JP6756916B2 - ニューラルネットワークを使用したテキストシーケンスの処理 - Google Patents
ニューラルネットワークを使用したテキストシーケンスの処理 Download PDFInfo
- Publication number
- JP6756916B2 JP6756916B2 JP2019522499A JP2019522499A JP6756916B2 JP 6756916 B2 JP6756916 B2 JP 6756916B2 JP 2019522499 A JP2019522499 A JP 2019522499A JP 2019522499 A JP2019522499 A JP 2019522499A JP 6756916 B2 JP6756916 B2 JP 6756916B2
- Authority
- JP
- Japan
- Prior art keywords
- sequence
- source
- translation system
- machine translation
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims description 13
- 238000013528 artificial neural network Methods 0.000 title claims description 9
- 238000013519 translation Methods 0.000 claims description 54
- 238000013527 convolutional neural network Methods 0.000 claims description 49
- 230000001537 neural effect Effects 0.000 claims description 43
- 238000000034 method Methods 0.000 claims description 38
- 238000010606 normalization Methods 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 25
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000014616 translation Effects 0.000 description 30
- 238000004590 computer program Methods 0.000 description 14
- 230000009471 action Effects 0.000 description 12
- 239000013598 vector Substances 0.000 description 12
- 238000010801 machine learning Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 4
- 230000015654 memory Effects 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000026683 transduction Effects 0.000 description 2
- 238000010361 transduction Methods 0.000 description 2
- 241000009334 Singa Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009125 cardiac resynchronization therapy Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
- G06F40/44—Statistical methods, e.g. probability models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
- G10L15/197—Probabilistic grammars, e.g. word n-grams
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Probability & Statistics with Applications (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
- Error Detection And Correction (AREA)
Description
102 ソースシーケンス
104 ソース埋め込みモデル
106 ソース埋め込みシーケンス
108 畳み込みニューラルネットワークエンコーダ
110 符号化されたソース表現
112 マスクされた畳み込みニューラルネットワークデコーダ
114 ターゲット埋め込みシーケンス
116 ターゲットシーケンス
Claims (18)
前記ニューラル機械翻訳システムが、ソース自然言語の単語のソースシーケンスを表すソース埋め込みの入力シーケンスを受信し、前記ソースシーケンスのターゲット自然言語への翻訳である単語のターゲットシーケンスを表すターゲット埋め込みの出力シーケンスを生成するように構成され、
前記ニューラル機械翻訳システムが、
前記ソースシーケンスの符号化表現を生成するために、ソース埋め込みの入力シーケンスを処理するように構成された拡張畳み込みニューラルネットワークと、
ターゲット埋め込みの前記出力シーケンスを生成するために、前記ソースシーケンスの前記符号化表現を処理するように構成されたマスクされた拡張畳み込みニューラルネットワークと
を含む、ニューラル機械翻訳システム。
前記出力シーケンスにおける各時間ステップにおいて、前記マスクされた拡張畳み込みネットワークが、前記符号化表現の対応する列を入力として受け取り、ターゲット埋め込みを生成するように構成される、請求項2に記載のニューラル機械翻訳システム。
前記サブバッチ正規化層が、トレーニングシーケンスのバッチにおける前記ニューラル機械翻訳システムのトレーニング中に、
トレーニングシーケンスの前記バッチの補助サブバッチ内のトレーニングシーケンスについて前記特定の1次元のマスクされた拡張畳み込みニューラルネットワーク層によって生成された出力のバッチ正規化統計を決定し、
前記バッチ正規化統計を使用して、前記補助サブバッチとは異なるトレーニングシーケンスの前記バッチのメインサブバッチ内のトレーニングシーケンスについて前記特定の1次元のマスクされた拡張畳み込みニューラルネットワーク層によって生成された出力を正規化する
ように構成される、請求項7に記載のニューラル機械翻訳システム。
各グループ内で、前記グループ内の1次元のマスクされた拡張畳み込みニューラルネットワーク層の拡張率が層ごとに2倍になる、請求項7〜11のいずれか一項に記載のニューラル機械翻訳システム。
前記ソースシーケンス内の所与の文字について、前記文字についての前記n-gram埋め込みのバッグが、前記ソースシーケンス内の所与の文字に隣接する文字のn-gram埋め込みの組合せである、請求項1〜12のいずれか一項に記載のニューラル機械翻訳システム。
