Speech & natural language publications

We investigate using state-of-the-art speaker diarization output for speech recognition purposes.

We present a method for annotating verbal reference to people in conversational speech, with a focus on reference to conversation participants.

We propose a novel approach to modeling prosodic features.

We find that ISV compensation is remarkably successful on a corpus of intrinsic variation that is highly controlled for channel (a dominant component of ISV). The results are particularly surprising…

We describe and analyze inference strategies for combining outputs from multiple question answering systems each of which was developed independently.

This work presents an extended Joint Factor Analysis model including explicit modelling of unwanted within-session variability.

We describe the recent progress in SRI's Mandarin speech-to-text system developed for 2008 evaluation in the DARPA GALE program. A data-driven lexicon expansion technique and language model adaptation methods contribute…

We describe a system for highly accurate large-vocabulary Mandarin speech recognition. The prevailing hidden Markov model based technologies are essentially language independent and constitute the backbone of our system.

We propose a new approach that takes into account speech from other talkers, relying only on speech/non-speech information from all participants.

We explore the integration of multiple factors such as genre and speaker gender for acoustic model adaptation tasks to improve Mandarin ASR system performance on broadcast news and broadcast conversation…

In this paper we explore the use of other speaker verification systems on the telephone channel data and compare against the GMM baseline. We found the GMM system to be…

We investigate genre effects on the task of automatic sentence segmentation, focusing on two important domains - broadcast news (BN) and broadcast conversation (BC).