-
公开(公告)号：US11114100B2
公开(公告)日：2021-09-07
申请号：US16549403
申请日：2019-08-23
Applicant: Google LLC
Inventor： Vladimir Vuskovic , Stephan Wenger , Zineb Ait Bahajji , Martin Baeuml , Alexandru Dovlecel , Gleb Skobeltsyn
IPC: G10L15/22 , G06F40/35 , G06F40/56 , G06F40/295 , G10L15/18
Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.
-
公开(公告)号：US20200243070A1
公开(公告)日：2020-07-30
申请号：US16837393
申请日：2020-04-01
Applicant: Google LLC
Inventor： Olga Kapralova , Evgeny A. Cherepanov , Dmitry Osmakov , Martin Baeuml , Gleb Skobeltsyn
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.
-
公开(公告)号：US20180308471A1
公开(公告)日：2018-10-25
申请号：US16023658
申请日：2018-06-29
Applicant: Google LLC
Inventor： Olga Kapralova , Evgeny A. Cherepanov , Dmitry Osmakov , Martin Baeuml , Gleb Skobeltsyn
CPC classification number: G10L15/063 , G10L15/01 , G10L15/06 , G10L15/10 , G10L15/22 , G10L15/32 , G10L2015/0635 , G10L2015/0638
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.
-
公开(公告)号：US20250037711A1
公开(公告)日：2025-01-30
申请号：US18912175
申请日：2024-10-10
Applicant: GOOGLE LLC
Inventor： Martin Baeuml , Thushan Amarasiriwardena , Roberto Pieraccini , Vikram Sridar , Daniel De Freitas Adiwardana , Noam M. Shazeer , Quoc Le
IPC: G10L15/183 , G06F16/9032 , G10L15/22
Abstract: As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.
-
公开(公告)号：US12148421B2
公开(公告)日：2024-11-19
申请号：US17532794
申请日：2021-11-22
Applicant: GOOGLE LLC
Inventor： Martin Baeuml , Thushan Amarasiriwardena , Roberto Pieraccini , Vikram Sridar , Daniel De Freitas Adiwardana , Noam M. Shazeer , Quoc Le
IPC: G10L15/22 , G06F16/9032 , G10L15/183
Abstract: As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.
-
Patent Agency Ranking
公开(公告)号：US20240311575A1
公开(公告)日：2024-09-19
申请号：US18123141
申请日：2023-03-17
Applicant: GOOGLE LLC
Inventor： Martin Baeuml , Alexander Bailey , Jonas Bragagnolo , Florent D'Halluin , Trevor Strohman
Abstract: Implementations relate to dialog management of a large language model (LLM) utilized in generating natural language (NL) output during an ongoing dialog. Processor(s) of a system can: receive NL based input as part of the ongoing dialog, generate NL based output utilizing the LLM, and cause the NL based output to be rendered. Further, the processor(s) can receive subsequent NL based input as part of the ongoing dialog. In some implementations, the processor(s) can determine whether to modify a corresponding dialog context in generating subsequent NL based output, and modify the corresponding dialog context accordingly. For example, the processor(s) can restrict the corresponding dialog context, or supplant the corresponding dialog context with a corresponding curated dialog context. In additional or alternative implementations, the processor(s) can modify a corresponding NL based output threshold utilized in generating the subsequent NL based response to ensure the resulting NL based output is desirable.
-
17.发明公开公开(公告)号：US20240311402A1
公开(公告)日：2024-09-19
申请号：US18136634
申请日：2023-04-19
Applicant: GOOGLE LLC
Inventor： Martin Baeuml , Yanping Huang , Wenhao Jia , Chang Lan , Yuanzhong Xu , Junwhan Ahn , Alexander Bailey , Leif Schelin , Trevor Strohman , Emanuel Taropa , Sidharth Mudgal , Yanyan Zheng , Zhifeng Chen , Ahmad Beirami
IPC: G06F16/332 , G06F40/40
CPC classification number: G06F16/3322 , G06F16/3329 , G06F40/40
Abstract: Implementations relate to reducing latency in generating and/or rendering natural language (NL) output generated using a large language model (LLM). Processor(s) of a system can: receive NL based input associated with a client device, and generate the NL based output utilizing the LLM. The NL based output can be a stream of NL based output in that it includes a plurality of segments, and is generated on a segment-by-segment basis. In some implementations, a first segment of the stream of NL based output is selected for inclusion in the stream of NL based output as a second segment (and any subsequent segment) is being generated to reduce latency in evaluating the NL based output as a whole prior to rendering thereof. In some versions of those implementations, the first segment is rendered as the second segment (and any subsequent segment) is being generated to further reduce latency in rendering thereof.
-
公开(公告)号：US11929069B2
公开(公告)日：2024-03-12
申请号：US17411532
申请日：2021-08-25
Applicant: Google LLC
Inventor： Vladimir Vuskovic , Stephan Wenger , Zineb Ait Bahajji , Martin Baeuml , Alexandru Dovlecel , Gleb Skobeltsyn
IPC: G10L15/22 , G06F40/295 , G06F40/35 , G06F40/56 , G10L15/18
CPC classification number: G10L15/22 , G06F40/295 , G06F40/35 , G06F40/56 , G10L15/1815 , G10L15/222 , G10L2015/227
Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.
-
公开(公告)号：US20220093080A1
公开(公告)日：2022-03-24
申请号：US17457421
申请日：2021-12-02
Applicant: Google LLC
Inventor： Olga Kapralova , Evgeny A. Cherepanov , Dmitry Osmakov , Martin Baeuml , Gleb Skobeltsyn
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.
-
公开(公告)号：US10019986B2
公开(公告)日：2018-07-10
申请号：US15224104
申请日：2016-07-29
Applicant: Google LLC
Inventor： Olga Kapralova , Evgeny A. Cherepanov , Dmitry Osmakov , Martin Baeuml , Gleb Skobeltsyn
CPC classification number: G10L15/063 , G10L15/01 , G10L15/06 , G10L15/10 , G10L15/22 , G10L15/32 , G10L2015/0635 , G10L2015/0638
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.
-
-
-
-
-
-
-
-
-
Search Results
26
records
(took 0.027 seconds)
