial set of sample call paths is defined for a dialog application. Each sample call path has associated call information including a sequence of system prompts and caller responses that model a user interaction through the dialog application for the sample call path. A call design database stores the call information. A set of subsequent call paths is defined for the dialog application using the call information in the call design database. The call information in the call design database is updated to reflect current versions of the call information for all the call paths.