Luca E Rigazio

6513004, Jan 28, 2003

Nov 24, 1999

09/449053

Luca Rigazio - Santa Barbara CA
David Kryze - Santa Barbara CA
Ted Applebaum - Santa Barbara CA
Jean-Claude Junqua - Santa Barbara CA

Matsushita Electric Industrial Co., Ltd. - Osaka

G10L 1504

704254, 704249, 704236

The acoustic speech signal is decomposed into wavelets arranged in an asymmetrical tree data structure from which individual nodes may be selected to best extract local features, as needed to model specific classes of sound units. The wavelet packet transformation is smoothed through integration and compressed to apply a non-linearity prior to discrete cosine transformation. The resulting subband features such as cepstral coefficients may then be used to construct the speech recognizers speech models. Using the local feature information extracted in this manner allows a single recognizer to be optimized for several different classes of sound units, thereby eliminating the need for parallel path recognizers.

6526379, Feb 25, 2003

Nov 29, 1999

09/450387

Luca Rigazio - Santa Barbara CA
Brice Tsakam - Vernier, CH
Jean-Claude Junqua - Santa Barbara CA

Matsushita Electric Industrial Co., Ltd. - Osaka

G10L 1506

704245, 704256, 704255, 704246, 704243, 704244

The discriminative clustering technique tests a provided set of Gaussian distributions corresponding to an acoustic vector space. A distance metric, such as the Bhattacharyya distance, is used to assess which distributions are sufficiently proximal to be merged into a new distribution. Merging is accomplished by computing the centroid of the new distribution by minimizing the Bhattacharyya distance between the parameters of the Gaussian distributions being merged.

6529872, Mar 4, 2003

Apr 18, 2000

09/551001

Christophe Cerisara - Goleta CA
Luca Rigazio - Santa Barbara CA
Robert Boman - Thousand Oaks CA
Jean-Claude Junqua - Santa Barbara CA

Matsushita Electric Industrial Co., Ltd. - Osaka

G10L 1506

704250, 704256

The improved noise adaptation technique employs a linear or non-linear transformation to the set of Jacobian matrices corresponding to an initial noise condition. An -adaptation parameter or artificial intelligence operation is employed in a linear or non-linear way to increase the adaptation bias added to the speech models. This corrects shortcomings of conventional Jacobian adaptation, which tend to underestimate the effect of noise. The improved adaptation technique is further enhanced by a reduced dimensionality, principal component analysis technique that reduces the computational burden, making the adaptation technique beneficial in embedded recognition systems.

6571174, May 27, 2003

Aug 14, 2001

09/929634

Luca Rigazio - Santa Barbara CA
Philippe R. Morin - Santa Barbara CA
Jean-Claude Junqua - Santa Barbara CA

Matsushita Electric Industrial Co., Ltd. - Osaka

G01C 2134

701209, 701117, 34235707, 34235709

A navigation apparatus is disclosed which may be used by law enforcement personnel for rapid intervention to a location while adding safety and reliability to the process. The apparatus includes a computer system, having an operating system, memory and a user interface. The system further includes a positioning system, such as a GPS system for determining the position of a vehicle. The positioning system communicates with the operating system. An information database, communicating with the operating system, contains data related to routing information concerning routes for travel by the vehicle. The routing information includes safety information concerning route safety in the traveling region accessible by the vehicle. The apparatus further includes a routing system in communication with the operating system that determines a route based at least in part on the routing information. Driving directions and call information are provided multi-modally to provide the officer with critical information in an efficient and timely fashion.

6687672, Feb 3, 2004

Mar 15, 2002

10/099428

Younes Souilmi - Juan-les Pins, FR
Luca Rigazio - Santa Barbara CA
Patrick Nguyen - Santa Barbara CA
Jean-Claude Junqua - Santa Barbara CA

Matsushita Electric Industrial Co., Ltd. - Osaka

G10L 1508

704237, 704233, 704226, 704219, 704216, 381 943

Methods and apparatus for blind channel estimation of a speech signal corrupted by a communication channel are provided. One method includes converting a noisy speech signal into either a cepstral representation or a log-spectral representation; estimating a correlation of the representation of the noisy speech signal; determining an average of the noisy speech signal; constructing and solving, subject to a minimization constraint, a system of linear equations utilizing a correlation structure of a clean speech training signal, the correlation of the representation of the noisy speech signal, and the average of the noisy speech signal; and selecting a sign of the solution of the system of linear equations to estimate an average clean speech signal in a processing window.

6691091, Feb 10, 2004

Jul 31, 2000

09/628376

Christophe Cerisara - Ars-sur-Moselle, FR
Luca Rigazio - Santa Barbara CA
Robert Boman - Thousand Oaks CA
Jean-Claude Junqua - Santa Barbara CA

Matsushita Electric Industrial Co., Ltd. - Osaka

G10L 1506

704255, 704244

A noise adaptation system and method provide for noise adaptation in a speech recognition system. The method includes the steps of generating a reference model based on a training speech signal, and compensating the reference model for additive noise in the cepstral domain. The reference model is also compensated for convolutional noise in the cepstral domain. In one embodiment, the convolutional noise is compensated for by estimating a convolutional bias between the reference model and a target speech signal. The estimated convolutional bias is transformed with a channel adaptation matrix, and the transformed convolutional bias is added to the reference model in the cepstral domain.

6879954, Apr 12, 2005

Apr 22, 2002

10/127184

Patrick Nguyen - Santa Barbara CA, US
Luca Rigazio - Santa Barbara CA, US

Matsushita Electric Industrial Co., Ltd. - Osaka

G10L015/00
G06F015/76

704238, 704231, 704243, 704254, 712 1

A method is provided for improving pattern matching in a speech recognition system having a plurality of acoustic models. The improved method includes: receiving continuous speech input; generating a sequence of acoustic feature vectors that represent temporal and spectral behavior of the speech input; loading a first group of acoustic feature vectors from the sequence of acoustic feature vectors into a memory workspace accessible to a processor; loading an acoustic model from the plurality of acoustic models into the memory workspace; and determining a similarity measure for each acoustic feature vector of the first group of acoustic feature vectors in relation to the acoustic model. Prior to retrieving another group of acoustic feature vectors, similarity measures are computed for the first group of acoustic feature vectors in relation to each of the acoustic models employed by the speech recognition system. In this way, the improved method reduces the number I/O operations associated with loading and unloading each acoustic model into memory.

6889189, May 3, 2005

Sep 26, 2003

10/672167

Robert Boman - Thousand Oaks CA, US
Luca Rigazio - Santa Barbara CA, US
Brian Hanson - Goleta CA, US
Rathinavelu Chengalvarayan - Santa Barbara CA, US

Matsushita Electric Industrial Co., Ltd. - Osaka

G10L021/00

704270, 704275

System speakers are switched to function as sound input transducers to improve recognizer performance and to support recognizer features. A crossbar switch is selectively activated, either manually or under software control, to allow system loudspeakers to function as sound input transducers that supplement the recognition system microphone or microphone array. Using loudspeakers as “microphones” improves speech recognition in noisy environments, thus attaining better recognition performance with little added system cost. The loudspeakers, positioned in physically separate locations also provide spatial information that can be used to determine the location of the person speaking and thereby offer different functionality for different persons. Acoustic models are selected based on environmental and vehicle operating conditions and may be adapted dynamically using ambient information obtained using the loudspeakers as sound input transducers.