Towards better language models for spontaneous speech

In our eeort to build a speech{to{speech translation system for spontaneous spoken dialogs we have developed several methods to improve the language models of the speech decoder of the system. We attempt to take advantage of natural equivalence word classes, frequently occur-ing word phrases, and discourse structure. Each of these methods was tested on spontaneous English, German and Spanish human{human dialogs.

• Publication year

  1994

• Venue

  ICSLP

• Publication date

  1994-09-18

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.21437/ICSLP.1994-222
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Speech--Language Integration In A Multi--Lingual Speech Translation System

  1994cited by this paper
• JANUS 93: towards spontaneous speech translation

  1994cited by this paper
• Predicting and Managing Spoken Disfluencies During Human-Computer Interaction

  1994cited by this paper
• Estimating 'small' probabilities by leaving-one-out

  1993cited by this paper
• Flexible use of semantic constraints in speech recognition

  1993cited by this paper
• Class-Based n-gram Models of Natural Language

  1992cited by this paper
• Understanding spontaneous speech: the Phoenix system

  1991cited by this paper
• Stochastic Representation of Conceptual Structure in the ATIS Task

  1991cited by this paper
• \self-organized Language Modeling for Speech Recognition". In

  year unknowncited by this paper

• From Speech to Summary: A Comprehensive Survey of Speech Summarization

  2025cites this paper
• Bayesian Low-Rank Factorization for Robust Model Adaptation

  2025cites this paper
• Weight Factorization and Centralization for Continual Learning in Speech Recognition

  2025cites this paper
• Summarizing Speech: A Comprehensive Survey

  2025cites this paper
• Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognition

  2025cites this paper
• Continuously Learning New Words in Automatic Speech Recognition

  2024cites this paper
• Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages

  2024cites this paper
• An Overview on Language Models: Recent Developments and Outlook

  2023cites this paper
• Modelos da Língua Baseados em Classes de Palavras para Sistema de Reconhecimento de Fala Contínua 10.14209/jcis.1999.10

  2015cites this paper
• Adding New Words into a Language Model using Parameters of Known Words with Similar Behavior

  2015cites this paper
• Integrating history-length interpolation and classes in language modeling

  2011cites this paper
• A Low-Power Hardware Architecture for Speech Recognition Search

  2011cites this paper
• Multimodal Processing and Interaction, Audio, Video, Text

  2010cites this paper
• IMPROVED LANGUAGE MODELING BY UNSUPERVISED ACQUISITION OF STRUCTURE

  2009cites this paper
• Phrase classes in two-level language models for ASR

  2009cites this paper
• Hierarchical linear discounting class N-gram language models: A multilevel class hierarchy approach

  2008cites this paper
• Toward the Integration of Natural Language Processing and Automatic Speech Recognition: Using Morpho-Syntax and Pragmatics for Transcription

  2008cites this paper
• Act Modeling for Conversational

  2008cites this paper
• Pragmatics and Computational Linguistics

  2008influential citation
• Class-based statistical machine translation for field maintainable speech-to-speech translation

  2008cites this paper
• DBN Based Joint Dialogue Act Recognition of Multiparty Meetings

  2007cites this paper
• Speech recognition co-processor

  2007cites this paper
• Informations morpho-syntaxiques et adaptation thématique pour améliorer la reconnaissance de la parole

  2007cites this paper
• Linearly Interpolated Hierarchical N-gram Language Models for Speech Recognition Engines

  2007influential citation
• Backoff hierarchical class n-gram language models: effectiveness to model unseen events in speech recognition

  2007cites this paper
• Hardware implementation of a low power speech recognition system

  2007cites this paper
• Utilisation de la linguistique en reconnaissance de la parole : un état de l'art

  2006cites this paper
• Modelling speech acts in conversational discourse

  2005cites this paper
• CSE 256 (Spring 2004) "Language Models for Spelling Correction"

  2004cites this paper
• Statistical feature language model

  2004cites this paper
• The Properties and Further Applications of Chinese Frequent Strings

  2004cites this paper
• Statistical language modeling based on variable-length sequences

  2003cites this paper
• Effectiveness of the backoff hierarchical class n-gram language models to model unseen events in speech recognition

  2003cites this paper
• Bilingual Collocation Extraction Based on Syntactic and Statistical Analyses

  2003cites this paper
• CSE 254 (Spring 2003) "Growing N-gram Trees for Language Modeling"

