Query engine for processing voice based queries including semantic decoding

IM Bennett - US Patent 7,725,307, 2010 - Google Patents
Primary Examiner Martin Lerner Related US Application Data(74) Attorney, Agent, or Firm
PatentBest; Andrew McAleavey (63) Continuation-in-part of application No. 09/439,145, filed …

Distributed real time speech recognition system

IM Bennett, BR Babu, K Morkhandikar… - US Patent …, 2015 - Google Patents
(57) ABSTRACT A real-time system incorporating speech recognition and lin guistic
processing for recognizing a spoken query by a user and distributed between client and …

Speech recognition system for client devices having differing computing capabilities

IM Bennett - US Patent 7,698,131, 2010 - Google Patents
US7698131B2 - Speech recognition system for client devices having differing computing
capabilities - Google Patents US7698131B2 - Speech recognition system for client devices …

Multi-language speech recognition system

I Bennett, BR Babu, K Morkhandikar… - US Patent 9,190,063, 2015 - Google Patents
(51) Int. Cl. 5,774,859 A 6/1998 Houser et al. GOL 5/30(2013.01) 5,794,050 A 8/1998
Dahlgren et al. 5,794, 193 A 8, 1998 Gorin GOL 7/22(2013.01) 5,797,123. A 8/1998 Chou et …

Jhu aspire system: Robust lvcsr with tdnns, ivector adaptation and rnn-lms

V Peddinti, G Chen, V Manohar, T Ko… - … IEEE Workshop on …, 2015 - ieeexplore.ieee.org
Multi-style training, using data which emulates a variety of possible test scenarios, is a
popular approach towards robust acoustic modeling. However acoustic models capable of …

Pronunciation modeling by sharing Gaussian densities across phonetic models

M Saraclar, H Nock, S Khudanpur - Computer Speech & Language, 2000 - Elsevier
Conversational speech exhibits considerable pronunciation variability, which has been
shown to have a detrimental effect on the accuracy of automatic speech recognition. There …

[PDF][PDF] Pronunciation and silence probability modeling for ASR.

G Chen, H Xu, M Wu, D Povey, S Khudanpur - Interspeech, 2015 - isca-archive.org
In this paper we evaluate the WER improvement from modeling pronunciation probabilities
and word-specific silence probabilities in speech recognition. We do this in the context of …

Method of interacting through speech with a web-connected server

IM Bennett - US Patent 8,352,277, 2013 - Google Patents
US8352277B2 - Method of interacting through speech with a web-connected server - Google
Patents US8352277B2 - Method of interacting through speech with a web-connected server …

Language model and speaking rate adaptation for spontaneous presentation speech recognition

H Nanjo, T Kawahara - IEEE Transactions on speech and …, 2004 - ieeexplore.ieee.org
The paper addresses adaptation methods to language model and speaking rate (SR) of
individual speakers which are two major problems in automatic transcription of spontaneous …

Using prosodic and lexical information for speaker identification

F Weber, L Manganaro, B Peskin… - 2002 IEEE International …, 2002 - ieeexplore.ieee.org
We investigate the incorporation of larger time-scale information, such as prosody, into
standard speaker ID systems. Our study is based on the Extended Data Task of the NIST …