Journal Article10.1109/29.103088
Automatic recognition of keywords in unconstrained speech using hidden Markov models
498
TL;DR: The modifications made to a connected word speech recognition algorithm based on hidden Markov models which allow it to recognize words from a predefined vocabulary list spoken in an unconstrained fashion are described.
read more
Abstract: The modifications made to a connected word speech recognition algorithm based on hidden Markov models (HMMs) which allow it to recognize words from a predefined vocabulary list spoken in an unconstrained fashion are described. The novelty of this approach is that statistical models of both the actual vocabulary word and the extraneous speech and background are created. An HMM-based connected word recognition system is then used to find the best sequence of background, extraneous speech, and vocabulary word models for matching the actual input. Word recognition accuracy of 99.3% on purely isolated speech (i.e., only vocabulary items and background noise were present), and 95.1% when the vocabulary word was embedded in unconstrained extraneous speech, were obtained for the five word vocabulary using the proposed recognition algorithm. >
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Language modeling for spontaneous speech recognition based on disfluency labeling and generation of disfluent text
Koharu Horii,Kengo Ohta,Ryota Nishimura,Atsunori Ogawa,Norihide Kitaoka +4 more
- 31 Oct 2023
TL;DR: This study fine-tuned a pre-trained Bidirectional Encoder Representations from Transformers to predict word boundaries where disfluency symbols should be inserted within a corpus of normal written text and trained an LM to predict disfluencies as pre-defined symbols, and integrated it into an E2E ASR model using Shallow Fusion.
•Dissertation
Source localization on solids for touch interfaces.
XueXin. Yap
- 01 Jan 2011
TL;DR: In this article, the authors proposed a new approach to the development of a touch interface through the use of a surface-mounted sensor which allows one to convert hard surfaces into touch pads.
Patent
System And Method For Adjusting Floor Controls Based On Conversational Characteristics Of Participants
Paul M. Aoki,Margaret H. Szymanski,James D. Thornton,Daniel H. Wilson,Allison Woodruff +4 more
- 27 Feb 2012
TL;DR: In this article, a system and method for automatically adjusting floor control based on conversational characteristics is provided, where audio streams are received, which each originate from an audio source, and a change threshold comprising a minimum number of timeslices for at least one of the current configuration and possible configurations is applied to the analysis.
Patent
Method and system for recognizing speech commands using background and foreground acoustic models
Shuai Yue,Li Lu,Xiang Zhang,Dadong Xie,Haibo Liu,Bo Chen,Jian Liu +6 more
- 13 Dec 2013
TL;DR: In this article, a method of recognizing speech commands includes generating a background acoustic model for a sound using a first sound sample and a foreground acoustic model is generated for the sound using the second sound sample.
pplying hybrid “CD-CNN-HMM” model for keywords spotting in continuous speech
Hinda Dridi,Kais Ouni +1 more
- 01 Oct 2018
TL;DR: This work proposes a systematic approach of keywords spotting in continuous speech using a Context Dependent-Convolutional Neural Network-Hidden Markov Model (CD-CNN-HMM) built with the open source speech recognition toolkit Kaldi and implemented with the software MATLAB.
References
Minimum prediction residual principle applied to speech recognition
TL;DR: A computer system is described in which isolated words, spoken by a designated talker, are recognized through calculation of a minimum prediction residual through optimally registering the reference LPC onto the input autocorrelation coefficients using the dynamic programming algorithm.
1.7K
Continuous speech recognition by statistical methods
Frederick Jelinek
- 01 Apr 1976
TL;DR: Experimental results are presented that indicate the power of the methods and concern modeling of a speaker and of an acoustic processor, extraction of the models' statistical parameters and hypothesis search procedures and likelihood computations of linguistic decoding.
1.1K
Recognition of isolated digits using hidden Markov models with continuous mixture densities
TL;DR: This paper extends previous work on isolated-word recognition based on hidden Markov models by replacing the discrete symbol representation of the speech signal with a continuous Gaussian mixture density, thereby eliminating the inherent quantization error introduced by the discrete representation.
296
A segmental k-means training procedure for connected word recognition
TL;DR: In this paper, a segmental k-means training procedure was used to extract whole-word patterns from naturally spoken word strings, which were then used to create a set of word reference patterns for recognition.
257
Related Papers (5)
Richard Rose,D.B. Paul +1 more
- 03 Apr 1990
Lawrence R. Rabiner,Biing-Hwang Juang +1 more
- 01 Jan 1993
Guoguo Chen,Carolina Parada,Georg Heigold +2 more
- 04 May 2014