An Overview of the SPHINX-II Speech Recognition System

In the past year at Carnegie Mellon steady progress has been made in the area of acoustic and language modeling. The result has been a dramatic reduction in speech recognition errors in the SPHINX-II system. In this paper, we review SPHINX-II and summarize our recent efforts on improved speech recognition. Recently SPHINX-II achieved the lowest error rate in the November 1992 DARPA evaluations. For 5000-word, speaker-independent, continuous, speech recognition, the error rate was reduced to 5%.

• Publication year

  1993

• Venue

  Human Language Technology - The Baltic Perspectiv

• Publication date

  1993-03-21

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/1075671.1075690
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Shared-distribution hidden Markov models for speech recognition

  1993cited by this paper
• An Improved Search Algorithm for Continuous Speech Rec-ognition

  1993cited by this paper
• An improved search algorithm using incremental knowledge for continuous speech recognition

  1993cited by this paper
• Unified stochastic engine (USE) for speech recognition

  1993influential reference
• A comparative study of discrete, semicontinuous, and continuous hidden Markov models

  1993cited by this paper
• Phoneme classification using semicontinuous hidden Markov models

  1992cited by this paper
• Discriminative learning for minimum error classification [pattern recognition]

  1992influential reference
• Applying SPHINX-II to the DARPA Wall Street Journal CSR Task

  1992cited by this paper
• Minimizing Speaker Variation Effects for Speaker-Independent Speech Recognition

  1992cited by this paper
• Subphonetic modeling with Markov states-Senone

  1992cited by this paper
• New uses for the N-Best sentence hypotheses within the BYBLOS speech recognition system

  1992cited by this paper
• Improved acoustic modeling with the SPHINX speech recognition system

  1991cited by this paper
• Acoustical and environmental robustness in automatic speech recognition

  1991cited by this paper
• Hidden Markov Models for Speech Recognition

  1991cited by this paper
• CMU robust vocabulary-independent speech recognition system

  1991cited by this paper
• The Harpy speech understanding system

  1990cited by this paper
• A Tree.Trellis Based Fast Search for Finding the N Best Sentence Hypotheses in Continuous Speech Recognition

  1990cited by this paper
• An overview of the SPHINX speech recognition system

  1990cited by this paper
• Modeling between-word coarticulation in continuous speech recognition

  1989cited by this paper
• Context-dependent modeling for acoustic-phonetic recognition of continuous speech

  1985cited by this paper
• A Maximum Likelihood Approach to Continuous Speech Recognition

  1983cited by this paper
• Language-model/acoustic channel balance mechanism

  1980cited by this paper
• A Theory of Adaptive Pattern Classifiers

  1967cited by this paper
• Error bounds for convolutional codes and an asymptotically optimum decoding algorithm

  1967cited by this paper

• Automatic Speech Recognition for Low-Resourced Middle Eastern Languages

  2025cites this paper
• Voice communication module for automotive instrument panel indicators based on virtual assistant open-source solution - Mycroft AI

  2023cites this paper
• Review on Query-focused Multi-document Summarization (QMDS) with Comparative Analysis

  2023cites this paper
• Multilingual Transfer Learning for Children Automatic Speech Recognition

  2022cites this paper
• A comparative review of dynamic neural networks and hidden Markov model methods for mobile on-device speech recognition

  2017cites this paper
• On the Design of an Automatic Speech Recognition System for Romanian Language

  2016influential citation
• Real Time Speech Based Integrated Development Environment for C Program

  2016cites this paper
• Sparse Non-negative Matrix Language Modeling

  2015cites this paper
• Voice operated intelligent fire extinguishing vehicle

  2015cites this paper
• Reconnaissance des entités nommées dans des documents multimodaux

  2014cites this paper
• SLAM and Localization of People with a Mobile Robot using a RGB-D Sensor

  2014cites this paper
• Developing an M-Learning Pilot for Qur'an and Its Sciences

  2013cites this paper
• Isolated Swahili Words Recognition using Sphinx4

  2013cites this paper
• Intégration de la reconnaissance des entités nommées au processus de reconnaissance de la parole [Integration of named entity recognition to automatic speech recognition]

  2013influential citation
• YAST: A Scalable ASR Toolkit Especially Designed for Under-Resourced Languages

  2012cites this paper
• Methods for pronunciation assessment in computer aided language learning

