International Business Machines Corporation

Nuance Communications, Inc.

Beijing University of Chemical Tehcnology

Qin Shi

Yong Qin

Shi Lei Zhang

Wen Liu

Zhong Su

Jian Ye Chen

Zhiwei Shuang

Shenghua Bao

Feng Jin

Peng Wang

Sheng Hua Bao

Zhi Wei Shuang

Fan Ping Meng

William F Ganong, Iii

Liu Wen

Shilei Zhang

Wei Zhang

Wei Zhu

Songfang Huang

Hai Xin Chai

Shiwan Zhao

Wei Wu

Yi Liu

Lin Luo

Yue Chen

Jie Zhou

Peng Fei Zhu

Changhua Sun

Enliang Xu

Haixin Chai

Liqin Shen

Guang-Wen Chu

Hai-Kui Zou

Jian-Feng Chen

Li Jun Ma

Peng Cheng P P Zhu

Peng-Yuan Zhang

Traffic jam patterns can be identified and, based on historical traffic data, pre-traffic jam patterns that are likely to result in the traffic jam patterns can be identified as well. Real-time traffic data regarding a driving road of a community can be received and analyzed to determine whether the real-time traffic data match with a pre-traffic jam pattern. If the data matches a pre-traffic jam pattern, an alerting signal for predicting a traffic jam can be transmitted.

Traffic data analysis and traffic jam prediction

Embodiments of the present disclosure relate to object detection in an image. In an embodiment, a computer-implemented method is disclosed. According to the method, image data representing a scene is obtained and sound distribution information related to the scene is obtained. A detection strategy to be applied in object detection is determined based on the sound distribution information. The object detection is performed on the image data by applying the detection strategy. In other embodiments, a system and a computer program product are disclosed.

Object detection in an image

A computer-implemented method for utilizing external knowledge and memory networks in a question-answering system includes receiving, from a search engine of a question-answering system, one or more search results based on a search query associated with a question submitted via a user interface associated with a computing device, analyzing the one or more search results to generate search evidence as a source of external knowledge for generating an answer to the question, the search evidence including one or more titles and one or more corresponding text snippets, encoding the search evidence and the search query to generate vectors stored in a memory network, obtaining a final vector representation based on the encoding, and decoding the final vector representation to obtain the answer to the question.

Utilizing external knowledge and memory networks in a question-answering system

Techniques are described that facilitate automatically distinguishing between different expressions of a same or similar emotion. In one embodiment, a computer-implemented is provided that comprises partitioning, by a device operatively coupled to a processor, a data set comprising facial expression data into different clusters of the facial expression data based on one or more distinguishing features respectively associated with the different clusters, wherein the facial expression data reflects facial expressions respectively expressed by people. The computer-implemented method can further comprise performing, by the device, a multi-task learning process to determine a final number of the different clusters for the data set using a multi-task learning process that is dependent on an output of an emotion classification model that classifies emotion types respectively associated with the facial expressions.

Emotion classification based on expression variations associated with same or similar emotions

Techniques for generating a personality trait model are described. According to an example, a system is provided that can generate text data and linguistic data, and apply psycholinguistic data to the text data and the linguistic data, resulting in updated text data and updated linguistic data. The system is further operable to combine the updated text data with the updated linguistic data to generate a personality trait model. In various embodiments, the personality trait model can be trained and updated as additional data is received from various inputs.

Predicting personality traits based on text-speech hybrid data

Techniques are provided for generating recommended query terms that are specialized to a topic of desired information based on a query associated with a user. In one example, a computer-implemented method comprising selecting, by a system operatively coupled to a processor, a coarse cluster of corpus terms having a defined relatedness to a query associated with a user from a plurality of coarse clusters of corpus terms; and determining, by the system, a plurality of candidate terms from search results associated with the query. The computer-implemented method can also comprise determining, by the system, at least one recommended query term based on refined clusters of the coarse cluster, the candidate terms, and the query; and displaying, by the system, the at least one recommended query term on a display device associated with the query.

Specialist keywords recommendations in semantic space

Speech recognition is performed by receiving a speech signal that includes spoken phones. A dynamic time warping procedure is applied to the received speech signal to generate a time-warped signal. The time-warped signal is compared to a plurality of stored reference patterns to identify a set of stored reference patterns that are most similar to the time-warped signal. A candidate hot word is selected from a list using the identified set of stored reference patterns. The selection of the candidate hot word is then refined.

Speech recognition by selecting and refining hot words

According to an embodiment of the present invention, a computer-implemented method for modeling text-to-articulatory movement conversion is provided. In the method, text features are generated for a plurality of texts, wherein the text feature comprises a phoneme. Articulatory features are determined for the plurality of texts from a plurality of audio signals and a plurality of visual signals, wherein the audio signals record speeches of the plurality of texts, the visual signals record three-dimensional images of an articulator when speaking the plurality of texts, and the articulatory features indicate articulatory positions of the articulator in the speeches. A text-to-articulatory movement model is established with the text features as inputs and the articulatory features as outputs.

Text-to-articulatory movement

Techniques disclosed herein include systems and methods for open-domain voice-enabled searching that is speaker sensitive. Techniques include using speech information, speaker information, and information associated with a spoken query to enhance open voice search results. This includes integrating a textual index with a voice index to support the entire search cycle. Given a voice query, the system can execute two matching processes simultaneously. This can include a text matching process based on the output of speech recognition, as well as a voice matching process based on characteristics of a caller or user voicing a query. Characteristics of the caller can include output of voice feature extraction and metadata about the call. The system clusters callers according to these characteristics. The system can use specific voice and text clusters to modify speech recognition results, as well as modifying search results.

Speaker and call characteristic sensitive open voice search

A method and system for achieving emotional text to speech. The method includes: receiving text data; generating emotion tag for the text data by a rhythm piece; and achieving TTS to the text data corresponding to the emotion tag, where the emotion tags are expressed as a set of emotion vectors; where each emotion vector includes a plurality of emotion scores given based on a plurality of emotion categories. A system for the same includes: a text data receiving module; an emotion tag generating module; and a TTS module for achieving TTS, wherein the emotion tag is expressed as a set of emotion vectors; and wherein emotion vector includes a plurality of emotion scores given based on a plurality of emotion categories.

Method and system for achieving emotional text to speech utilizing emotion tags expressed as a set of emotion vectors

The present invention relates to voice processing and provides a method and system for correcting a text. The method comprising: determining a target text unit to be corrected in a text; receiving a reference voice segment input by the user for the target text unit; determining a reference text unit whose pronunciation is similar to a word in the target text unit based on the reference voice segment; and correcting the word in the target text unit in the text by the reference text unit. The present invention enables the user to easily correct errors in the text vocally.

Correcting text with voice processing

A method, system and computer readable storage medium for assessing speech prosody. The method includes the steps of: receiving input speech data; acquiring a prosody constraint; assessing prosody of the input speech data according to the prosody constraint; and providing assessment result where at least of the steps is carried out using a computer device.

Assessing speech prosody

Growing community of inventors

Beijing, China

Qin Shi