Aruna Bayya from 130 Heritage Ave, Ashland, MA 01721, age 66, Phone: (508) 881-7470

Resumes

Aruna Bayya

View page

Publications

Us Patents

Speaker Dependent Speech Recognition Training Using Simplified Hidden Markov Modeling And Robust End-Point Detection

View page

US Patent:

6405168, Jun 11, 2002

Filed:

Sep 30, 1999

Appl. No.:

09/410215

Inventors:

Aruna Bayya - Irvine CA
Dianne L. Steiger - Irvine CA

Assignee:

Conexant Systems, Inc. - Newport Beach CA

International Classification:

G10L 1514

US Classification:

704256, 704255, 704253

Abstract:

A speech recognition training system that provides for model generation to be used within speaker dependent speech recognition systems requiring very limited training data, including single token training. The present invention provides a very fast and reliable training method based on the segmentation of a speech signal for subsequent estimating of speaker dependent word models. In addition, the invention provides for a robust method of performing end-point detection of a word contained within a speech utterance or speech signal. The invention is geared ideally for speaker dependent speech recognition systems that employ word-based speaker dependent models. The invention provides the end-point detection method is operable to extract a desired word or phrase from a speech signal that is recorded in varying degrees of undesirable background noise. In addition, the invention provides a simplified method of building the speaker dependent models using a simplified hidden Markov modeling method. The invention requires very limited training and is operable within systems having constrained budgets of memory and processing resources.

Method And System For Objectively Evaluating Speech

View page

US Patent:

6446038, Sep 3, 2002

Filed:

Apr 1, 1996

Appl. No.:

08/627249

Inventors:

Aruna Bayya - Louisville CO
Marvin Vis - Boulder CO

Assignee:

Qwest Communications International, Inc. - Denver CO

International Classification:

G10L 1500

US Classification:

704232, 704231, 704236

Abstract:

A method and system for objectively evaluating the quality of speech in a voice communication system. A plurality of speech reference vectors is first obtained based on a plurality of clean speech samples. A corrupted speech signal is received and processed to determine a plurality of distortions derived from a plurality of distortion measures based on the plurality of speech reference vectors. The plurality of distortions are processed by a non-linear neural network model to generate a subjective score representing user acceptance of the corrupted speech signal. The non-linear neural network model is first trained on clean speech samples as well as corrupted speech samples through the use of backpropagation to obtain the weights and bias terms necessary to predict subjective scores from several objective measures.

Smart Training And Smart Scoring In Sd Speech Recognition System With User Defined Vocabulary

View page

US Patent:

6535850, Mar 18, 2003

Filed:

Mar 9, 2000

Appl. No.:

09/522448

Inventors:

Aruna Bayya - Irvine CA

Assignee:

Conexant Systems, Inc. - Newport Beach CA

International Classification:

G10L 1506

US Classification:

704239, 704243, 704254

Abstract:

In a speech training and recognition system, the current invention detects and warns the user about the similar sounding entries to vocabulary and permits entry of such confusingly similar terms which are marked along with the stored similar terms to identify the similar words. In addition, the states in similar words are weighted to apply more emphasis to the differences between similar words than the similarities of such words. Another aspect of the current invention is to use modified scoring algorithm to improve the recognition performance in the case where confusing entries were made to the vocabulary despite the warning. Yet another aspect of the current invention is to detect and warn the user about potential problems with new entries such as short words and two or more word entries with long silence periods in between words. Finally, the current invention also includes alerting the user about the dissimilarity of the multiple tokens of the same vocabulary item in the case of multiple-token training.

Automatic Speech Recognition To Control Integrated Communication Devices

View page

US Patent:

20050149337, Jul 7, 2005

Filed:

Feb 17, 2005

Appl. No.:

11/060193

Inventors:

Ayman Asadi - Laguna Niguel CA, US
Aruna Bayya - Irvine CA, US
Dianne Steiger - Irvine CA, US

Assignee:

Conexant Systems, Inc. - Newport Beach CA

International Classification:

G10L015/00

US Classification:

704277000

Abstract:

An integrated communications device provides an automatic speech recognition (ASR) system to control communication functions of the communications device. The ASR system includes an ASR engine and an ASR control module with an out-of-vocabulary rejection capability. The ASR engine performs speaker independent and dependent speech recognition and also performs speaker dependent training. The ASR engine thus includes a speaker dependent recognizer, a speaker independent recognizer and a speaker dependent trainer. Speaker independent models and speaker dependent models stored on the communications device are used by the ASR engine. A speaker dependent mode of the ASR system provides flexibility to add new language independent vocabulary. A speaker independent mode of the ASR system provides the flexibility to select desired commands from a predetermined list of speaker independent vocabulary. The ASR control module, which can be integrated into an application, initiates the appropriate communication functions based on speech recognition results from the ASR engine. One way of implementing the ASR system is with a processor, controller and memory of the communications device. The communications device also can include a microphone and telephone to receive voice commands for the ASR system from a user.

