公开(公告)号：US20140379349A1

公开(公告)日：2014-12-25

申请号：US14479980

申请日：2014-09-08

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Srinivas BANGALORE ,  Taniya MISHRA

IPC: G10L15/18 ,  G06F17/30

CPC classification number: G10L15/18 ,  G06F17/30637 ,  G06F17/30663 ,  G10L15/083

Abstract: Disclosed herein are systems, methods, and computer-readable storage media for performing a search. A system configured to practice the method first receives from an automatic speech recognition (ASR) system a word lattice based on speech query and receives indexed documents from an information repository. The system composes, based on the word lattice and the indexed documents, at least one triple including a query word, selected indexed document, and weight. The system generates an N-best path through the word lattice based on the at least one triple and re-ranks ASR output based on the N-best path. The system aggregates each weight across the query words to generate N-best listings and returns search results to the speech query based on the re-ranked ASR output and the N-best listings. The lattice can be a confusion network, the arc density of which can be adjusted for a desired performance level.

Abstract translation: 本文公开了用于执行搜索的系统，方法和计算机可读存储介质。 配置为实施该方法的系统首先从自动语音识别（ASR）系统接收基于语音查询的字格，并从信息库接收索引的文档。 该系统基于字格和索引文档，组合至少一个包括查询词，选择的索引文档和权重的三元组。 该系统基于至少一个三重生成通过该字格的N个最佳路径，并且基于该N最佳路径重新排列ASR输出。 系统通过查询字聚合每个权重，以产生N最佳列表，并根据重新排列的ASR输出和N最佳列表将搜索结果返回给语音查询。 晶格可以是混淆网络，其电弧密度可以针对期望的性能水平进行调整。

公开(公告)号：US20140358537A1

公开(公告)日：2014-12-04

申请号：US14459719

申请日：2014-08-14

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Mazin GILBERT ,  Srinivas BANGALORE ,  Patrick HAFFNER ,  Robert BELL

IPC: G10L15/32 ,  G10L15/06 ,  G10L15/26

CPC classification number: G10L15/32 ,  G10L15/063 ,  G10L15/26 ,  G10L2015/0638

Abstract: Disclosed herein are systems, methods and non-transitory computer-readable media for performing speech recognition across different applications or environments without model customization or prior knowledge of the domain of the received speech. The disclosure includes recognizing received speech with a collection of domain-specific speech recognizers, determining a speech recognition confidence for each of the speech recognition outputs, selecting speech recognition candidates based on a respective speech recognition confidence for each speech recognition output, and combining selected speech recognition candidates to generate text based on the combination.

Abstract translation: 本文公开了用于在不需要模型定制或接收到的语音的领域的先前知识的情况下在不同的应用或环境上执行语音识别的系统，方法和非暂时的计算机可读介质。 该公开内容包括：利用特定领域的语音识别器的集合来识别接收的语音，为每个语音识别输出确定语音识别置信度，基于每个语音识别输出的相应语音识别置信度选择语音识别候选，以及组合所选语音 识别候选人基于组合生成文本。