SPEECH RECOGNITION ADAPTATION SYSTEMS BASED ON ADAPTATION DATA

• US 20130325447A1
• Filed: 06/29/2012
• 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:
  US13/538,866
• Publication Number:
  US 20130325447A1
• Time in Patent Office: Days
• US Class Current: 704/201
• 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

Abstract

The instant application includes computationally-implemented systems and methods that include acquiring indication of a speech-facilitated transaction between a particular party and a target device, receiving adaptation data correlated to the particular party, the receiving facilitated by a particular device associated with the particular party, processing audio data from the particular party at least partly using the received adaptation data correlated to the particular party, and updating the adaptation data based at least in part on a result of the processed audio data, such that the updated adaptation data is configured to be transmitted to the particular device. In addition to the foregoing, other aspects are described in the claims, drawings, and text.

Claims

1-194. -194. (canceled)

195. A device, comprising:

a speech-facilitated transaction initiation between particular party and target device indicator acquiring module, configured to acquire indication of a speech-facilitated transaction between a particular party and a target device;

a particular party-correlated adaptation data receiving facilitated by particular party associated particular device module, configured to receive adaptation data correlated to the particular party, said receiving facilitated by a particular device associated with the particular party;

a particular party audio data processing using received adaptation data module configured to process audio data from the particular party at least partly using the received adaptation data correlated to the particular party; and

an adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module configured to update the adaptation data based at least in part on a result of the processed audio data, such that the updated adaptation data is configured to be transmitted to the particular device.

204. The device of claim 195, wherein said speech-facilitated transaction initiation between particular party and target device indicator acquiring module comprises:

a particular party and target device particular proximity indication acquiring module.

210. The device of claim 195, wherein said speech-facilitated transaction initiation between particular party and target device indicator acquiring module comprises:

a particular party speaking to target device indicator acquiring module.

214. The device of claim 210, wherein said particular party speaking to target device indicator acquiring module comprises:

a target sentence on output module of target device presenting module; and

a particular party speaking sentence detecting module.

220. The device of claim 210, wherein said particular party speaking to target device indicator acquiring module comprises:

a particular party speaking to target device indicator based on an orientation of a particular party body part acquiring module.

224. The device of claim 195, wherein said particular party-correlated adaptation data receiving facilitated by particular party associated particular device module comprises:

a particular party-correlated adaptation data comprising particular party speech characteristics, adaptation data location receiving from particular device module configured to receive adaptation data comprising at least one speech characteristic of the particular party, said adaptation data received from a location specified by the particular device.

225. The device of claim 195, wherein said particular party-correlated adaptation data receiving facilitated by particular party associated particular device module comprises:

a particular party-correlated adaptation data comprising particular party speech characteristics, adaptation data reception instruction receiving from particular device module configured to receive adaptation data comprising at least one speech characteristic of the particular party, wherein the particular device provides instructions for receiving the adaptation data.

229. The device of claim 195, wherein said particular party-correlated adaptation data receiving facilitated by particular party associated particular device module comprises:

a particular party audibly distinguishable sound pronunciation concept linking data receiving facilitated by particular party associated particular device module configured to receiving adaptation data comprising data linking pronunciation by the particular party of one or more audibly distinguishable sounds to one or more concepts, said receiving facilitated by a particular device associated with the particular party.

230. The device of claim 195, wherein said particular party-correlated adaptation data receiving facilitated by particular party associated particular device module comprises:

an authorization to receive adaptation data correlated to the particular party receiving from particular party associated particular device module configured to receive data comprising authorization to receive adaptation data correlated to the particular party, from a particular device associated with the particular party.

231. The device of claim 195, wherein said particular party-correlated adaptation data receiving facilitated by particular party associated particular device module comprises:

receiving a table of at least one word and at least one corresponding pronunciation of the at least one word by the particular party, from a smartphone associated with the particular party.

233. The device of claim 195, wherein said particular party audio data processing using received adaptation data module comprises:

a transmission of received adaptation data to speech recognition module configured to process audio data facilitating module configured to facilitate transmission of the received adaptation data to a speech recognition component configured to process the audio data.

