Transient learning of machine learning models von STROMAN TREVOR, BEAUFAYS FRANCOISE, SHEN QICAI, LITVIN OREN

Volltext bestellen

Enabling natural conversations with soft endpoints for automated assistants von STROMAN TREVOR, SMALL, JOSEPH, SCHALKWYK JOHAN, BLOOM JONATHAN, CONZELMANN JACLYN

Volltext bestellen

Unfluent detection model for natural talk voice system von STROMAN TREVOR, SAINATH TARA N, ZHANG SHUOYING, ZHANG CHAO, LI BO

Volltext bestellen

Training for long form speech recognition von STROMAN TREVOR, LU ZHIYUN, PRABHAKAR, ROHIT, DUTT, THIBAUT, PAN YANWEI, ZHANG CHAO, CAO LIANGLIANG

Volltext bestellen

Transducer-based streaming push for cascaded encoders von STROMAN TREVOR, SAINATH TARA N, NARAYANAN ARUN, PANG RUOMING, HU KE

Volltext bestellen

Optimizing reasoning performance of Conformer von STROMAN TREVOR, HOROMANSKI KRZYSZTOF, GULATI ANMOL, WANG WEIREN, SAINATH TARA N, YU JIAHUA, PANG RUOMING, BOTROS, RAMI

Volltext bestellen

Recognizing and correcting automatic speech recognition (ASR) error recognition in decentralized manner von ZHANG, HARRY, STROMAN TREVOR, PRABHAKAR, ROHIT, CHOW LILLIAN, CHEN MINGQING, MOTTA GIOVANNI, BEAUFAYS FRANCOISE, MATHEWS RAJIV, GULIANI, DEHROUF

Volltext bestellen

End-to-end model on high efficiency streaming non-recursive devices von VARIANI, EHSAN, STROMAN TREVOR, NARAYANAN ARUN, PANG RUOMING, BOTROS, RAMI, HE YANZHANG, ALOZEN CYRIL, LEIBACH, DAVID, SAINATH, TARA

Volltext bestellen

Utilizing end-to-end model to issue word timing von CASTRO GARCIA BASILIO, STROMAN TREVOR, SAINATH TARA N, PANG RUOMING, LEIBACH, DAVID

Volltext bestellen

Method and system for reducing latency in automated assistant interaction von GOLDFARB RAPHAEL, STROMAN TREVOR, TASCA NINO, GOODMAN MICHAEL ANDREW, OESTER DECKER, RACINE DAN, ALON LIOR, CONZELMANN JACLYN, NYGAARD VALERIE

Volltext bestellen

Cascade encoder for simplified streaming and non-streaming speech recognition von VARIANI, EHSAN, YU JIAHUI, STROMAN TREVOR, PRABHAKAR, ROHIT, NARAYANAN ARUN, PANG RUOMING, QIU ZHONGZHEN, SAINATH, TARA

Volltext bestellen

Joint acoustic and text device upper end-to-end model based on attention von STROMAN TREVOR, SAINATH TARA N, WISE, RON, PANG RUOMING, HE YANZHANG, QIU ZHONGZHEN

Volltext bestellen

ASR system on language-independent multi-language end-to-end streaming device von LIANG QIAO, STROMAN TREVOR, HAHANI, PARISHA, XU QIUMIN, CHEN VINCE, PANG RUOMING, ZHANG SHUOYING, BIDCHANDANI, SAMIR, SANAT TARA N, HE YANZHANG, LIU HEGUANG, LI BO

Volltext bestellen