公开(公告)号：US20180144749A1

公开(公告)日：2018-05-24

申请号：US15862935

申请日：2018-01-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hee Youl CHOI ,  Seokjin HONG

IPC: G10L15/32 ,  G10L15/22 ,  G10L15/16 ,  G10L15/183 ,  G10L15/08 ,  G10L15/06

CPC classification number: G10L15/32 ,  G10L15/08 ,  G10L15/16 ,  G10L15/183 ,  G10L15/22 ,  G10L2015/0635 ,  G10L2015/221 ,  G10L2015/223

Abstract: A speech recognition apparatus and method. The speech recognition apparatus includes one or more processors configured to reflect a final recognition result for a previous audio signal in a language model, generate a first recognition result of an audio signal, in a first linguistic recognition unit, by using an acoustic model, generate a second recognition result of the audio signal, in a second linguistic recognition unit, by using the language model reflecting the final recognition result for the previous audio signal, and generate a final recognition result for the audio signal in the second linguistic recognition unit based on the first recognition result and the second recognition result. The first linguistic recognition unit may be a same or different linguistic unit type as the second linguistic recognition unit.

公开(公告)号：US20170076719A1

公开(公告)日：2017-03-16

申请号：US15231909

申请日：2016-08-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： HoShik LEE ,  Hee Youl CHOI

IPC: G10L15/20 ,  G10L15/16 ,  G10L25/84 ,  G10L15/06 ,  G10L15/02

CPC classification number: G10L15/20 ,  G10L15/02 ,  G10L15/063 ,  G10L15/16 ,  G10L25/84 ,  G10L2015/025

Abstract: Described are an apparatus and method for generating to generate an acoustic model. The apparatus and method include a processor a processor configured to calculate a noise representation that represents noise data by using a noise model, and generate the acoustic model through training using training noisy speech data, which comprises speech data and the noise data, a string of phonemes corresponding to the speech data, and the noise representation.

Abstract translation: 描述了用于产生声学模型的装置和方法。 该装置和方法包括处理器，处理器被配置为通过使用噪声模型来计算表示噪声数据的噪声表示，并且通过使用包括语音数据和噪声数据的训练噪声语音数据的训练来生成声学模型， 对应于语音数据的音素和噪声表示。

公开(公告)号：US20170004824A1

公开(公告)日：2017-01-05

申请号：US15139926

申请日：2016-04-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sang Hyun YOO ,  Hee Youl CHOI

IPC: G10L15/02 ,  G10L15/22 ,  G06F17/28

CPC classification number: G10L15/02 ,  G06F17/2818 ,  G06N3/0454 ,  G10L15/00 ,  G10L15/187 ,  G10L15/197 ,  G10L15/22 ,  G10L2015/025 ,  G10L2015/228

Abstract: A speech recognition apparatus includes a probability calculator configured to calculate phoneme probabilities of an audio signal using an acoustic model; a candidate set extractor configured to extract a candidate set from a recognition target list; and a result returner configured to return a recognition result of the audio signal based on the calculated phoneme probabilities and the extracted candidate set.

Abstract translation: 语音识别装置包括概率计算器，被配置为使用声学模型来计算音频信号的音素概率; 候选集提取器，被配置为从识别目标列表中提取候选集合; 以及结果返回器，被配置为基于所计算的音素概率和所提取的候选组返回音频信号的识别结果。

公开(公告)号：US20210272551A1

公开(公告)日：2021-09-02

申请号：US17322965

申请日：2021-05-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sang Hyun YOO ,  Hee Youl CHOI

IPC: G10L15/02 ,  G10L15/00 ,  G10L15/197 ,  G10L15/187 ,  G06F40/44 ,  G10L15/22

Abstract: A speech recognition apparatus includes a probability calculator configured to calculate phoneme probabilities of an audio signal using an acoustic model; a candidate set extractor configured to extract a candidate set from a recognition target list; and a result returner configured to return a recognition result of the audio signal based on the calculated phoneme probabilities and the extracted candidate set.