前記ソースシーケンスからn-gram埋め込みのバッグのシーケンスを生成する
ように構成された入力サブシステムをさらに含む請求項13または14のいずれか一項に記載のニューラル機械翻訳システム。
前記ソースシーケンスのターゲット自然言語への翻訳である単語のターゲットシーケンスを表すターゲット埋め込みの出力シーケンスを生成するために、請求項1〜16のいずれか一項の前記ニューラル機械翻訳システムを使用して、前記入力シーケンスを処理するステップと
を含む方法。
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201662413366P | 2016-10-26 | 2016-10-26 | |
US62/413,366 | 2016-10-26 | ||
PCT/US2017/058046 WO2018081089A1 (en) | 2016-10-26 | 2017-10-24 | Processing text sequences using neural networks |
Publications (2)
Publication Number | Publication Date |
---|---|
JP2020502625A JP2020502625A (ja) | 2020-01-23 |
JP6756916B2 true JP6756916B2 (ja) | 2020-09-16 |
Family
ID=60263120
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2019522499A Active JP6756916B2 (ja) | 2016-10-26 | 2017-10-24 | ニューラルネットワークを使用したテキストシーケンスの処理 |
Country Status (6)
Country | Link |
---|---|
US (3) | US10354015B2 (ja) |
EP (1) | EP3532998A1 (ja) |
JP (1) | JP6756916B2 (ja) |
KR (2) | KR102458808B1 (ja) |
CN (1) | CN110023963B (ja) |
WO (1) | WO2018081089A1 (ja) |
Families Citing this family (50)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10628735B2 (en) * | 2015-06-05 | 2020-04-21 | Deepmind Technologies Limited | Reading comprehension neural networks |
CA3155320A1 (en) | 2016-09-06 | 2018-03-15 | Deepmind Technologies Limited | Generating audio using neural networks |
EP3497630B1 (en) | 2016-09-06 | 2020-11-04 | Deepmind Technologies Limited | Processing sequences using convolutional neural networks |
US11080591B2 (en) | 2016-09-06 | 2021-08-03 | Deepmind Technologies Limited | Processing sequences using convolutional neural networks |
US20180077689A1 (en) * | 2016-09-15 | 2018-03-15 | Qualcomm Incorporated | Multiple bandwidth operation |
JP6756916B2 (ja) | 2016-10-26 | 2020-09-16 | ディープマインド テクノロジーズ リミテッド | ニューラルネットワークを使用したテキストシーケンスの処理 |
US11423143B1 (en) | 2017-12-21 | 2022-08-23 | Exabeam, Inc. | Anomaly detection based on processes executed within a network |
CN110083448B (zh) * | 2018-01-25 | 2023-08-18 | 腾讯科技(深圳)有限公司 | 一种计算资源调整方法、装置以及相关设备 |
US10770063B2 (en) * | 2018-04-13 | 2020-09-08 | Adobe Inc. | Real-time speaker-dependent neural vocoder |
US11431741B1 (en) * | 2018-05-16 | 2022-08-30 | Exabeam, Inc. | Detecting unmanaged and unauthorized assets in an information technology network with a recurrent neural network that identifies anomalously-named assets |
CN108776832B (zh) * | 2018-06-05 | 2021-08-24 | 腾讯科技(深圳)有限公司 | 信息处理方法、装置、计算机设备和存储介质 |
US11735028B2 (en) | 2018-06-12 | 2023-08-22 | Intergraph Corporation | Artificial intelligence applications for computer-aided dispatch systems |
US11205121B2 (en) * | 2018-06-20 | 2021-12-21 | Disney Enterprises, Inc. | Efficient encoding and decoding sequences using variational autoencoders |
CN109117483B (zh) * | 2018-07-27 | 2020-05-19 | 清华大学 | 神经网络机器翻译模型的训练方法及装置 |
JP7143677B2 (ja) * | 2018-08-24 | 2022-09-29 | 日本電信電話株式会社 | 単語符号化装置、解析装置、言語モデル学習装置、方法、及びプログラム |
CN111382584B (zh) * | 2018-09-04 | 2022-07-29 | 腾讯科技(深圳)有限公司 | 文本翻译方法、装置、可读存储介质和计算机设备 |
CN109285111B (zh) * | 2018-09-20 | 2023-05-09 | 广东工业大学 | 一种字体转换的方法、装置、设备及计算机可读存储介质 |
