Nuance Communications

About: Nuance Communications is a company organization based out in Vienna, Austria. It is known for research contribution in the topics: Speech processing & Voice activity detection. The organization has 1518 authors who have published 1701 publications receiving 54891 citations. The organization is also known as: ScanSoft & ScanSoft Inc..

Method for determining a noise reference signal for noise compensation and/or noise reduction

Abstract: The invention provides a method for determining a noise reference signal for noise compensation and/or noise reduction. A first audio signal on a first signal path and a second audio signal on a second signal path are received. The first audio signal is filtered using a first adaptive filter to obtain a first filtered audio signal. The second audio signal is filtered using a second adaptive filter to obtain a second filtered audio signal. The first and the second filtered audio signal are combined to obtain the noise reference signal. The first and the second adaptive filter are adapted such as to minimize a wanted signal component in the noise reference signal.

Hands free contact database information entry at a communication device

Abstract: A method, system, and program provides for hands free contact database information entry at a communication device. A recording system at a communication device detects a user initiation to record. Responsive to detecting the user initiation to record, the recording system records the ongoing conversation supported between the communication device and a second remote communication device. The recording system converts the recording of the conversation into text. Next, the recording system extracts contact information from the text. Then, the recording system stores the extracted contact information in an entry of the contact database, such that contact information is added to the contact database of the communication device without manual entry of the contact information by the user.

Reduced keyboard with prediction solutions when input is a partial sliding trajectory

Abstract: A reduced virtual keyboard system for text input on electronic devices is disclosed. Text input is performed by creating a tracing trajectory. Dynamic prediction solutions are created during the tracing process, thus avoiding the need for a user to complete the entire word trajectory. The system also allows a mixture of tapping actions and sliding motions for the same word. The system may comprise a Long Words Dictionary database having first letters corresponding to predetermined keys of the keyboard. Alternatively, the system uses a Dictionary and a database management tool to find long words.

Multiple pass automatic speech recognition methods and apparatus

Abstract: In some aspects, a method of recognizing speech that comprises natural language and at least one word specified in at least one domain-specific vocabulary is provided. The method comprises performing a first speech processing pass comprising identifying, in the speech, a first portion including the natural language and a second portion including the at least one word specified in the at least one domain-specific vocabulary, and recognizing the first portion including the natural language. The method further comprises performing a second speech processing pass comprising recognizing the second portion including the at least one word specified in the at least one domain-specific vocabulary.

Privacy-sensitive speech model creation via aggregation of multiple user models

Abstract: Techniques disclosed herein include systems and methods for privacy-sensitive training data collection for updating acoustic models of speech recognition systems. In one embodiment, the system locally creates adaptation data from raw audio data. Such adaptation can include derived statistics and/or acoustic model update parameters. The derived statistics and/or updated acoustic model data can then be sent to a speech recognition server or third-party entity. Since the audio data and transcriptions are already processed, the statistics or acoustic model data is devoid of any information that could be human-readable or machine readable such as to enable reconstruction of audio data. Thus, such converted data sent to a server does not include personal or confidential information. Third-party servers can then continually update speech models without storing personal and confidential utterances of users.