Articles

We present results of a study of the relationship between intonational features including pitch range, timing, and amplitude and aspects of discourse structure defined in terms of Grosz and Sidner's (1986) model of discourse. We compare structural labelings of AP news text with prosodic/acoustic features examined from recordings of the …...

A persistent problem for keyword-driven speech recognition sys- tems is that users often embed the to-be-recognized words or phrases in longer utterances. The recognizer needs to locate the relevant sections of the speech signal and ignore extraneous words. Prosody might provide an extra source of information to help locate target …...

The relative size and location of prosodic phrase boundaries provides an important cue for resolving syntactic ambiguity. In previous work, we have introduced an analysis/synthesis formalism for scoring parses in terms of the similarity be- tween prosodic patterns recognized from a given utterance and synthesized for the hypothesized parse. This …...

It is natural to expect phrase structure to be important in predicting prosodic phrasing. Yet there appears to be a concensus that syntactic phrases do not correspond well to prosodic phrasing, and independent structures have been pro- posed to account for prosody. I propose that the problem with phrase structure …...

We have analyzed 607 sentences of spontaneous human- computer speech data containing repairs (drawn from a cor- pus of 10,718). We present here criteria and techniques for automatically detecting the presence of a repair, its loca- tion, and making the appropriate correction. The criteria in- volve integration of knowledge from …...

The stack decoder is an attractive algorithm for controlling the acoustic and language model matching in a continuous speech recognizer. A previous paper described a near-optimal admissible Viterbi A* search algorithm for use with non- cross-word acoustic models and no-grammar language models [16]. This paper extends this algorithm to include …...

The work described here focuses on recognition of the Wall Street Journal (WSJ) pilot database [17], a new CSR database which supports 5K, 20K, and up to 64K- word CSR tasks. The original Lincoln Tied-Mixture HMM CSR was im- plemented using a time-synchronous beam-pruned search of a static network[14] and …...

This paper reports recent efforts to apply the speaker-independent SPHINX-H system to the DARPA Wall Street Journal continuous speech recognition task. In SPHINX-H, we incorporated ad- ditional dynamic and speaker-normalized features, replaced dis- crete models with sex-dependent semi-continuous hidden Markov models, augmented within-word triphones with between-word triphones, and extended generalized …...

In this paper we present some of the algorithm improvements that have been made to Dragon's continuous speech recog- nition and training prograxns, improvements that have more than halved our error rate on the Resource Management task since the last SLS meeting in February 1991. We also report the "dry …...

Recently, the DARPA community started a new data col- lection initiative in the Wall Street Journal (WSJ) domain to support research and development of very large vocabu- lary continuous speech recognition (CSR) systems. Since Au- gust 1991, our group has actively participated in the develop- ment of the WSJ-CSR corpus. …...

A series of experiments on speaker-independent phone recogni- tion of continuous speech have been carried out using the recently recorded BREF corpus. These experiments are the first to use this large corpus, and are meant to provide a baseline performance eval- uation for vocabulary-independent phone recognition of French. The HMM-based …...

The DARPA Spoken Language System (SLS) community has long taken a leadership position in designing, imple- menting, and globally distributing significant speech corpora widely used for advancing speech recognition research. The Wall Street Journal (WSJ) CSR Corpus described here is the newest addition to this valuable set of resources. In …...

As part of a pilot data collection for DARPA's Continuous Speech Recognition (CSR) speech corpus, SRI International experi- mented with the collection of spontaneous speeoh material. The bulk of the CSR pilot data was read versions of news articles from the Wall Street Journal (WSJ), and the spontaneous sentences were …...

We describe three analyses on the effects of spontaneous speech on continuous speech recognition performance. We have found that: (1) spontaneous speech effects signifi- cantly degrade recognition performance, (2) fluent sponta- neous speech yields word accuracies equivalent to read speech, and (3) using spontaneous speech training data can significantly improve …...

We present a new search algorithm for very large vocabulary contin- uous speech recognition. Continuous speech recognition with this algorithm is only about 10 times more computationally expensive than isolated word recognition. We report preliminary recognition results obtained by testing our recognizer on "books on tape" using a 60,000 word …...

This paper describes a new algorithm for building rapid match models for use in Dragon's continuous speech recog- nizer. Rather than working from a single representative token for each word, the new procedure works directly from a set of trained hidden Markov models. By simulated traversals of the HMMs, we …...

On what basis are the input processing capabilities of Natural Language software judged? That is, what are the capabilities to be described and measured, and what are the standards against which we measure them? Rome Laboratory is currently supporting an effort to develop a concise terminology for describing the linguistic …...

This paper first briefly describes the architecture of PLUM, BBN's text processing system, and then reports on some experiments evaluating the effectiveness of the design at the component level. Three features are unusual in PLUM's architecture: a domain- independent deterrninistie parser, processing of (the resulting) fragments at the semantic and …...

This paper presents the fallback understanding component of BBN's DELPHI NL sysystem. This component is invoked when the core DELPHI system is unable to understand an input. It incorporates both syntax- and frame-based fragment combination sub-components, in an attempt to provide a smoother path from accurate but fragile conventional parsers …...

This paper describes an extension to the MIT ATIS (Air Travel Information Service) system, which allows it to answer a question when a full linguistic analysis fails. This "robust" parsing capability was achieved through minor extensions of pre-existing components already in place for the full linguis- tic analysis component. Robust …...