CN109325103B (zh) * | 2018-10-19 | 2020-12-04 | 北京大学 | 一种序列学习的动态标识符表示方法、装置及系统 |
CN109543838B (zh) * | 2018-11-01 | 2021-06-18 | 浙江工业大学 | 一种基于变分自编码器的图像增量学习方法 |
CN109784149B (zh) * | 2018-12-06 | 2021-08-20 | 苏州飞搜科技有限公司 | 一种人体骨骼关键点的检测方法及系统 |
CN111401512B (zh) * | 2019-01-03 | 2024-06-04 | 三星电子株式会社 | 以可变的扩张率在神经网络中进行卷积的方法和系统 |
CN111476039B (zh) * | 2019-01-04 | 2023-06-30 | 深圳永德利科技股份有限公司 | 智能车载系统的即时语言翻译方法及相关产品 |
US11313950B2 (en) | 2019-01-15 | 2022-04-26 | Image Sensing Systems, Inc. | Machine learning based highway radar vehicle classification across multiple lanes and speeds |
CN110222329B (zh) * | 2019-04-22 | 2023-11-24 | 平安科技(深圳)有限公司 | 一种基于深度学习的中文分词方法和装置 |
US11587552B2 (en) | 2019-04-30 | 2023-02-21 | Sutherland Global Services Inc. | Real time key conversational metrics prediction and notability |
US11625366B1 (en) | 2019-06-04 | 2023-04-11 | Exabeam, Inc. | System, method, and computer program for automatic parser creation |
MX2022000163A (es) * | 2019-06-24 | 2022-05-20 | Insurance Services Office Inc | Sistemas y metodos de aprendizaje de maquina para localizacion mejorada de falsificacion de imagenes. |
US11862146B2 (en) * | 2019-07-05 | 2024-01-02 | Asapp, Inc. | Multistream acoustic models with dilations |
US11157705B2 (en) * | 2019-07-22 | 2021-10-26 | International Business Machines Corporation | Semantic parsing using encoded structured representation |
CN110807335B (zh) * | 2019-09-02 | 2023-06-30 | 腾讯科技(深圳)有限公司 | 基于机器学习的翻译方法、装置、设备及存储介质 |
CN110600015B (zh) * | 2019-09-18 | 2020-12-15 | 北京声智科技有限公司 | 一种语音的密集分类方法及相关装置 |
CN110807336B (zh) * | 2019-09-19 | 2023-10-31 | 平安科技(深圳)有限公司 | 基于最优传输损失的序列模型的翻译方法及相关设备 |
US11341340B2 (en) * | 2019-10-01 | 2022-05-24 | Google Llc | Neural machine translation adaptation |
US11651209B1 (en) | 2019-10-02 | 2023-05-16 | Google Llc | Accelerated embedding layer computations |
CN110717345B (zh) * | 2019-10-15 | 2020-07-07 | 内蒙古工业大学 | 一种译文重对齐的循环神经网络跨语言机器翻译方法 |
CN111079450B (zh) * | 2019-12-20 | 2021-01-22 | 北京百度网讯科技有限公司 | 基于顺句驱动的语言转换方法和装置 |
CN111191709B (zh) * | 2019-12-25 | 2023-10-31 | 清华大学 | 深度神经网络的持续学习框架及持续学习方法 |
CN115885323A (zh) * | 2020-01-08 | 2023-03-31 | 谷歌有限责任公司 | 对在图像中描绘的文本的翻译 |
KR102362532B1 (ko) * | 2020-03-16 | 2022-02-16 | 주식회사 로보볼트 | 신경망 기반의 배터리 잔존 수명 예측 방법 및 장치 |
US11263753B2 (en) * | 2020-04-07 | 2022-03-01 | Naver Corporation | Method for training a convolutional neural network for image recognition using image-conditioned masked language modeling |
CN111767723A (zh) * | 2020-05-14 | 2020-10-13 | 上海大学 | 一种基于bic的中文电子病历实体标注方法 |
CN111539223B (zh) * | 2020-05-29 | 2023-08-18 | 北京百度网讯科技有限公司 | 语言模型的训练方法、装置、电子设备及可读存储介质 |
CN111737994B (zh) * | 2020-05-29 | 2024-01-26 | 北京百度网讯科技有限公司 | 基于语言模型获取词向量的方法、装置、设备及存储介质 |
CN111475658B (zh) | 2020-06-12 | 2020-12-25 | 北京百度网讯科技有限公司 | 知识表示学习方法、装置、设备以及存储介质 |
US11956253B1 (en) | 2020-06-15 | 2024-04-09 | Exabeam, Inc. | Ranking cybersecurity alerts from multiple sources using machine learning |
US11875131B2 (en) | 2020-09-16 | 2024-01-16 | International Business Machines Corporation | Zero-shot cross-lingual transfer learning |
US11281928B1 (en) * | 2020-09-23 | 2022-03-22 | Sap Se | Querying semantic data from unstructured documents |