  2003cites this paper
• Hierarchical class n-gram language models: towards better estimation of unseen events in speech recognition

  2003cites this paper
• Learning a syntagmatic and paradigmatic structure from language data with a bi-multigram model

  2002cites this paper
• Backoff hierarchical class n-gram language modelling for automatic speech recognition systems

  2002cites this paper
• A new lexicon optimization method for LVCSR based on linguistic and acoustic characteristics of words

  2002cites this paper
• Learning Strategies In A Grammar Induction Framework

  2001cites this paper
• Data-driven approach to designing compound words for continuous speech recognition

  2001influential citation
• Pragmatics and Computational Linguistics [ for Handbook of Pragmatics ]

  2001cites this paper
• Dialog Act Modeling for Automatic Tagging and Recognition of Conversational Speech

  2000cites this paper
• Beyond the conventional statistical language models: the variable-length sequences approach

  2000cites this paper
• Dialog Act Modeling for Automatic Tagging and Recognition of Conversational Speech

  2000cites this paper
• Modelos K-explorables en sentido estricto integrados en un sistema de reconocimiento automático del habla

  2000cites this paper
• Vers une meilleure modélisation du langage : la prise en compte des séquences dans les modèles statistiques

  2000cites this paper
• Dialogue act modeling for automatic tagging and recognition of conversational speech

  2000cites this paper
• Effects of word string language models on noisy broadcast news speech recognition

  2000cites this paper
• Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

  2000cites this paper
• Multimodal interactive error recovery for non-conversational speech user interfaces

  1999cites this paper
• Variable-Length Sequence Language Model for Large Vocabulary Continuous Dictation Machine

  1999cites this paper
• Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech?

  1998cites this paper
• Flexible speech understanding based on combined key-phrase detection and verification

  1998influential citation
• A language modeling based on a hierarchical approach: m_n^v

  1998cites this paper
• Using information above the word level for automatic speech recognition

  1998influential citation
• Performance evaluation of word phrase and noun category language models for broadcast news speech recognition

  1998cites this paper
• Learning a Syntagmatic and Paradigmatic Structure from Language Data with a Bi-Multigram Model

  1998cites this paper
• Dialog Act Modeling for Conversational Speech

  1998cites this paper
• Dialog act modelling for conversational speech

  1998cites this paper
• Lexical, Prosodic, and Syntactic Cues for Dialog Acts

  1998cites this paper
• Automatic detection of discourse structure for speech recognition and understanding

  1997cites this paper
• Category-Based Statistical Language Models

  1997cites this paper
• Phrase language models for detection and verification-based speech understanding

  1997cites this paper
• Switchboard Discourse Language Modeling Project (Final Report)

  1997cites this paper
• PHRASE LANGUAGE MODELS FOR SPEECH UNDERSTANDING DETECTION AND VERIFICATION-BASED

  1997cites this paper
• What makes a word: Learning base units in Japanese for speech recognition

  1997cites this paper
• Inference of variable-length linguistic and acoustic units by multigrams

  1997cites this paper
• From HMM's to segment models: a unified view of stochastic modeling for speech recognition

  1996cites this paper
• Concept-based phrase spotting approach for spontaneous speech understanding

  1996cites this paper
• Evaluation of a language model using a clustered model backoff

  1996cites this paper
• Class phrase models for language modeling

  1996cites this paper
• Clustering words for statistical language models based on contextual word similarity

  1996cites this paper
• A maximum entropy approach to adaptive statistical language modelling

  1996cites this paper
• Key-phrase detection and verification for flexible speech understanding

  1996cites this paper
• Improved language modelling by unsupervised acquisition of structure

  1995cites this paper
• JANUS II - ADVANCES IN SPONTANEOUS SPEECH TRANSLATION

  1995cites this paper
• Phrase bigrams for continuous speech recognition

  1995cites this paper
• Integrating different learning approaches into a multilingual spoken language translation system

  1995cites this paper
• Janus: Towards Multilingual Spoken Language Translation

  1995cites this paper
• IMPROVED LANGUAGE MODELING BY UNSUPERVISED ACQUISITION OF STRUCTURE

  1995cites this paper
• Adaptive Statistical Language Modeling; A Maximum Entropy Approach

  1994cites this paper
• JANUS : TOWARDS MULTILINGUAL SPOKEN LANGUAGE TRANSLATION

  year unknowncites this paper