公开(公告)号：WO2020157283A1

公开(公告)日：2020-08-06

申请号：PCT/EP2020/052446

申请日：2020-01-31

Applicant: MOODAGENT A/S

Inventor： STEFFENSEN, Peter, Berg ,  HENDERSON, Mikael

IPC: G06F16/783 ,  G06F16/683 ,  G06F16/632

Abstract: A method of recommending video content using a computer-based system (30), the method comprising providing (101) an initial set comprising a plurality of videos (1); extracting (102) a digital audio signal (2) from each of the plurality of videos (1); determining (103) at least one temporal sequence (4) of low-level audio features for each digital audio signal (2) of the plurality of videos (1) by analyzing the digital audio signals (2); calculating (104) an audio similarity index (5) between each of the plurality of videos (1) by comparing their respective at least one temporal sequence (4) of low-level audio features; receiving (105) a query Q comprising reference to a seed video; the seed video being one of the plurality of videos (1); determining (106), for the seed video, a ranking (7) of the rest of the initial set of videos (1) based on their audio similarity index (5) with respect to the seed video; and returning (107), as a reply to the query Q , an ordered set of video references according to the ranking (7).

公开(公告)号：WO2023020999A1

公开(公告)日：2023-02-23

申请号：PCT/EP2022/072773

申请日：2022-08-15

Applicant: UTOPIA MUSIC AG

Inventor： WAHLGREN, Linus ,  FLACH, Max

IPC: G06F16/61 ,  G06F16/632

Abstract: Apparatus, method, and computer program code for processing an audio stream. The method includes: receiving (206) a candidate audio stream and candidate metadata;obtaining (208) candidate audio fingerprints; comparing (212) the candidate audio stream against a database using the candidate audio fingerprints; if no matching track is found, comparing (214, 218) the candidate audio stream against the sample storage using the candidate audio fingerprints, and computing (220) a merging score, and if the merging score meets a merging score threshold, merging (226, 228) the candidate audio fingerprints with sample audio fingerprints of matching sample tracks and the candidate metadata with sample metadata of the matching sample tracks to create a new final track, and saving (230) the new final track in the database, or else storing (236) the candidate audio fingerprints and the candidate metadata in the sample storage.

公开(公告)号：WO2021068467A1

公开(公告)日：2021-04-15

申请号：PCT/CN2020/083545

申请日：2020-04-07

Applicant: 百度在线网络技术（北京）有限公司

Inventor： 姬然 ,  黄际洲 ,  李莹 ,  季永志 ,  贾磊

IPC: G06F16/632

Abstract: 一种语音包的推荐方法、装置、电子设备和存储介质，涉及智能搜索技术领域。所述方法包括：获取用户的搜索请求（101）；对搜索请求进行识别以获取用户的音色兴趣标识（102）；根据音色兴趣标识搜索对应的目标语音包，并推荐给用户（103）。该方法通过对用户的搜索请求进行识别，获取用户的音色兴趣标识，根据用户的音色兴趣标识向用户推荐具有用户感兴趣的音色的语音包，实现了语音包的个性化推荐，无需用户通过逐一试听来选择语音包，操作简单，推荐精准，提高了智能化。

公开(公告)号：WO2019236581A1

公开(公告)日：2019-12-12

申请号：PCT/US2019/035391

申请日：2019-06-04

Applicant: DISRUPTEL, INC.

Inventor： QUINN, Alexander, Clifford Hunt ,  LOWREY, John, F.

IPC: G06F16/632 ,  G06F16/68 ,  G10L15/26

Abstract: Systems and methods for operation and control of a smart device, generally a video output device. An aspect is a gesture-based control system that identifies the operative user, regardless of how many potential users are present in the room, and regardless of where each potential user is disposed in the room. Another aspect is controlling and interfacing with a user output device using various types of queries and context cues, and responding to queries by resolving ambiguities in the query. These aspects may be used independently or in combination.

公开(公告)号：WO2023273596A1

公开(公告)日：2023-01-05

申请号：PCT/CN2022/090978

申请日：2022-05-05

Applicant: 北京字节跳动网络技术有限公司

Inventor： 王鑫宇 ,  张永华

IPC: G06F16/68 ,  G06F16/632 ,  G06F16/685 ,  G06F16/686

Abstract: 本公开提供一种确定文本相关性的方法、装置、可读介质及电子设备，所述方法包括：获取待搜索文本和待搜索文本对应的待匹配文本；按照预设文本划分要素，将待匹配文本划分为多个目标文本，预设文本划分要素用于表征所述待匹配文本的不同维度；根据待搜索文本和多个所述目标文本，获取待搜索文本与待匹配文本之间的相关性。