US11836438B2 (en) * | 2021-01-28 | 2023-12-05 | Microsoft Technology Licensing, Llc | ML using n-gram induced input representation |
US12013958B2 (en) | 2022-02-22 | 2024-06-18 | Bank Of America Corporation | System and method for validating a response based on context information |
WO2024128442A1 (ko) * | 2022-12-12 | 2024-06-20 | 숙명여자대학교산학협력단 | 트랜스포머 기반의 자연어 주석 자동 생성 방법 및 장치 |
Family Cites Families (53)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US1004910A (en) | 1911-01-07 | 1911-10-03 | Ohio Grease Lubricant Company | Grease-lubricator. |
JPH0450121Y2 (ja) | 1986-04-30 | 1992-11-26 | ||
US5377302A (en) | 1992-09-01 | 1994-12-27 | Monowave Corporation L.P. | System for recognizing speech |
WO1995030193A1 (en) | 1994-04-28 | 1995-11-09 | Motorola Inc. | A method and apparatus for converting text into audible signals using a neural network |
JPH10333699A (ja) | 1997-06-05 | 1998-12-18 | Fujitsu Ltd | 音声認識および音声合成装置 |
US8645137B2 (en) | 2000-03-16 | 2014-02-04 | Apple Inc. | Fast, language-independent method for user authentication by voice |
DE10018134A1 (de) | 2000-04-12 | 2001-10-18 | Siemens Ag | Verfahren und Vorrichtung zum Bestimmen prosodischer Markierungen |
JP2002123280A (ja) | 2000-10-16 | 2002-04-26 | Seiko Epson Corp | 音声合成方法および音声合成装置ならびに音声合成処理プログラムを記録した記録媒体 |
US7062437B2 (en) | 2001-02-13 | 2006-06-13 | International Business Machines Corporation | Audio renderings for expressing non-audio nuances |
US20060064177A1 (en) | 2004-09-17 | 2006-03-23 | Nokia Corporation | System and method for measuring confusion among words in an adaptive speech recognition system |
US7747070B2 (en) | 2005-08-31 | 2010-06-29 | Microsoft Corporation | Training convolutional neural networks on graphics processing units |
KR100832556B1 (ko) | 2006-09-22 | 2008-05-26 | (주)한국파워보이스 | 강인한 원거리 음성 인식 시스템을 위한 음성 인식 방법 |
FR2950713A1 (fr) | 2009-09-29 | 2011-04-01 | Movea Sa | Systeme et procede de reconnaissance de gestes |
TWI413104B (zh) | 2010-12-22 | 2013-10-21 | Ind Tech Res Inst | 可調控式韻律重估測系統與方法及電腦程式產品 |
CN102651217A (zh) | 2011-02-25 | 2012-08-29 | 株式会社东芝 | 用于合成语音的方法、设备以及用于语音合成的声学模型训练方法 |
EP2565667A1 (en) * | 2011-08-31 | 2013-03-06 | Friedrich-Alexander-Universität Erlangen-Nürnberg | Direction of arrival estimation using watermarked audio signals and microphone arrays |
US8527276B1 (en) | 2012-10-25 | 2013-09-03 | Google Inc. | Speech synthesis using deep neural networks |
US9230550B2 (en) | 2013-01-10 | 2016-01-05 | Sensory, Incorporated | Speaker verification and identification using artificial neural network-based sub-phonetic unit discrimination |
CA2810457C (en) | 2013-03-25 | 2018-11-20 | Gerald Bradley PENN | System and method for applying a convolutional neural network to speech recognition |
US9190053B2 (en) * | 2013-03-25 | 2015-11-17 | The Governing Council Of The Univeristy Of Toronto | System and method for applying a convolutional neural network to speech recognition |
US9953634B1 (en) * | 2013-12-17 | 2018-04-24 | Knowles Electronics, Llc | Passive training for automatic speech recognition |
US10181098B2 (en) * | 2014-06-06 | 2019-01-15 | Google Llc | Generating representations of input sequences using neural networks |
