Tied and reduced RNN-T
US-12062363-B2 · Aug 13, 2024 · US
Dynamic long-distance dependency with conditional random fields
US9037460B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9037460-B2 |
| Application number | US-201213433186-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 28, 2012 |
| Priority date | Mar 28, 2012 |
| Publication date | May 19, 2015 |
| Grant date | May 19, 2015 |
How to read this patent
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
- Title
What the patent document calls the invention.
- Abstract
A short plain-language summary of the technical disclosure.
- Assignees and inventors
Who owns or filed the patent and who is credited as inventor.
- Key dates
Filing, priority, publication, and grant dates set the timeline.
- First independent claim
The legal scope of protection — read this for what is actually claimed.
- CPC / IPC classifications
Technology tags used to group this patent with similar filings.
- Citations and related patents
Prior art links and similar publications in this corpus.
Abstract
Official abstract text for this publication.
Dynamic features are utilized with CRFs to handle long-distance dependencies of output labels. The dynamic features present a probability distribution involved in explicit distance from/to a special output label that is pre-defined according to each application scenario. Besides the number of units in the segment (from the previous special output label to the current unit), the dynamic features may also include the sum of any basic features of units in the segment. Since the added dynamic features are involved in the distance from the previous specific label, the searching lattice associated with Viterbi searching is expanded to distinguish the nodes with various distances. The dynamic features may be used in a variety of different applications, such as Natural Language Processing, Text-To-Speech and Automatic Speech Recognition. For example, the dynamic features may be used to assist in prosodic break and pause prediction.
First claim
Opening claim text (preview).
What is claimed is: 1. A method, performed by a processor of a computer system, utilizing an expanded Conditional Random Field (eCRF) model, the method comprising: performing actions, by an eCRF manager, relating to eCRF applications, the actions comprising: accessing an eCRF model that includes modeling of labels with long-distance dependencies; constructing an expanded searching lattice comprising nodes and edges; extracting features for the nodes and edges in the searchin…
Assignees
Inventors
Classifications
Physics · mapped topic
Physics · mapped topic
- G10L15/083Primary
Physics · mapped topic
Patent family
Related publications grouped by family.
External sources
Next steps
Free tools are coming soon. Tell us what you want to track and we'll notify you.
Frequently asked questions
Answers are generated from the same data shown on this page.
- What does patent US9037460B2 cover?
- Dynamic features are utilized with CRFs to handle long-distance dependencies of output labels. The dynamic features present a probability distribution involved in explicit distance from/to a special output label that is pre-defined according to each application scenario. Besides the number of units in the segment (from the previous special output label to the current unit), the dynamic features…
- Who is the assignee on this patent?
- Luan Jian, Wang Linfang, Xia Hairong, and 3 more
- What technology area does this patent fall under?
- Primary CPC classification G10L15/083. Mapped technology areas include Physics.
- When was this patent published?
- Publication date Tue May 19 2015 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
- What related patents are in patentsdb?
- We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).