Microsoft Technology Licensing, LLC

Albert Joseph Kishan Thambiratnam

Frank Torsten Bernd Seide

Gang Li

Peng Yu

Frank T B Seide

Timo Pascal Mertens

Weiwu Zhu

Sha Meng

In various embodiments, a transcript that represents a media file is created. Keyword candidates that may represent topics and/or content associated with the media content are then be extracted from the transcript. Furthermore, a keyword set may be generated for the media content utilizing a mutual information criteria. In other embodiments, one or more queries may be generated based at least in part on the transcript, and a plurality of web documents may be retrieved based at least in part on the one or more queries. Additional keyword candidates may be extracted from each web document and then ranked. A subset of the keyword candidates may then be selected to form a keyword set associated with the media content.

Keyword generation for media content

Techniques are described for training a speech recognition model for accented speech. A subword parse table is employed that models mispronunciations at multiple subword levels, such as the syllable, position-specific cluster, and/or phone levels. Mispronunciation probability data is then generated at each level based on inputted training data, such as phone-level annotated transcripts of accented speech. Data from different levels of the subword parse table may then be combined to determine the accented speech model. Mispronunciation probability data at each subword level is based at least in part on context at that level. In some embodiments, phone-level annotated transcripts are generated using a semi-supervised method.

Subword-based multi-level pronunciation adaptation for recognizing accented speech

A voice activity detection (VAD) module analyzes a media file, such as an audio file or a video file, to determine whether one or more frames of the media file include speech. A speech recognizer generates feedback relating to an accuracy of the VAD determination. The VAD module leverages the feedback to improve subsequent VAD determinations. The VAD module also utilizes a look-ahead window associated with the media file to adjust estimated probabilities or VAD decisions for previously processed frames.

Leveraging speech recognizer feedback for voice activity detection

A full-text lattice indexing and searching system and method for indexing word lattices using a text indexer to enable enhance searching of audio content. The system and method utilize a Time-Anchored Lattice Expansion (TALE) method that represents word lattices such that they can be indexed with existing text indexers with little or no modification. Embodiments of system and method include an indexing module for generating and indexing word lattices based on audio content and a searching module for allowing searching of a full-text index containing indexed word lattices. The indexing module includes a custom IFilter and a custom Wordbreaker. Embodiments of the searching module include an ExpandQuery function for decorating an input query and a custom Stemmer. Embodiments of the searching module also include a GenerateSnippets module that extracts information from the indexed word lattices to enable the creation of clickable snippets.

Growing community of inventors

Beijing, China

Albert Joseph Kishan Thambiratnam