KR102332729B1 (ko) * | 2014-07-28 | 2021-11-30 | 삼성전자주식회사 | 발음 유사도를 기반으로 한 음성 인식 방법 및 장치, 음성 인식 엔진 생성 방법 및 장치 |
US9821340B2 (en) | 2014-07-28 | 2017-11-21 | Kolo Medical Ltd. | High displacement ultrasonic transducer |
ES2880316T3 (es) | 2014-08-29 | 2021-11-24 | Google Llc | Procesamiento de imágenes mediante redes neuronales profundas |
EP3889954B1 (en) | 2014-09-25 | 2024-05-08 | Sunhouse Technologies, Inc. | Method for extracting audio from sensors electrical signals |
US10783900B2 (en) | 2014-10-03 | 2020-09-22 | Google Llc | Convolutional, long short-term memory, fully connected deep neural networks |
US9542927B2 (en) | 2014-11-13 | 2017-01-10 | Google Inc. | Method and system for building text-to-speech voice from diverse recordings |
US11080587B2 (en) | 2015-02-06 | 2021-08-03 | Deepmind Technologies Limited | Recurrent neural networks for data item generation |
CN105096939B (zh) | 2015-07-08 | 2017-07-25 | 百度在线网络技术(北京)有限公司 | 语音唤醒方法和装置 |
US9786270B2 (en) | 2015-07-09 | 2017-10-10 | Google Inc. | Generating acoustic models |
CN105068998B (zh) * | 2015-07-29 | 2017-12-15 | 百度在线网络技术(北京)有限公司 | 基于神经网络模型的翻译方法及装置 |
CN105321525B (zh) | 2015-09-30 | 2019-02-22 | 北京邮电大学 | 一种降低voip通信资源开销的系统和方法 |
US10733979B2 (en) | 2015-10-09 | 2020-08-04 | Google Llc | Latency constraints for acoustic modeling |
US10395118B2 (en) * | 2015-10-29 | 2019-08-27 | Baidu Usa Llc | Systems and methods for video paragraph captioning using hierarchical recurrent neural networks |
US10332509B2 (en) | 2015-11-25 | 2019-06-25 | Baidu USA, LLC | End-to-end speech recognition |
CN105513591B (zh) | 2015-12-21 | 2019-09-03 | 百度在线网络技术(北京)有限公司 | 用lstm循环神经网络模型进行语音识别的方法和装置 |
KR102223296B1 (ko) | 2016-03-11 | 2021-03-04 | 매직 립, 인코포레이티드 | 콘볼루셔널 신경 네트워크들에서의 구조 학습 |
US10460747B2 (en) | 2016-05-10 | 2019-10-29 | Google Llc | Frequency based audio analysis using neural networks |
US11373672B2 (en) | 2016-06-14 | 2022-06-28 | The Trustees Of Columbia University In The City Of New York | Systems and methods for speech separation and neural decoding of attentional selection in multi-speaker environments |
US9984683B2 (en) | 2016-07-22 | 2018-05-29 | Google Llc | Automatic speech recognition using multi-dimensional models |
US11080591B2 (en) | 2016-09-06 | 2021-08-03 | Deepmind Technologies Limited | Processing sequences using convolutional neural networks |
CA3155320A1 (en) | 2016-09-06 | 2018-03-15 | Deepmind Technologies Limited | Generating audio using neural networks |
EP3497630B1 (en) | 2016-09-06 | 2020-11-04 | Deepmind Technologies Limited | Processing sequences using convolutional neural networks |
JP6756916B2 (ja) * | 2016-10-26 | 2020-09-16 | ディープマインド テクノロジーズ リミテッド | ニューラルネットワークを使用したテキストシーケンスの処理 |
US10049106B2 (en) * | 2017-01-18 | 2018-08-14 | Xerox Corporation | Natural language generation through character-based recurrent neural networks with finite-state prior knowledge |
US11934935B2 (en) | 2017-05-20 | 2024-03-19 | Deepmind Technologies Limited | Feedforward generative neural networks |
US9959272B1 (en) * | 2017-07-21 | 2018-05-01 | Memsource a.s. | Automatic classification and translation of written segments |
