Invention Grant
- Patent Title: Discriminative training of multi-state barge-in models for speech processing
- Patent Title (中): 多国语言处理模式的歧视性训练
-
Application No.: US11930656Application Date: 2007-10-31
-
Publication No.: US08000971B2Publication Date: 2011-08-16
- Inventor: Andrej Ljolje
- Applicant: Andrej Ljolje
- Applicant Address: US GA Atlanta
- Assignee: AT&T Intellectual Property I, L.P.
- Current Assignee: AT&T Intellectual Property I, L.P.
- Current Assignee Address: US GA Atlanta
- Main IPC: G10L15/20
- IPC: G10L15/20 ; G10L15/28 ; G10L17/00 ; G10L11/00 ; G10L21/00

Abstract:
Disclosed are systems and methods for training a barge-in-model for speech processing in a spoken dialogue system comprising the steps of (1) receiving an input having at least one speech segment and at least one non-speech segment, (2) establishing a restriction of recognizing only speech states during speech segments of the input and non-speech states during non-speech segments of the input, (2) generating a hypothesis lattice by allowing any sequence of speech Hidden Markov Models (HMMs) and non-speech HMMs, (4) generating a reference lattice by only allowing speech HMMs for at least one speech segment and non-speech HMMs for at least one non-speech segment, wherein different iterations of training generates at least one different reference lattice and at least one reference transcription, and (5) employing the generated reference lattice as the barge-in-model for speech processing.
Public/Granted literature
- US20090112595A1 DISCRIMINATIVE TRAINING OF MULTI-STATE BARGE-IN MODELS FOR SPEECH PROCESSING Public/Granted day:2009-04-30
Information query