METHODS AND SYSTEMS FOR SPEECH ADAPTATION DATA

• US 20130325453A1
• Filed: 09/10/2012
• Published: 12/05/2013
• Est. Priority Date: 05/31/2012
• Status: Abandoned Application

• Current Assignee: Elwha LLC (Intellectual Ventures LLC)
• Original Assignee: Elwha LLC (Intellectual Ventures LLC)
• Inventors: Levien, Royce A., Lord, Richard T., Lord, Robert W., Malamud, Mark A.
• Application Number:
  US13/609,145
• Publication Number:
  US 20130325453A1
• Time in Patent Office: Days
• US Class Current: 704/201
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence

Abstract

Computationally implemented methods and systems include receiving speech data correlated to one or more words spoken by a particular party, receiving adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the received speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party, obtaining target data regarding a target configured to process at least a portion of the received speech data, and determining whether to apply the adaptation data for processing at least a portion of the received speech data, at least partly based on the acquired target data. In addition to the foregoing, other aspects are described in the claims, drawings, and text.

Claims

1-329. -329. (canceled)

330. A device, comprising:

a speech data correlated to one or more particular party spoken words receiving module;

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device receiving module configured to receive adaptation data that is at least partly based on at least one speech interaction of a particular party that is discrete from the received speech data, wherein at least a portion of the adaptation data has been stored on a particular device associated with the particular party;

a target data regarding a target configured to process at least a portion of the received speech data obtaining module configured to obtain target data regarding a target configured to process at least a portion of the received speech data;

an application of adaptation data for processing at least a portion of the received speech data determining module; and

an adaptation result data based on at least one aspect of the received speech data transmitting module.

338. The device of claim 330, wherein said speech data correlated to one or more particular party spoken words receiving module comprises:

a speech data comprising a representation of particular party spoken word receiving module.

342. The device of claim 338, wherein said speech data comprising a representation of particular party spoken word receiving module comprises:

a speech data corresponding to partially processed particular party spoken word receiving module configured to receive speech data corresponding to received speech spoken by the particular party that has been at least partially processed.

354. The device of claim 330, wherein said speech data correlated to one or more particular party spoken words receiving module comprises:

a speech data correlated to one or more particular party spoken words receiving from further device module.

355. The device of claim 354, wherein said speech data correlated to one or more particular party spoken words receiving from further device module comprises:

an audio data derived from one or more particular party spoken words receiving from further device module.

358. The device of claim 355, wherein said audio data derived from one or more particular party spoken words receiving from further device module comprises:

an audio data derived from one or more particular party words detected by particular device receiving from further device module.

378. The device of claim 330, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device receiving module comprises:

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device module.

379. The device of claim 378, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device module comprises:

an adaptation data originating at further device and at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device module.

380. The device of claim 378, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device module comprises:

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device related to the particular device module.

381. The device of claim 380, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device related to the particular device module comprises:

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device associated with the particular party module.

384. The device of claim 378, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device module comprises:

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device acquiring from a further device that received the adaptation data from the particular device module.

400. The device of claim 330, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device receiving module comprises:

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data and using same utterance as speech that is part of speech data, and has been stored on a particular party-associated particular device receiving module.

405. The device of claim 330, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device receiving module comprises:

an adaptation data comprising instructions for modifying one or more portions of a speech recognition component of a target device that are at least partly based on one or more particular party speech interactions, and has been stored on a particular party-associated particular device receiving module.

406. The device of claim 330, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device receiving module comprises:

an adaptation data comprising a location of instructions for modifying one or more portions of a speech recognition component of a target device that are at least partly based on one or more particular party speech interactions, and has been stored on a particular party-associated particular device receiving module.

411. The device of claim 330, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device receiving module comprises:

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and at least a portion of which originated at a particular party-associated particular device receiving module.

412. The device of claim 330, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device receiving module comprises:

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and at least a portion of which was transmitted to a remote location from a particular party-associated particular device receiving from remote location module.

413. The device of claim 330, wherein said adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data, and has been stored on a particular party-associated particular device receiving module comprises:

an adaptation data at least partly based on discrete speech interaction of particular party separate from detected speech data receiving module; and

a further data adding to adaptation data module configured to add further data to the received adaptation data.

420. The device of claim 330, wherein said target data regarding a target configured to process at least a portion of the received speech data obtaining module comprises:

a data indicating that the adaptation data is configured to be applied to the target device to assist in processing at least a portion of the speech data receiving from a speech processing component module.

425. The device of claim 330, wherein said target data regarding a target configured to process at least a portion of the received speech data obtaining module comprises:

a target data regarding a target configured to process at least a portion of the received speech data generating module.

426. The device of claim 330, wherein said target data regarding a target configured to process at least a portion of the received speech data obtaining module comprises:

a speech data configurable to be processed by a speech recognition component to which the adaptation data has been applied determining module; and

a target data regarding intended target device generating based on determination module.

427. The device of claim 426, wherein said speech data configurable to be processed by a speech recognition component to which the adaptation data has been applied determining module comprises:

an at least a portion of speech data analyzing module; and

a target data regarding intended target device determining at least partly based on the analyzing at least a portion of speech data module.

428. The device of claim 427, wherein said at least a portion of speech data analyzing module comprises:

an at least a portion of speech data analyzing using an adaptation data-applied speech recognition component module.

429. The device of claim 428, wherein said at least a portion of speech data analyzing using an adaptation data-applied speech recognition component module comprises:

an at least a portion of speech data analyzing using an adaptation data-applied speech recognition component of target device module.

430. The device of claim 428, wherein said at least a portion of speech data analyzing using an adaptation data-applied speech recognition component module comprises:

an at least a portion of speech data analyzing using an adaptation data-applied speech recognition component of further device module.

433. The device of claim 330, wherein said target data regarding a target configured to process at least a portion of the received speech data obtaining module comprises:

a target device configurable to process received speech data determining module; and

a target data regarding target device generating based on determination regarding the target device module.

434. The device of claim 433, wherein said target device configurable to process received speech data determining module comprises:

an at least a portion of the speech data analyzing module; and

a target device configurable to process speech data determining at least partly based on result of analyzing at least a portion of the speech data module.

435. The device of claim 433, wherein said target device configurable to process received speech data determining module comprises:

a header data indicating a type of intended target device that is configured to process received speech data extracting from received speech data header module; and

a type of target device is same type as type of intended target device determining module.

436. The device of claim 435, wherein said header data indicating a type of intended target device that is configured to process received speech data extracting from received speech data header module comprises:

a header data indicating a manufacturer of intended target device that is configured to process received speech data extracting from received speech data header module.

437. The device of claim 435, wherein said header data indicating a type of intended target device that is configured to process received speech data extracting from received speech data header module comprises:

a header data indicating a type of input accepted by one or more intended target devices configured to process received speech data extracting from received speech data header module.

438. The device of claim 437, wherein said header data indicating a type of input accepted by one or more intended target devices configured to process received speech data extracting from received speech data header module comprises:

a header data indicating a data format accepted by one or more intended target devices configured to process received speech data extracting from received speech data header module.

439. The device of claim 437, wherein said header data indicating a type of input accepted by one or more intended target devices configured to process received speech data extracting from received speech data header module comprises:

a header data indicating one or more word categories accepted by one or more intended target devices configured to process received speech data extracting from received speech data header module.

442. The device of claim 330, wherein said target data regarding a target configured to process at least a portion of the received speech data obtaining module comprises:

a target data regarding a target device configured to process at least a portion of speech data receiving module.

444. The device of claim 442, wherein said target data regarding a target device configured to process at least a portion of speech data receiving module comprises:

a target data regarding a target device configured to process at least a portion of speech data receiving from a further device module.

446. The device of claim 444, wherein said target data regarding a target device configured to process at least a portion of speech data receiving from a further device module comprises:

a target data regarding a target device configured to process at least a portion of speech data receiving from a further device configured to apply at least a portion of the adaptation data module.

447. The device of claim 444, wherein said target data regarding a target device configured to process at least a portion of speech data receiving from a further device module comprises:

a target data regarding a target device configured to process at least a portion of speech data receiving from a further device configured to process the speech data less efficiently than the target device module.

448. The device of claim 444, wherein said target data regarding a target device configured to process at least a portion of speech data receiving from a further device module comprises:

a target data regarding a target device configured to process at least a portion of speech data receiving from a further device for which the speech data is unintended module.

449. The device of claim 444, wherein said target data regarding a target device configured to process at least a portion of speech data receiving from a further device module comprises:

a target data regarding a target device configured to process at least a portion of speech data and target data indicating the speech data was determined to be intended for the target device receiving from a further device module.

450. The device of claim 330, wherein said target data regarding a target configured to process at least a portion of the received speech data obtaining module comprises:

a data identifying the target device receiving module.

453. The device of claim 330, wherein said target data regarding a target configured to process at least a portion of the received speech data obtaining module comprises:

an address of the target device receiving module.

455. The device of claim 330, wherein said target data regarding a target configured to process at least a portion of the received speech data obtaining module comprises:

a target data regarding an intended application module configured to process at least a portion of the received speech data obtaining module.

462. The device of claim 330, wherein said application of adaptation data for processing at least a portion of the received speech data determining module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining based on acquired target data comprising an indication of intended device module.

463. The device of claim 330, wherein said application of adaptation data for processing at least a portion of the received speech data determining module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining based on acquired target data comprising an indication that speech data has arrived at intended device module.

467. The device of claim 330, wherein said application of adaptation data for processing at least a portion of the received speech data determining module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining when acquired target data indicates capability of adaptation data application module.