Method And System For Region Based Filtering Of Speech

View page

US Patent:

59638990, Oct 5, 1999

Filed:

Aug 7, 1996

Appl. No.:

8/694654

Inventors:

Aruna Bayya - Irvine CA
Marvin L. Vis - Longmont CO

Assignee:

U S West, Inc. - Denver CO
MediaOne Group, Inc. - Englewood CO

International Classification:

G10L 302

US Classification:

704226

Abstract:

A speech signal divided into frames, each frame having a sound type, and a class is determined for each frame depending on the sound type of the frame. One of multiple filters is selected for each frame depending on the class of the frame. Each frame is filtered according to the filter selected, and the filtered frames combined to provide a filtered speech signal. The system includes filters and software.

Method Of Independently Creating And Using A Garbage Model For Improved Rejection In A Limited-Training Speaker-Dependent Speech Recognition System

View page

US Patent:

62231553, Apr 24, 2001

Filed:

Aug 14, 1998

Appl. No.:

9/134177

Inventors:

Aruna Bayya - Irvine CA

Assignee:

Conexant Systems, Inc. - Newport Beach CA

International Classification:

G10L 1506

US Classification:

704243

Abstract:

A speaker-dependent (SD) speech recognition system. The invention is specifically tailored to operate with very little training data, and also within hardware constraints such as limited memory and processing resources. A garbage model and a vocabulary model are generated and are subsequently used to perform comparison to a speech signal to decide if the speech signal is a specific vocabulary word. A word score is generated, and it is compared to a number of parameters, including an absolute threshold and another word score. Off-line training of the system is performed, in one embodiment, using compressed training tokens. A speech signal is segmented into scramble frames wherein the scramble frames have certain characteristics. For example, length is one characteristic of the scramble frames, each scramble frame having a length of an average vowel sound, or a predetermined length of nominally 40-50 msec. The invention is operable to be trained using as little as one single training token that is segmented.

Method And System For Adaptive Filtering Of Speech Signals Using Signal-To-Noise Ratio To Choose Subband Filter Bank

View page

US Patent:

58060251, Sep 8, 1998

Filed:

Aug 7, 1996

Appl. No.:

8/695097

Inventors:

Marvin L. Vis - Longmont CO
Aruna Bayya - Irvine CA

Assignee:

U S West, Inc. - Englewood CO

International Classification:

G10L 302

US Classification:

704226

Abstract:

A method and system for adaptively filtering a speech signal. The method includes decomposing the signal into subbands, which may include performing a discrete Fourier transform on the signal to provide approximately orthogonal components. The method also includes determining a speech quality indicator for each subband, which may include estimating a signal-to-noise ratio for each subband. The method also includes selecting a filter for filtering each subband depending on the speech quality indicator, which may include estimating parameters for the filter based on a clean speech signal. The method further includes determining an overall average error for the filtered subbands, which may include calculating a mean-squared error. The method still further includes identifying at least one filtered subband which, if excluded from the filtered speech signal, would reduce the overall average error determined, and combining, with exception of the filtered subbands identified, the filtered subbands to provide an estimated filtered speech signal. The system includes filters and software for performing the method.

Method And System For Identifying A Corrupted Speech Message Signal

View page

US Patent:

56849214, Nov 4, 1997

Filed:

Jul 13, 1995

Appl. No.:

8/501852

Inventors:

Aruna Bayya - Louisville CO
Louis A. Cox - Denver CO
Marvin L. Vis - Boulder CO

Assignee:

U S West Technologies, Inc. - Boulder CO

International Classification:

G10L 918

US Classification:

395 235

Abstract:

A method is disclosed for identifying corrupted speech signals in a call receiving mode of a voice messaging system. The method includes the step of receiving a message signal. The message signal represents an audio message. The method next includes the step of determining a signal quality. The signal quality is then compared to a threshold. If the signal quality is at least as great as the threshold, the audio data representing the message signal is stored in a memory. If the signal quality is not as great as the threshold, an indication signal is transmitted indicating that the signal quality is poor. A system is also disclosed for implementing the steps of the method.

Videos & Images