Publications
-
SVM Modeling of “SNERF-Grams” for Speaker Recognition
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…
-
Effective Acoustic Modeling for Rate-of-Speech Variation in Large Vocabulary Conversational Speech Recognition
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.
-
National Early Intervention Longitudinal Study (NEILS): Family Outcomes at the End of Early Intervention
The report has two primary aims: to describe the outcomes reported by families following their experience with early intervention programs, and to identify a subset of families who were less…
-
On Using MLP Features in LVCSR
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…
-
Using Machine Learning to Cope with Imbalanced Classes in Natural Speech: Evidence from Sentence Boundary and Disfluency Detection
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…
-
Morphology-Based Language Modeling for Arabic Speech Recognition
In this paper we investigate the use of morphology-based language models at different stages in a speech recognition system for conversational Arabic.
-
From Switchboard to Meetings: Development of the 2004 ICSI-SRI-UW Meeting Recognition System
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…
-
The ICSI-SRI-UW Metadata Extraction System
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.
-
A Wizard of Oz framework for collecting spoken human-computer dialogs
This paper describes a data collection process aimed at gathering human-computer dialogs in high-stress or “busy” domains where the user is concentrating on tasks other than the conversation, for example,…
-
Assessment In The Palm Of Your Hand: Handheld Computers Transform The Assessment Process
-
Automatic Diacritization of Arabic for Acoustic Modeling in Speech Recognition
In this paper we investigate different procedures that enable us to use training data by automatically inserting the missing diacritics into the transcription.
-
Database Editing Metrics for Pattern Matching
This paper introduces a family of metrics to measure the degree of qualitative match between a database and a pattern, that is, an elastic constraint on database objects and their…