1
Barbara J Wheatley, Charles T Hemphill, Thomas D Fisher, George R Doddington: System and method for time aligning speech. Robert L Troike, Richard L Donaldson, July 26, 1994: US05333275 (212 worldwide citation)

A method and system are provided for time aligning speech. Speech data is input representing speech signals from a speaker. An orthographic transcription is input including a plurality of words transcribed from the speech signals. A sentence model is generated indicating a selected order of the word ...


2
Shivaling S Mahant Shetti, Derek J Smith, Basavaraj I Pawate, George R Doddington, Warren L Bean, Mark G Harward, Thomas J Aton: Distributed processing memory chip with embedded logic having both data memory and broadcast memory. Texas Instruments Incorporated, Jacqueline J Garner, W James Brady III, Richard L Donaldson, May 12, 1998: US05751987 (200 worldwide citation)

Memory chips with data memory (202), embedded logic (206) and broadcast memory (204) for two modes of operation are disclosed. A first mode of operation is the usual memory mode expected of a data RAM. The second mode of operation allows localized computation and/or processing of the data in data me ...


3
George R Doddington, Basavaraj I Pawate: Efficient pruning algorithm for hidden markov model speech recognition. Texas Instruments Incorporated, L Joy Griebenow, James T Comfort, Melvin Sharp, December 11, 1990: US04977598 (169 worldwide citation)

An efficient pruning method reduces central processing unit (CPU) loading during real time speech recognition by instructing the CPU to compare a current state's previously calculated probability score against a predetermined threshold value and to discard hypothesis containing states with probabili ...


4
Lorin P Netsch, George R Doddington: Temporal decorrelation method for robust speaker verification. Texas Instruments Incorporated, L Joy Griebenow, William E Hiller, Richard Donaldson, November 24, 1992: US05167004 (104 worldwide citation)

A speaker voice verification system uses temporal decorrelation linear transformation and includes a collector for receiving speech inputs from an unknown speaker claiming a specific identity, a word-level speech features calculator operable to use a temporal decorrelation linear transformation for ...


5
Thomas B Schalk, George R Doddington: Speaker-dependent connected speech word recognizer. Texas Instruments Incorporated, William E Hiller, N Rhys Merrett, Melvin Sharp, May 16, 1989: US04831551 (90 worldwide citation)

Speech recognition is improved using reference pattern templates which have an added noise signal (noise floor) to avoid LPC high-gain synthesizer instability at low signal levels. Also, input signal frames have a length one-half that of reference frames whereby dynamic time warp computation steps a ...


6
Masud Arjmand, George R Doddington: Voice messaging system with pitch-congruent baseband coding. Texas Instruments Incorporated, William E Hiller, James T Comfort, Melvin Sharp, May 19, 1987: US04667340 (81 worldwide citation)

An improved voice messaging system using LPC baseband speech coding. In standard LPC-based baseband speech coding techniques, LPC parameters plus a residual signal are transmitted. To save band width, the residual signal is filtered so that only a fraction of its full bandwidth (e.g., the bottom 1 K ...


7
George R Doddington: Speech analysis/synthesis system with silence suppression. Texas Instruments Incorporated, Kenneth C Hill, James T Comfort, Melvin Sharp, September 22, 1987: US04696039 (58 worldwide citation)

Silence suppression in speech synthesis systems is achieved by detecting and processing only segments of voice activity. A segment is classified as "speech" if the energy of the signal is greater than an adaptively adjusted threshold. The adaptively adjusted threshold is preferably defined as the ma ...


8
Jayant M Naik, George R Doddington: Fixed text speaker verification method and apparatus. Texas Instruments Incorporated, W Daniel Swayze Jr, W James Brady III, Richard L Donaldson, August 20, 1996: US05548647 (57 worldwide citation)

Speaker verification is performed by computing principal components of a fixed text statement comprising a speaker identification code and a two-word phrase, and principal spectral components of a random word phrase. A multi-phrase strategy is utilized in access control to allow successive verificat ...


9
George R Doddington, Yeunung Chen, R Gary Leonard: Method for utilizing formant frequencies in speech recognition. Texas Instruments Incorporated, William E Hiller, Richard L Donaldson, September 8, 1992: US05146539 (56 worldwide citation)

A speech recognizer which utilizes hypothesis testing to determine formant frequencies for use in speech recognition. A pre-processor (36) receives speech signal frames and utilizes linear predictive coding to generate all formant frequency candidates. An optimum formant selector (38) operates with ...


10
Joseph W Picone, George R Doddington: Very low rate speech encoder and decoder. Texas Instruments Incorporated, William E Hiller, N Rhys Merrett, Melvin Sharp, March 21, 1989: US04815134 (55 worldwide citation)

A speech encoder is disclosed quantizing speech information with respect to energy, voicing and pitch parameters to provide a fixed number of bits per block of frames. Coding of the parameters takes place for each N frames, which comprise a block, irrespective of phonemic boundaries. Certain frames ...