Search Results - "Stolcke, A."

The Microsoft 2017 Conversational Speech Recognition System by Xiong, W., Wu, L., Alleva, F., Droppo, J., Huang, X., Stolcke, A.

“…We describe the latest version of Microsoft's conversational speech recognition system for the Switchboard and CallHome domains. The system adds a CNN-BLSTM…”
Get full text

The microsoft 2016 conversational speech recognition system by Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M., Stolcke, A., Yu, D., Zweig, G.

“…We describe Microsoft's conversational speech recognition system, in which we combine recent developments in neural-network-based acoustic and language…”
Get full text

Enriching speech recognition with automatic detection of sentence boundaries and disfluencies by Yang Liu, Shriberg, E., Stolcke, A., Hillard, D., Ostendorf, M., Harper, M.

“…Effective human and automatic processing of speech requires recovery of more than just the words. It also involves recovering phenomena such as sentence…”
Get full text

Modeling prosodic feature sequences for speaker recognition by Shriberg, E., Ferrer, L., Kajarekar, S., Venkataraman, A., Stolcke, A.

“…We describe a novel approach to modeling idiosyncratic prosodic behavior for automatic speaker recognition. The approach computes various duration, pitch, and…”
Get full text

Speaker Recognition With Session Variability Normalization Based on MLLR Adaptation Transforms by Stolcke, A., Kajarekar, S.S., Ferrer, L., Shrinberg, E.

“…We present a new modeling approach for speaker recognition that uses the maximum-likelihood linear regression (MLLR) adaptation transforms employed by a speech…”
Get full text

Recent innovations in speech-to-text transcription at SRI-ICSI-UW by Stolcke, A., Barry Chen, Franco, H., Venkata Ramana Rao Gadde, Graciarena, M., Mei-Yuh Hwang, Kirchhoff, K., Mandal, A., Morgan, N., Xin Lei, Ng, T., Ostendorf, M., Sonmez, K., Venkataraman, A., Vergyri, D., Wen Wang, Jing Zheng, Qifeng Zhu

“…We summarize recent progress in automatic speech-to-text transcription at SRI, ICSI, and the University of Washington. The work encompasses all components of…”
Get full text

Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech? by Shriberg, Elizabeth, Bates, Rebecca, Stolcke, Andreas, Taylor, Paul, Jurafsky, Daniel, Ries, Klaus, Coccaro, Noah, Martin, Rachel, Meteer, Marie, van Ess-Dykema, Carol

“…Investigated whether current approaches to automatically classifying dialog acts (DAs) in natural conversation could be improved by adding prosodic…”
Get more information

Statistical language modeling for speech disfluencies by Stolcke, A., Shriberg, E.

“…Speech disfluencies (such as filled pauses, repetitions, restarts) are among the characteristics distinguishing spontaneous speech from planned or read speech…”
Get full text

The use of a linguistically motivated language model in conversational speech recognition by Wen Wang, Stolcke, A., Harper, M.P.

“…Structured language models have recently been shown to give significant improvements in large-vocabulary recognition relative to traditional word N-gram…”
Get full text

Finding consensus in speech recognition: word error minimization and other applications of confusion networks by Mangu, Lidia, Brill, Eric, Stolcke, Andreas

“…We describe a new framework for distilling information from word lattices to improve the accuracy of the speech recognition output and obtain a more…”
Get full text

Editorial for computer speech and language by Stolcke, A.

Get full text

The CALO Meeting Assistant System by Tur, G, Stolcke, A, Voss, L, Peters, S, Hakkani-Tur, Dilek, Dowding, J, Favre, B, Fernandez, R, Frampton, M, Frandsen, M, Frederickson, C, Graciarena, M, Kintzing, D, Leveque, K, Mason, S, Niekrasz, J, Purver, M, Riedhammer, K, Shriberg, E, Jing Tien, Vergyri, D, Fan Yang

“…The CALO Meeting Assistant (MA) provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and…”
Get full text

Prosody-based automatic segmentation of speech into sentences and topics by Shriberg, Elizabeth, Stolcke, Andreas, Hakkani-Tür, Dilek, Tür, Gökhan

“…A crucial step in processing speech audio data for information extraction, topic detection, or browsing/playback is to segment the input into sentence and…”
Get full text

Multispeaker speech activity detection for the ICSI meeting recorder by Pfau, T., Ellis, D.P.W., Stolcke, A.

“…As part of a project into speech recognition in meeting environments, we have collected a corpus of multichannel meeting recordings. We expected the…”
Get full text

Meetings about meetings: research at ICSI on speech in multiparty conversations by Morgan, N., Baron, D., Bhagat, S., Carvey, H., Dhillon, R., Edwards, J., Gelbart, D., Janin, A., Krupski, A., Peskin, B., Pfau, T., Shriberg, E., Stolcke, A., Wooters, C.

“…In early 2001, we reported (at the Human Language Technology meeting) the early stages of an ICSI (International Computer Science Institute) project on…”
Get full text

Nonparametric feature normalization for SVM-based speaker verification by Stolcke, A., Kajarekar, S., Ferrer, L.

“…We investigate several feature normalization and scaling approaches for use in speaker verification based on support vector machines. We are particularly…”
Get full text

Neural-network based measures of confidence for word recognition by Weintraub, M., Beaufays, F., Rivlin, Z., Konig, Y., Stolcke, A.

“…This paper proposes a probabilistic framework to define and evaluate confidence measures for word recognition. We describe a novel method to combine different…”
Get full text

Automatic linguistic segmentation of conversational speech by Stolcke, A., Shriberg, E.

“…As speech recognition moves toward more unconstrained domains such as conversational speech, we encounter a need to be able to segment (or resegment) waveforms…”
Get full text

Open-vocabulary spoken term detection using graphone-based hybrid recognition systems by Akbacak, M., Vergyri, D., Stolcke, A.

“…We address the problem of retrieving out-of-vocabulary (OOV) words/queries from audio archives for spoken term detection (STD) task. Many STD systems use the…”
Get full text

Unsupervised Languagemodel Adaptation for Meeting Recognition by Tur, G., Stolcke, A.

“…We present an application of unsupervised language model (ML) adaptation to meeting recognition, in a scenario where sequences of multiparty meetings on…”
Get full text