234. The device of claim 233, wherein said transmission of received adaptation data to speech recognition module configured to process audio data facilitating module comprises:

a transmission of received adaptation data to target device-external speech recognition module configured to process audio facilitating module configured to facilitate transmission of the received adaptation data to a speech recognition component configured to process the audio data that is external to the target device.

237. The device of claim 195, wherein said particular party audio data processing using received adaptation data module comprises:

a received particular party phoneme database applying to audio data module configured to apply the received adaptation data correlated to the particular party to a speech recognition component of the target device, wherein the received adaptation data comprises a phoneme database.

238. The device of claim 195, wherein said particular party audio data processing using received adaptation data module comprises:

a received particular party audio data training set and transcript data applying to target device for interpreting audio data module configured to apply the received adaptation data correlated to the particular party to a speech recognition component of the target device, wherein the received adaptation data comprises a training set of audio data and corresponding transcript data.

239. The device of claim 195, wherein said particular party audio data processing using received adaptation data module comprises:

a received probability information of one or more words to target device speech recognition component applying module configured to apply the received adaptation data correlated to the particular party to a speech recognition component of the target device, wherein the received adaptation data comprises probability information of one or more words.

240. The device of claim 195, wherein said particular party audio data processing using received adaptation data module comprises:

a particular party speech processing using received adaptation data module configured to process received speech from the particular party at least partly using the received adaptation data correlated to the particular party.

243. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

an adaptation data configured to be transmitted to the particular device received result-based updating module configured to update the adaptation data based at least in part on a received result of the processed audio data, such that the updated adaptation data is configured to be transmitted to the particular device.

244. The device of claim 243, wherein said adaptation data configured to be transmitted to the particular device received result-based updating module comprises:

an adaptation data configured to be transmitted to the particular device received from further device result-based updating module configured to update the adaptation data based at least in part on a received result of the processed audio data from a further device, such that the updated adaptation data is configured to be transmitted to the particular device.

247. The device of claim 243, wherein said adaptation data configured to be transmitted to the particular device received result-based updating module comprises:

an adaptation data updating based on result received from particular party module configured to update the adaptation data based at least in part on a received result of the processed audio data from the particular party, such that the updated adaptation data is configured to be transmitted to the particular device.

248. The device of claim 243, wherein said adaptation data configured to be transmitted to the particular device received result-based updating module comprises:

an adaptation data updating based on result received from particular device module configured to update the adaptation data based at least in part on a received result of the processed audio data from the particular device, such that the updated adaptation data is configured to be transmitted to the particular device.

249. The device of claim 243, wherein said adaptation data configured to be transmitted to the particular device received result-based updating module comprises:

an adaptation data updating based on received result indicating particular party ranking of success of transaction module.

256. The device of claim 243, wherein said adaptation data configured to be transmitted to the particular device received result-based updating module comprises:

an adaptation data updating based on received result indicating post-transaction particular party determination of transaction quality module configured to update the adaptation data based at least in part on a received result indicating the particular party'"'"'s determination of quality of the speech-facilitated transaction in response to a query regarding the success of the speech-facilitated transaction.

257. The device of claim 243, wherein said adaptation data configured to be transmitted to the particular device received result-based updating module comprises:

a success of speech-facilitated transaction feedback from particular party requesting module; and

a particular party feedback regarding success of speech facilitated transaction receiving module.

258. The device of claim 257, wherein said success of speech-facilitated transaction feedback from particular party requesting module comprises:

a message requesting feedback from particular party regarding speech-facilitated transaction success presenting on target device module. configured to present a message using the target device requesting feedback from the particular party regarding a success of the speech-facilitated transaction.

259. The device of claim 258, wherein said message requesting feedback from particular party regarding speech-facilitated transaction success presenting on target device module comprises:

a message requesting feedback from particular party regarding speech-facilitated transaction success displaying on target device screen module.

261. The device of claim 257, wherein said success of speech-facilitated transaction feedback from particular party requesting module comprises:

a location of request for particular party speech-facilitated transaction feedback transmitting module configured to transmit a location at which feedback is requested from the particular party regarding a success of the speech-facilitated transaction.

