N-best speech hypotheses reordering using linear regression

We propose a hypothesis reordering technique to improve speech recognition accuracy in a dialog system. For such systems, additional information external to the decoding process itself is available, in particular features derived from the parse and the dialog. Such features can be combined with recognizer features by means of a linear regression model to predict the most likely entry in the hypothesis list. We introduce the use of concept error rate as an alternative accuracy measurement and compare it withy the use of word error rate. The proposed model performs better than human subjects performing the same hypothesis reordering task.

• Publication year

  2001

• Venue

  Interspeech

• Publication date

  2001-09-03

• Fields of study

  Computer Science

• Identifiers
  DOI 10.21437/Eurospeech.2001-432
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Task and domain specific modelling in the Carnegie Mellon communicator system

  2000influential reference
• The use of dynamic reliability scoring in speech recognition

  2000cited by this paper
• Beyond N-Grams: Can Linguistic Sophistication Improve Language Modeling?

  1998cited by this paper
• Statistical language modeling using the CMU-cambridge toolkit

  1997cited by this paper
• Towards understanding spontaneous speech: word accuracy vs. concept accuracy

  1996cited by this paper
• Combining Linguistic and Statistical Knowledge Sources in Natural-Language Processing for ATIS

  1995influential reference
• Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists

  1994influential reference
• The SPHINX-II speech recognition system: an overview

  1993cited by this paper
• Understanding spontaneous speech: the Phoenix system

  1991cited by this paper

• Employee Attrition Prediction Using Machine Learning Algorithms

  2023cites this paper
• Real-time ASR Customization via Hypotheses Re-ordering: A Comparative Study of Different Scoring Functions

  2022cites this paper
• Leveraging ASR N-Best in Deep Entity Retrieval

  2021cites this paper
• Survey on evaluation methods for dialogue systems

  2019cites this paper
• Context-Aware Dialog Re-Ranking for Task-Oriented Dialog Systems

  2018cites this paper
• Selection and combination of hypotheses for dialectal speech recognition

  2016cites this paper
• Toward incremental dialogue act segmentation in fast-paced interactive dialogue systems

  2016cites this paper
• Hypotheses ranking and state tracking for a multi-domain dialog system using multiple ASR alternates

  2015cites this paper
• The Semiotic Structure of Geometry Diagrams: How Textbook Diagrams Convey Meaning

  2015cites this paper
• Improving Speech Recognizer Performance in a Dialog System Using N-best Hypotheses Reranking

  2015cites this paper
• An empirical investigation of sparse log-linear models for improved dialogue act classification

  2013cites this paper
• Modeling user behavior online for disambiguating user input in a spoken dialogue system

  2013cites this paper
• Using POMDP-based Reinforcement Learning for Online Optimization of Teaching Strategies in an Intelligent Tutoring System

  2013cites this paper
• Improving Spoken Dialogue Understanding Using Phonetic Mixture Models

  2011cites this paper
• Modeling Human-Robot Interaction Based on Generic Interaction Patterns

  2010cites this paper
• Spoken Language Understanding via Supervised Learning and Linguistically Motivated Features

  2010cites this paper
• Contextual computing for natural language processing

  2009cites this paper
• Evaluating the potential utility of ASR n-best lists for incremental spoken dialogue systems

  2009cites this paper
• Incorporating non-verbal modalities in spoken language understanding for multimodal conversational systems

  2009cites this paper
• Acquiring and maintaining knowledge by natural multimodal dialog

  2009cites this paper
• User Simulations for Context-Sensitive Speech Recognition in Spoken Dialogue Systems

  2009cites this paper
• Toward Widely-Available and Usable Multimodal Conversational Interfaces

  2009cites this paper
• Beyond attention: the role of deictic gesture in intention recognition in multimodal conversational interfaces

  2008cites this paper
• Discriminative learning using linguistic features to rescore n-best speech hypotheses

  2008cites this paper
• Learning N-Best Correction Models from Implicit User Feedback in a Multi-Modal Local Search Application

  2008cites this paper
• Response-Based Confidence Annotation for Spoken Dialogue Systems

  2008cites this paper
• Dialogue Context-Based Speech Recognition using User Simulation

  2008cites this paper
• Machine learning for spoken dialogue systems

  2007cites this paper
• Generating Statistical Language Models from Interpretation Grammars in Dialogue Systems

  2006cites this paper
• Robust interpretation in dialogue by combining confidence scores with contextual features

  2006cites this paper
• DIALOGUE CONTEXT-BASED RE-RANKING OF ASR HYPOTHESES

  2006cites this paper
• D2.1: Integration of ontological knowledge with the ISU approach

  2006cites this paper
• D1.3: SLM generation in the Grammatical Framework

  2006cites this paper
• Context dependent speech recognition

  2006influential citation
• Using Dialogue Context to Improve Parsing Performance in Dialogue Systems

  2005influential citation
• D4. 1: Integration of Learning and Adaptivity with the ISU approach

  2005cites this paper
• Combining Confidence Scores with Contextual Features for Robust Multi-Device Dialogue

  2005cites this paper
• Combining Acoustic and Pragmatic Features to Predict Recognition Performance in Spoken Dialogue Systems

  2004cites this paper
• Towards Measuring Scalability in Natural Language Understanding Tasks

  2004cites this paper
• Context-sensitive speech recognition in ISU dialogue systems: results for the grammar switching approach

  2004cites this paper
• Combining Acoustic Confidences and Pragmatic Plausibility for Classifying Spoken Chess Move Instructions

  2004cites this paper
• Apply n-best list re-ranking to acoustic model combinations of boosting training

  2004cites this paper
• multithreaded context for robust conversational interfaces: Context-sensitive speech recognition and interpretation of corrective fragments

  2004cites this paper
• A data-driven spoken language understanding system

  2003cites this paper
• CI-based NLU methodology with applications in information content control

  2003cites this paper
• N-best speech hypothesis reordering based on comprehensive information theory

  2003cites this paper
• How can a dialogue system compensate for speech recognition deficiencies

  2002cites this paper
• Integrating Multiple Knowledge Sources for Utterance-Level Confidence Annotation in the CMU Communicator Spoken Dialog System

  2002cites this paper