公开(公告)号：WO2022114438A1

公开(公告)日：2022-06-02

申请号：PCT/KR2021/008999

申请日：2021-07-13

Applicant: 주식회사 아하정보통신

Inventor： 구기도

IPC: G06F3/16 ,  G06F3/041 ,  G10L15/26 ,  G10L15/22 ,  G06F16/632 ,  G06F16/683 ,  G06F16/638 ,  H04L29/08

Abstract: 본 발명의 목적은 터치패널을 포함하는 전자 칠판에서 여러 가지 IoT 입력 정보(음성 인식 입력정보, 터치 입력정보, 무선 입력정보)에 따라 사물인터넷(IoT) 네트워크로 연결된 외부 기기를 유무선으로 제어하는 기능을 수행하는 것이다. 이를 위하여, 터치 인식이 가능한 패널부와 상기 패널부가 터치되는 경우에 터치 방식에 따른 터치인식을 수행하는 센서부를 포함하고 일정한 물리적 거리 이내에 IoT 기반으로 연결된 주변 기기와 상호 연동되도록 유무선으로 연결된 전자 칠판에 있어서, 터치 입력 신호에 의하여 상기 패널부 및 센서부에서 인식한 터치 신호에 해당하는 제어 기능을 수행하는 제 1 신호 처리부; 무선 입력 신호에 의하여 무선 통신망을 통한 무선 제어 신호에 해당하는 제어 기능을 수행하는 제 2 신호 처리부; 음성 입력 신호에 의하여 아날로그 음성 신호를 디지털 텍스트 신호로 변환하여 명령어를 해석하고 해석된 명령어에 대응하는 제어 기능을 수행하는 제 3 신호 처리부; 및 상기 제 1 내지 3 신호 처리부에서 수행하는 제어 기능이 상기 전자 칠판에 유무선으로 연결된 주변 기기에 대한 제어인 경우에 원격으로 상기 주변 기기를 제어하는 컨트롤러를 구비한 제어부를 포함하는 전자 칠판 시스템을 제공한다.

公开(公告)号：WO2022102975A1

公开(公告)日：2022-05-19

申请号：PCT/KR2021/013707

申请日：2021-10-06

Applicant: 삼성전자주식회사

Inventor： 민범기

IPC: G06Q30/02 ,  G06F16/632 ,  G06F16/635 ,  G06F16/638

Abstract: 전자 장치는, 마이크, 스피커, 메모리, 프로세서를 포함한다. 프로세서는, 마이크를 통해 입력된 사용자 음성이 변환된 텍스트로부터 상품 키워드를 획득하고, 상품 키워드와 관련된 상품 카테고리를 식별하고, 발화 이력 정보에 따른 사용자의 관심도 및 사용자의 광고 피로도를 기반으로, 사용자 음성과 관련된 광고의 제공 여부를 결정하고, 광고를 제공하는 것으로 결정되면, 사용자의 관심도에 따라 결정된 타겟 상품 카테고리에 기초하여 광고 정보를 획득하고, 광고 정보에 기초하여 광고 음성을 출력하도록 스피커를 제어한다.

公开(公告)号：WO2021188126A1

公开(公告)日：2021-09-23

申请号：PCT/US2020/029346

申请日：2020-04-22

Applicant: GOOGLE LLC

Inventor： BAROR, Yuval ,  LEVIATHAN, Yaniv

IPC: H04M3/42 ,  G06F16/632 ,  G06Q10/02 ,  H04M1/725

Abstract: Implementations are directed to using an automated assistant to initiate an assisted call on behalf of a given user. The assistant can, during the assisted call, receiving a request, from an additional user on the assisted call, for information that is not known to the assistant. In response, the assistant can render a prompt for the information and, while awaiting responsive input from the given user, continue the assisted call using already resolved value(s) for the assisted call. If responsive input is received within a threshold duration of time, synthesized speech, corresponding to the responsive input, is rendered as part of the assisted call. Implementations are additionally or alternatively directed to using the automated assistant to provide, during an ongoing call between a given user and an additional user, output that is based on a value requested by the additional user during the ongoing call.

公开(公告)号：WO2020054409A1

公开(公告)日：2020-03-19

申请号：PCT/JP2019/033624

申请日：2019-08-28

Applicant: ソニー株式会社

Inventor： 島田　一希

IPC: G10L25/51 ,  G06F16/632 ,  G10L15/06

Abstract: 本技術は、事後に認識対象を追加することができるようにする音響イベント認識装置および方法、並びにプログラムに関する。 音響イベント認識装置は、入力音響信号から特徴量を抽出する特徴量抽出部と、特徴量の入力音響信号が、事前に付けたラベルの範囲内の音響イベントか否かを認識し、その認識結果を出力するラベル内認識部と、ラベル内認識部により音響イベントを認識できなかった場合、ラベルによらず取得した音響イベントとの同異を判定することにより判定結果を出力する同異判定部と、ラベル内認識部または同異判定部から出力された音響イベントに該当するフラグが有効になっているかを判定し、フラグが有効になっている場合、当該音響イベントを認識結果として出力するフラグ管理部とを備える。本技術は音響イベント認識装置に適用することができる。

公开(公告)号：WO2022272281A1

公开(公告)日：2022-12-29

申请号：PCT/US2022/073113

申请日：2022-06-23

Applicant: SRI INTERNATIONAL

Inventor： KATHOL, Andreas ,  RICHEY, Colleen ,  ABRASH, Victor ,  KWON, Homin

IPC: G06F16/632 ,  G10L15/08 ,  G10L15/187 ,  G10L15/26 ,  G10L21/06 ,  G10L25/54 ,  G06F16/638 ,  G10L21/12

Abstract: Techniques are disclosed for searching audio recordings in a second language with a key phrase in a first language. For example, a system as described herein receives a first key phrase in the first language and an audio recording in the second language. The system converts the first key phrase into a second key phrase in the second language. The system processes the second key phrase to produce a second key phrase variant. The system identifies, from a graph of words in the second language generated from the audio recording, instances of the second key phrase or the second key phrase variant within the audio recording. The system displays the identified instances of the second key phrase or the second key phrase variant within the audio recording to enhance searchability of the audio recording in the second language.