Speech & natural language publications

This paper describes our recent efforts in exploring longer-range features and their statistical modeling techniques for speaker recognition. In particular, we describe a system that uses discriminant features from cepstral…

In this paper we provide a brief overview of research on structural metadata extraction in the DARPA EARS rich transcription program. Tasks include detection of sentence boundaries, filler words, and…

In this paper, we present results on the Switchboard-2 corpus, where we compare 1-best phone decodings versus lattice phone decodings for the purposes of performing phonetic speaker recognition.

We explore the two related tasks of dialog act (DA) segmentation and DA classification for speech from the ICSI Meeting Corpus. We employ simple lexical and prosodic knowledge sources, and…

We describe a novel approach to modeling idiosyncratic prosodic behavior for automatic speaker recognition.

We describe a state-of-the-art system for automatic detection of "metadata" in both broadcast news and spontaneous telephone conversations, developed as part of the DARPA EARS Rich Transcription program.

We investigate machine learning techniques for coping with highly skewed class distributions in two spontaneous speech processing tasks. Both tasks, sentence boundary and disfluency detection, provide important structural information for…

In this paper we investigate the use of morphology-based language models at different stages in a speech recognition system for conversational Arabic.

We describe the ICSI-SRI-UW team's entry in the Spring 2004 NIST Meeting Recognition Evaluation. The system was derived from SRI's 5xRT Conversational Telephone Speech (CTS) recognizer by adapting CTS acoustic…

One of the major research thrusts in the speech group at ICSI is to use Multi-Layer Perceptron (MLP) based features in automatic speech recognition (ASR). This paper presents a study…

We investigate several variants of speech-rate-dependent acoustic models for large-vocabulary conversational speech recognition, in the framework of combining rate-specific models in decoding to compensate for speech rate variation.

We describe a new approach to modeling idiosyncratic prosodic behavior for automatic speaker recognition. The approach computes prosodic features by syllable, and models the syllable-feature sequences using support vector machines…