263. The device of claim 257, wherein said success of speech-facilitated transaction feedback from particular party requesting module comprises:

a success of speech-facilitated transaction speech feedback requesting from particular party module configured to request feedback in a form of speech from the particular party regarding a success of the speech-facilitated transaction.

264. The device of claim 257, wherein said success of speech-facilitated transaction feedback from particular party requesting module comprises:

a success of speech-facilitated transaction non-speech feedback requesting from particular party module.

265. The device of claim 257, wherein said success of speech-facilitated transaction feedback from particular party requesting module comprises:

a sending a message requesting feedback regarding speech-facilitated transaction to particular device module.

270. The device of claim 257, wherein said particular party feedback regarding success of speech facilitated transaction receiving module comprises:

a particular party feedback regarding success of speech facilitated transaction receiving from a further device module configured to receive feedback from a further device regarding the success of the speech-facilitated transaction.

274. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

a determining that the adaptation data should not be modified and transmitting a recommendation not to modify adaptation data as updated adaptation data module.

275. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

a determining that the adaptation data should not be modified and transmitting an instruction to increment a speech-facilitated transaction counter as updated adaptation data module.

282. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

an adaptation data updating based at least in part on calculated word recognition rate of processed audio data module configured to update the adaptation data based at least in part on a calculated word recognition rate of the processed audio data, such that the updated adaptation data is configured to be transmitted to the particular device.

283. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

an adaptation data updating based at least in part on calculated phoneme recognition rate of processed audio data module configured to update the adaptation data based at least in part on a calculated phoneme recognition rate of the processed audio data, such that the updated adaptation data is configured to be transmitted to the particular device.

284. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

an adaptation data updating based at least in part on calculated confidence rate of processed audio data module configured to update the adaptation data based at least in part on a confidence rate of the processed audio data, such that the updated adaptation data is configured to be transmitted to the particular device.

285. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

an updating adaptation data based at least in part on comparisons between at least two repeated utterances detected in the processed audio data and configuring updated adaptation data for transmission to particular device module.

286. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

a transmitting updated adaptation data to particular device, said updating based at least in part on comparisons between at least two repeated utterances detected in the processed audio data module

288. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

a transmitting updated adaptation data to location specified by particular device, said updating based at least in part on processed audio data module configured to update the adaptation data based at least in part on one or more comparisons between at least two repeated utterances, such that the updated adaptation data is transmitted to a location specified by the particular device.

289. The device of claim 195, wherein said adaptation data configured to be transmitted to the particular device result of processed audio data-based updating module comprises:

a transmitting updated adaptation data to retrieval-configured location said updating based at least in part on processed audio data module configured to update the adaptation data based at least in part on one or more comparisons between at least two repeated utterances, such that the updated adaptation data is transmitted to a location configured to store the updated adaptation data for retrieval by the particular device.

196. (canceled)

197. (canceled)

198. (canceled)

199. (canceled)

200. (canceled)

201. (canceled)

202. (canceled)

203. (canceled)

205. (canceled)

206. (canceled)

207. (canceled)

208. (canceled)

209. (canceled)

211. (canceled)

212. (canceled)

213. (canceled)

215. (canceled)

216. (canceled)

217. (canceled)

218. (canceled)

219. (canceled)

221. (canceled)

222. (canceled)

223. (canceled)

226. (canceled)

227. (canceled)

228. (canceled)

232. (canceled)

235. (canceled)

236. (canceled)

241. (canceled)

242. (canceled)

245. (canceled)

246. (canceled)

250. (canceled)

251. (canceled)

252. (canceled)

253. (canceled)

254. (canceled)

255. (canceled)

260. (canceled)

262. (canceled)

266. (canceled)

267. (canceled)

268. (canceled)

269. (canceled)

271. (canceled)

272. (canceled)

273. (canceled)

276. (canceled)

277. (canceled)

278. (canceled)

279. (canceled)

280. (canceled)

281. (canceled)

287. (canceled)