1. A computer-implemented method comprising:
receiving (i) a first transcription of a particular utterance from a first computing device and (ii) a second transcription of the particular utterance from a second computing device;
determining a grammatical alignment between the first transcription and the second transcription based on a comparison between the first transcription and the second transcription;
associating each word or phrase within the first transcription and the second transcription with a measure respectively calculated for each word or phrase within the first transcription and the second transcription, the measure corresponding to a likelihood of relevance for each word or phrase within the first transcription and the second transcription;
comparing the measure associated with each word or phrase within the first transcription and the second transcription;
generating a combined transcription from the first transcription and the second transcription that represents the particular utterance based on the comparison of the measure associated with each word or phrase within the first transcription and the second transcription; and
providing the combined transcription as a speech recognizer output of the particular utterance.
2. The computer-implemented method of claim 1, wherein aligning the first transcription with the second transcription comprises at least one of a pairwise alignment, a sequence alignment, and inexact matching.
3. The computer-implemented method of claim 1, wherein generating the combined transcription comprises using words or phrases from the first transcription for which the measure is greater than a particular threshold and using words or phrases from the second transcription for which the measure satisfies a certain threshold to obtain the combined transcription that represents the particular utterance.
4. The computer-implemented method of claim 1,
wherein the first transcription was generated using a limited speech recognizer, the limited speech recognizer comprising a speech recognizer that includes a language model that is trained over a limited speech recognition vocabulary that includes one or more terms from a voice command grammar, but that includes fewer than all terms of an expanded grammar; and
wherein the second transcription was generated using an expanded speech recognizer, the expanded speech recognizer comprising a speech recognizer that includes a language model that is trained over an expanded speech recognition vocabulary that includes all of the terms of the expanded grammar.
5. The computer-implemented method of claim 4, further comprising:
determining that a particular word or phrase was generated by the limited speech recognizer at a grammatical position within the particular utterance that indicates the particular utterance comprises a voice action command.
6. The computer-implemented method of claim 4, further comprising:
determining that a particular word or phrase was generated by the expanded speech recognizer that indicates the particular utterance comprises a voice search command.
7. The computer-implemented method of claim 1, further comprising:
analyzing the first transcription and the second transcription, which have been aligned, to determine a type of the particular utterance,
wherein the measure is based on the type of the particular utterance that is determined.
8. The computer-implemented method of claim 7, wherein the type of the particular utterance comprises at least one of a voice action command and a voice search command.
9. A system comprising:
one or more processors and one or more storage devices storing instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform operations comprising:
receiving (i) a first transcription of a particular utterance from a first computing device and (ii) a second transcription of the particular utterance from a second computing device;
determining a grammatical alignment between the first transcription and the second transcription based on a comparison between the first transcription and the second transcription;
associating each word or phrase within the first transcription and the second transcription with a measure respectively calculated for each word or phrase within the first transcription and the second transcription, the measure corresponding to a likelihood of relevance for each word or phrase within the first transcription and the second transcription;
comparing the measure associated with each word or phrase within the first transcription and the second transcription;
generating a combined transcription from the first transcription and the second transcription that represents the particular utterance based on the comparison of the measure associated with each word or phrase within the first transcription and the second transcription; and
providing the combined transcription as a speech recognizer output of the particular utterance.
10. The computer-implemented method of claim 9, wherein aligning the first transcription with the second transcription comprises at least one of a pairwise alignment, a sequence alignment, and inexact matching.
11. The computer-implemented method of claim 9, wherein generating the combined transcription comprises using words or phrases from the first transcription for which the measure is greater than a particular threshold and using words or phrases from the second transcription for which the measure satisfies a certain threshold to obtain the combined transcription that represents the particular utterance.
12. The computer-implemented method of claim 9,
wherein the first transcription was generated using a limited speech recognizer, the limited speech recognizer comprising a speech recognizer that includes a language model that is trained over a limited speech recognition vocabulary that includes one or more terms from a voice command grammar, but that includes fewer than all terms of an expanded grammar; and
wherein the second transcription was generated using an expanded speech recognizer, the expanded speech recognizer comprising a speech recognizer that includes a language model that is trained over an expanded speech recognition vocabulary that includes all of the terms of the expanded grammar.
13. The computer-implemented method of claim 12, further comprising:
determining that a particular word or phrase was generated by the limited speech recognizer at a grammatical position within the particular utterance that indicates the particular utterance comprises a voice action command.
14. The computer-implemented method of claim 12, further comprising:
determining that a particular word or phrase was generated by the expanded speech recognizer that indicates the particular utterance comprises a voice search command.