  2011cites this paper
• Multimodal intent recognition for natural human-robotic interaction

  2011cites this paper
• Video accessibility enhancement for hearing-impaired users

  2011cites this paper
• A Keyword Based Interactive Speech Recognition System for Embedded Applications

  2011cites this paper
• Integrating Interactive Digital Maps into a Digital Library

  2010cites this paper
• Hierarchy-Based Partition Models: Using Classification Hierarchies to Improve the Statistical Estimation of Bigrams

  2010cites this paper
• Efficiency of TR-Classifier versus TFIDF

  2010cites this paper
• Skipping-Based Collaborative Recommendations inspired from Statistical Language Modeling

  2010cites this paper
• The Prosody of Uncertainty for Spoken Dialogue Intelligent Tutoring Systems

  2008cites this paper
• Gesture in automatic discourse processing

  2008cites this paper
• Gestural Cohesion for Topic Segmentation

  2008cites this paper
• Gesture Salience as a Hidden Variable for Coreference Resolution and Keyframe Extraction

  2008cites this paper
• Honours Project Report

  2007cites this paper
• The Performance Appraising of Language Models and the Entropy Estimation of Chinese

  2007cites this paper
• Gesture Features for Coreference Resolution

  2006cites this paper
• A Vectorized Processing Algorithm for Continuous Speech Recognition and Associated FPGA-Based Architecture

  2006cites this paper
• Summarization of Broadcast News Video through Link Analysis of Named Entities

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

  2004cites this paper
• CSE 254 (Spring 2003) "Growing N-gram Trees for Language Modeling"

  2003cites this paper
• TRAINS as an Embodied Natural Language Dialogue System

  2001cites this paper
• Framework for proximal personified interfaces

  2000influential citation
• A A* heuristic search strategy with two-level tree beam search

  1998cites this paper
• Rapid language model development for new task domains

  1998cites this paper
• Error-responsive feedback mechanisms for speech recognizers

  1997cites this paper
• Word-based confidence measures as a guide for stack search in speech recognition

  1997cites this paper
• Word set probability boosting for improved spontaneous dialog recognition

  1997influential citation
• Estimation of language models for new spoken language applications

  1996cites this paper
• A novel word pre-selection method based on phonetic set indexing

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

  1996influential citation
• An Overview of Automatic Speech Recognition

  1996cites this paper
• Word Set Probability Boosting for Improved SpontaneousDialogue Recognition : The AB / TAB

  1996cites this paper
• Large Vocabulary Continuous Speech Recognition:From Laboratory Systems towards Real-World Applications (音声言語によるコミュニケ-ションシステムの実現に向けて(音声認識,合成,対話処理,システム構築の諸問題)論文特集)

  1996cites this paper
• An Overview of Automatic Speech Recognition

  1996cites this paper
• From Sphinx-II to Whisper — Making Speech Recognition Usable

  1996cites this paper
• Deleted interpolation and density sharing for continuous hidden Markov models

  1996cites this paper
• Improved spontaneous dialogue recognition using dialogue and utterance triggers by adaptive probability boosting

  1996cites this paper
• Microsoft Windows highly intelligent speech recognizer: Whisper

  1995cites this paper
• Word Set Probability Boosting for Improved Spontaneous Dialogue Recognition: The AB/TAB Algorithms

  1995cites this paper
• The role of voice input for human-machine communication.

  1995cites this paper
• A Robust Loose Coupling for Speech Recognition and Natural Language Understanding

  1995cites this paper
• Surfing the Web by voice

  1995cites this paper
• Speechacts: A Testbed For Continuous Speech Applications

  1994cites this paper
• Adaptive Statistical Language Modeling; A Maximum Entropy Approach

  1994cites this paper
• Environment normalization for robust speech recognition using direct cepstral comparison

  1994cites this paper
• A Hybrid Approach to Adaptive Statistical Language Modeling

  1994cites this paper
• Recent Improvements in the CMU Spoken Language Understanding System

  1994cites this paper
• Benchmark Tests For The Darpa Spoken Language Program

  1993cites this paper
• Predicting unseen triphones with senones

  1993cites this paper
• Efficient Cepstral Normalization for Robust Speech Recognition

  1993influential citation
• Search Algorithms for Software-Only Real-Time Recognition with Very Large Vocabularies

  1993cites this paper