公开(公告)号：US20170084268A1

公开(公告)日：2017-03-23

申请号：US15263977

申请日：2016-09-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sang Hyun YOO ,  Jung Hoe KIM ,  Hyoung Min PARK ,  Hee Youl CHOI ,  Seok Jin HONG

IPC: G10L15/14 ,  G10L15/18 ,  G10L15/06

CPC classification number: G10L15/14 ,  G10L15/063 ,  G10L15/07 ,  G10L15/08 ,  G10L15/18 ,  G10L15/183 ,  G10L2015/0635 ,  G10L2015/226 ,  G10L2015/227 ,  G10L2015/228

Abstract: Provided are a method and an apparatus for speech recognition, and a method and an apparatus for training transformation parameter. A speech recognition apparatus includes an acoustic score calculator configured to use an acoustic model to calculate an acoustic score of a speech input, an acoustic score transformer configured to transform the calculated acoustic score into an acoustic score corresponding to standard pronunciation by using a transformation parameter, and a decoder configured to decode the transformed acoustic score to output a recognition result of the speech input.

公开(公告)号：US20170133006A1

公开(公告)日：2017-05-11

申请号：US15344110

申请日：2016-11-04

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ho Shik LEE ,  Hee Youl CHOI

IPC: G10L15/06 ,  G10L15/02 ,  G10L15/16

Abstract: A neural network training apparatus includes a primary trainer configured to perform a primary training of a neural network model based on clean training data and target data corresponding to the clean training data; and a secondary trainer configured to perform a secondary training of the neural network model on which the primary training has been performed based on noisy training data and an output probability distribution of an output class for the clean training data calculated during the primary training of the neural network model.

公开(公告)号：US20170053652A1

公开(公告)日：2017-02-23

申请号：US15205515

申请日：2016-07-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hee Youl CHOI ,  Seokjin HONG

IPC: G10L15/32 ,  G10L15/183 ,  G10L15/22 ,  G10L15/16

CPC classification number: G10L15/32 ,  G10L15/08 ,  G10L15/16 ,  G10L15/183 ,  G10L15/22 ,  G10L2015/0635 ,  G10L2015/221 ,  G10L2015/223

Abstract: A speech recognition apparatus and method. The speech recognition apparatus includes a first recognizer configured to generate a first recognition result of an audio signal, in a first linguistic recognition unit, by using an acoustic model, a second recognizer configured to generate a second recognition result of the audio signal, in a second linguistic recognition unit, by using a language model, and a combiner configured to combine the first recognition result and the second recognition result to generate a final recognition result in the second linguistic recognition unit and to reflect the final recognition result in the language model. The first linguistic recognition unit may be a same linguistic unit type as the second linguistic recognition unit. The first recognizer and the second recognizer are configured in a same neural network and simultaneously/collectively trained in the neural network using audio training data provided to the first recognizer.

Abstract translation: 一种语音识别装置及方法。 语音识别装置包括：第一识别器，被配置为通过使用声学模型在第一语言识别单元中生成音频信号的第一识别结果;第二识别器，被配置为生成音频信号的第二识别结果， 第二语言识别单元，通过使用语言模型，以及组合器，被配置为组合第一识别结果和第二识别结果以在第二语言识别单元中生成最终识别结果，并将最终识别结果反映在语言模型中。 第一语言识别单元可以是与第二语言识别单元相同的语言单元类型。 第一识别器和第二识别器被配置在相同的神经网络中，并且使用提供给第一识别器的音频训练数据在神经网络中同时/集体训练。

公开(公告)号：US20160027437A1

公开(公告)日：2016-01-28

申请号：US14614582

申请日：2015-02-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seok Jin HONG ,  Young Sang CHOI ,  Hee Youl CHOI ,  Sang Hyun YOO

IPC: G10L15/08

CPC classification number: G10L15/187

Abstract: A method and apparatus for speech recognition and for generation of speech recognition engine, and a speech recognition engine are provided. The method of speech recognition involves receiving a speech input, transmitting the speech input to a speech recognition engine, and receiving a speech recognition result from the speech recognition engine, in which the speech recognition engine obtains a phoneme sequence from the speech input and provides the speech recognition result based on a phonetic distance of the phoneme sequence.

Abstract translation: 提供了用于语音识别和用于语音识别引擎的生成的方法和装置以及语音识别引擎。 语音识别的方法包括接收语音输入，将语音输入发送到语音识别引擎，以及从语音识别引擎接收语音识别结果，其中语音识别引擎从语音输入中获取音素序列，并提供 基于音素序列语音距离的语音识别结果。