15. The computer-implemented method of claim 9, further comprising:
analyzing the first transcription and the second transcription, which have been aligned, to determine a type of the particular utterance,
wherein the measure is based on the type of the particular utterance that is determined.
16. The computer-implemented method of claim 15, wherein the type of the particular utterance comprises at least one of a voice action command and a voice search command.
17. A non-transitory computer-readable medium storing instructions executable by one or more computers that, upon such execution, cause the one or more computers to perform operations comprising:
receiving (i) a first transcription of a particular utterance from a first computing device and (ii) a second transcription of the particular utterance from a second computing device;
determining a grammatical alignment between the first transcription and the second transcription based on a comparison between the first transcription and the second transcription;
associating each word or phrase within the first transcription and the second transcription with a measure respectively calculated for each word or phrase within the first transcription and the second transcription, the measure corresponding to a likelihood of relevance for each word or phrase within the first transcription and the second transcription;
comparing the measure associated with each word or phrase within the first transcription and the second transcription;
generating a combined transcription from the first transcription and the second transcription that represents the particular utterance based on the comparison of the measure associated with each word or phrase within the first transcription and the second transcription; and
providing the combined transcription as a speech recognizer output of the particular utterance.
18. The non-transitory computer-readable medium of claim 17,
wherein the first transcription was generated using a limited speech recognizer, the limited speech recognizer comprising a speech recognizer that includes a language model that is trained over a limited speech recognition vocabulary that includes one or more terms from a voice command grammar, but that includes fewer than all terms of an expanded grammar; and
wherein the second transcription was generated using an expanded speech recognizer, the expanded speech recognizer comprising a speech recognizer that includes a language model that is trained over an expanded speech recognition vocabulary that includes all of the terms of the expanded grammar.
19. The non-transitory computer-readable medium of claim 17, wherein generating the combined transcription comprises using words or phrases from the first transcription for which the measure is greater than a particular threshold and using words or phrases from the second transcription for which the measure satisfies a certain threshold to obtain the combined transcription that represents the particular utterance.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A process for separating metaxylene with a purity of at least 99% by weight from a feedstock F of aromatic hydrocarbons having essentially 8 carbon atoms by direct separation into a single stage of adsorption in a simulated moving bed in a simulated moving bed (SMB) absorption device with at least one column that comprises a number of adsorbent beds that are separated by distributionextraction plates Pi, in which at least one feedstock F and one desorbent D are fed into this device, and at least one extract E that is high in paraxylene and at least one raffinate R are drawn off, whereby the supply and draw-off points are changed over time with a switching time T providing a number of operating zones of the SMB, the following primary operating zones of the SMB:
a zone 1 for desorption of the metaxylene that is located between the supply of the desorbent D and the draw-off of the extract E;
a zone 2 for desorption of the compounds of the raffinate, located between the draw-off of the extract E and the supply of the feedstock F;
a zone 3 for the adsorption of at least metaxylene, located between the supply of the feedstock and the draw-off of the raffinate R;
a zone 4 that is located between the draw-off of the raffinate R and the supply of the desorbent D,
and conducting the process according to a predetermined configuration of zones (a, b, c, d) with:
a=number of adsorbent beds operating in zone 1;
b=number of adsorbent beds operating in zone 2;
c=number of adsorbent beds operating in zone 3;
d=number of adsorbent beds operating in zone 4;
said predetermined configuration being one of the following:
An SMB of 12 adsorbent beds operating according to configuration (2, 5, 3, 2),
or an SMB of 13 adsorbent beds operating according to configuration (2, 5, 4, 2),
or an SMB of 15 adsorbent beds operating according to configuration (2, 6, 4, 3).
2. A process according to claim 1, conducted with an SMB of 12 adsorbent beds operating according to configuration (2, 5, 3, 2).
3. A process according to claim 1, conducted with an SMB of 13 adsorbent beds operating according to configuration (2, 5, 4, 2).
4. A process according to claim 1, conducted with an SMB of 15 adsorbent beds operating according to configuration (2, 6, 4, 3).
5. A process according to claim 1, in which the desorbent comprises toluene or tetralin.
6. A process according to claim 5, in which the desorbent is toluene.
7. A process according to claim 1, in which the operation is conducted with a sufficient feedstock flow rate coupled with a sufficient solvent flow rate to result in a metaxylene purity of 99.5% by weight.
8. A process according to claim 7, wherein the adsorbent is a NaY zeolite, the desorbent is toluene and process is conducted at between 20 and 250\xb0 C., a pressure between the bubble pressure of xylenes at the operating temperature and 2 MPa are a volumetric ratio of desorbent to feedstock of between 0.5 and 6.