Search results for: “stolcke”
-
Incorporating Tandem / HATs MLP Features into SRI’s Conversational Speech Recognition System
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLPs). The acoustic features are based on frame-level phone posterior probabilities, obtained by merging two different MLP estimators, one based on PLP-Tandem features, the other based on hidden activation TRAPs (HATs) features.
-
Two Experiments Comparing Reading with Listening for Human Processing of Conversational Telephone Speech
We report on results of two experiments designed to compare subjects’ ability to extract information from audio recordings of conversational telephone speech (CTS) with their ability to extract information from text transcripts of these conversations, with and without the ability to hear the audio recordings.
-
Does Active Learning Help Automatic Dialog Act Tagging in Meeting Data?
We ask if active learning with lexical cues can help for this task and this domain. To better address this question, we explore active learning for two different types of DA models — hidden Markov models (HMMs) and maximum entropy (maxent).
-
Improved Discriminative Training Using Phone Lattices
We present an efficient discriminative training procedure utilizing phone lattices. Different approaches to expediting lattice generation, statistics collection, and convergence were studied.
-
Leveraging Speaker-dependent Variation of Adaptation
This work introduces an automatic procedure for determining the size of regression class trees for individual speakers using an ensemble of speaker-level features to control the number of transformations, if any, that should be estimated by maximum likelihood linear regression.
-
Comparing HMM, Maximum Entropy, and Conditional Random Fields for Disfluency Detection
We compare a generative hidden Markov model (HMM)-based approach and two conditional models — a maximum entropy (Maxent) model and a conditional random field (CRF) — for detecting disfluencies in speech. The conditional modeling approaches provide a more principled way to model correlated features.
-
Using MLP Features in SRI’s Conversational Speech Recognition System
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLP). The acoustic features are based on frame-level phone posterior probabilities, obtained by merging two different MLP estimators, one based on PLP-Tandem features, the other based on hidden activation TRAPs (HATs) features.
-
Development of a Conversational Telephone Speech Recognizer for Levantine Arabic
In this paper, we describe the development of a large-vocabulary speech recognition system for Levantine Arabic, which was a new dialectal recognition task for our existing system. We discuss the dialect-specific modeling choices and investigate to what extent techniques previously tested on other languages are portable to the present task.
-
Using Conditional Random Fields for Sentence Boundary Detection in Speech
In this paper, we evaluate the use of a conditional random field (CRF) for this task and relate results with this model to our prior work. We evaluate across two corpora (conversational telephone speech and broadcast news speech) on both human transcriptions and speech recognition output.
-
SRI’s 2004 NIST Speaker Recognition Evaluation System
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 coefficients, and systems that use discriminant models from word n-grams and syllable-based NERF n-grams.
-
Structural Metadata Research in the EARS Program
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 disfluencies.
-
Improved Phonetic Speaker Recognition Using Lattice Decoding
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.