469. The device of claim 330, wherein said application of adaptation data for processing at least a portion of the received speech data determining module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining against based on acquired target data indicating presence of one or more other devices configured to efficiently apply adaptation data module.

471. The device of claim 330, wherein said application of adaptation data for processing at least a portion of the received speech data determining module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining based on one or more characteristics of one or more applications and target data indicating a presence of the one or more applications module.

472. The device of claim 330, wherein said application of adaptation data for processing at least a portion of the received speech data determining module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining against based acquired target data comprising one or more characteristics of one or more applications module.

474. The device of claim 472, wherein said application of adaptation data for processing at least a portion of the received speech data determining against based acquired target data comprising one or more characteristics of one or more applications module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining against based acquired target data comprising a developer of one or more applications module.

476. The device of claim 330, wherein said application of adaptation data for processing at least a portion of the received speech data determining module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining based on one or more user-controlled preference flags module.

477. The device of claim 330, wherein said application of adaptation data for processing at least a portion of the received speech data determining module comprises:

an application of adaptation data for processing at least a portion of the received speech data determining based on operating system decision module.

480. The device of claim 330, wherein said adaptation result data based on at least one aspect of the received speech data transmitting module comprises:

an adaptation result data based on processing received speech data transmitting module.

481. The device of claim 480, wherein said adaptation result data based on processing received speech data transmitting module comprises:

an adaptation result data indicating at least a portion of received speech data has been processed transmitting module.

482. The device of claim 330, wherein said adaptation result data based on at least one aspect of the received speech data transmitting module comprises:

an adaptation result data indicating that at least a portion of the received speech data is intended for an other device transmitting module.

483. The device of claim 482, wherein said adaptation result data indicating that at least a portion of the received speech data is intended for an other device transmitting module comprises:

an adaptation result data indicating that at least a portion of the received speech data is intended for an other device transmitting to the other device module.

484. The device of claim 482, wherein said adaptation result data indicating that at least a portion of the received speech data is intended for an other device transmitting module comprises:

an adaptation result data comprising the adaptation data and indicating that at least a portion of the received speech data is intended for an other device transmitting module.

486. The device of claim 330, wherein said adaptation result data based on at least one aspect of the received speech data transmitting module comprises:

an adaptation result data based on a measure of success of at least one portion of a speech-facilitated transaction corresponding to the received speech data transmitting module.

491. The device of claim 330, wherein said adaptation result data based on at least one aspect of the received speech data transmitting module comprises:

an adaptation result data comprising a list of at least one word that was a portion of the received speech data and that was improperly interpreted during speech data processing transmitting module.

331. (canceled)

332. (canceled)

333. (canceled)

334. (canceled)

335. (canceled)

336. (canceled)

337. (canceled)

339. (canceled)

340. (canceled)

341. (canceled)

343. (canceled)

344. (canceled)

345. (canceled)

346. (canceled)

347. (canceled)

348. (canceled)

349. (canceled)

350. (canceled)

351. (canceled)

352. (canceled)

353. (canceled)

356. (canceled)

357. (canceled)

359. (canceled)

360. (canceled)

361. (canceled)

362. (canceled)

363. (canceled)

364. (canceled)

365. (canceled)

366. (canceled)

367. (canceled)

368. (canceled)

369. (canceled)

370. (canceled)

371. (canceled)

372. (canceled)

373. (canceled)

374. (canceled)

375. (canceled)

376. (canceled)

377. (canceled)

382. (canceled)

383. (canceled)

385. (canceled)

386. (canceled)

387. (canceled)

388. (canceled)

389. (canceled)

390. (canceled)

391. (canceled)

392. (canceled)

393. (canceled)

394. (canceled)

395. (canceled)

396. (canceled)

397. (canceled)

398. (canceled)

399. (canceled)

401. (canceled)

402. (canceled)

403. (canceled)

404. (canceled)

407. (canceled)

408. (canceled)

409. (canceled)

410. (canceled)

414. (canceled)

415. (canceled)

416. (canceled)

417. (canceled)

418. (canceled)

419. (canceled)

421. (canceled)

422. (canceled)

423. (canceled)

424. (canceled)

431. (canceled)

432. (canceled)

440. (canceled)

441. (canceled)

443. (canceled)

445. (canceled)

451. (canceled)

452. (canceled)

454. (canceled)

456. (canceled)

457. (canceled)

458. (canceled)

459. (canceled)

460. (canceled)

461. (canceled)

464. (canceled)

465. (canceled)

466. (canceled)

468. (canceled)

470. (canceled)

473. (canceled)

475. (canceled)

478. (canceled)

479. (canceled)

485. (canceled)

487. (canceled)

488. (canceled)

489. (canceled)

490. (canceled)

492. (canceled)