US11227108B2 (en) * | 2017-09-11 | 2022-01-18 | Nec Corporation | Convolutional neural network architecture with adaptive filters |
US10489792B2 (en) * | 2018-01-05 | 2019-11-26 | Asapp, Inc. | Maintaining quality of customer support messages |
US11003856B2 (en) * | 2018-02-22 | 2021-05-11 | Google Llc | Processing text using neural networks |
US10726858B2 (en) | 2018-06-22 | 2020-07-28 | Intel Corporation | Neural network for speech denoising trained with deep feature losses |
US10971170B2 (en) | 2018-08-08 | 2021-04-06 | Google Llc | Synthesizing speech from text using neural networks |
-
2017
- 2017-10-24 JP JP2019522499A patent/JP6756916B2/ja active Active
- 2017-10-24 KR KR1020227003520A patent/KR102458808B1/ko active IP Right Grant
- 2017-10-24 CN CN201780073530.0A patent/CN110023963B/zh active Active
- 2017-10-24 EP EP17794596.1A patent/EP3532998A1/en active Pending
- 2017-10-24 WO PCT/US2017/058046 patent/WO2018081089A1/en active Search and Examination
- 2017-10-24 KR KR1020197013231A patent/KR102359216B1/ko active IP Right Grant
-
2018
- 2018-07-11 US US16/032,971 patent/US10354015B2/en active Active
-
2019
- 2019-06-07 US US16/434,459 patent/US10733390B2/en active Active
-
2020
- 2020-07-13 US US16/927,267 patent/US11321542B2/en active Active
Also Published As
Publication number | Publication date |
---|---|
JP2020502625A (ja) | 2020-01-23 |
CN110023963B (zh) | 2023-05-30 |
KR102359216B1 (ko) | 2022-02-07 |
CN110023963A (zh) | 2019-07-16 |
US20190286708A1 (en) | 2019-09-19 |
US10733390B2 (en) | 2020-08-04 |
US20180329897A1 (en) | 2018-11-15 |
KR20220020421A (ko) | 2022-02-18 |
EP3532998A1 (en) | 2019-09-04 |
KR20190058636A (ko) | 2019-05-29 |
US10354015B2 (en) | 2019-07-16 |
US20200342183A1 (en) | 2020-10-29 |
WO2018081089A1 (en) | 2018-05-03 |
US11321542B2 (en) | 2022-05-03 |
KR102458808B1 (ko) | 2022-10-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6756916B2 (ja) | ニューラルネットワークを使用したテキストシーケンスの処理 | |
US11948066B2 (en) | Processing sequences using convolutional neural networks | |
US11869530B2 (en) | Generating audio using neural networks | |
US10268671B2 (en) | Generating parse trees of text segments using neural networks | |
AU2018271931B2 (en) | Attention-based sequence transduction neural networks | |
EP2953065B1 (en) | Generating representations of input sequences using neural networks | |
CN110326002B (zh) | 使用在线注意的序列处理 | |
JP6876814B2 (ja) | バッチ再正規化層 | |
WO2019157462A1 (en) | Fast decoding in sequence models using discrete latent variables | |
WO2019155054A1 (en) | Generating output examples using recurrent neural networks conditioned on bit values |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20190611 |
|
A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20200720 |
|
TRDD | Decision of grant or rejection written | ||
A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20200803 |
|
A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20200827 |
|
R150 | Certificate of patent or registration of utility model |
Ref document number: 6756916 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |
|
R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |