Filters








1,788 Hits in 6.0 sec

Keyword Detection for Spontaneous Speech

Weifeng Li, Aude Billard, Herve Bourlard
2009 2009 2nd International Congress on Image and Signal Processing  
This paper presents a system for keyword detection in spontaneous speech. Keywords are predefined through a set of acoustic examples provided by the users.  ...  Keyword detection proceeds in two steps: keyword searching and verification.  ...  Guillermo Aradilla for the helpful discussions.  ... 
doi:10.1109/cisp.2009.5303824 fatcat:jn6xe7gflrdr5h3wrdsxmujovu

Detailed author index

2009 2009 IEEE Workshop on Automatic Speech Recognition & Understanding  
Robust Vocabulary Independent Keyword Spotting with Graphical Models 376 From Speech to Letters -Using a Novel Neural Network Architecture for Grapheme Based ASR W continues on next page… [Search] A B  ...  Schuller, Björn 349 Robust Vocabulary Independent Keyword Spotting with Graphical Models 376 From Speech to Letters -Using a Novel Neural Network Architecture for Grapheme Based ASR 552 Acoustic  ... 
doi:10.1109/asru.2009.5373491 fatcat:tgoktcyotncatbvo3l3cslfapa

ProfLifeLog: Environmental analysis and keyword recognition for naturalistic daily audio streams

Abhijeet Sangwan, Ali Ziaei, John H. L. Hansen
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
The ProfLifeLog corpus contains speech data in a variety of noise backgrounds which is challenging for keyword recognition.  ...  This study presents keyword recognition evaluation on a new corpus named ProfLifeLog. ProfLifeLog is a collection of data captured on a portable audio recording device called the LENA unit.  ...  In summary, the proposed front-end technique acts as a filter, and retains only relatively clean speech (high SNR) for keyword spotting.  ... 
doi:10.1109/icassp.2012.6289028 dblp:conf/icassp/SangwanZH12 fatcat:zvd6kjrwa5ekvn57hxz3fo2hqu

Utterance verification using prosodic information for Mandarin telephone speech keyword spotting

Yeou-Jiunn Chen, Chung-Hsien Wu, Gwo-Lang Yan
1999 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)  
For keyword recognition, 59 context-independent subsyllables, i.e., 22 m s and 37 FINAL'S in Mandarin speech, and one backgroundkilence model, are used as the basic recognition units.  ...  In this paper, the prosodic information, a very special and important feature in Mandarin speech, is used for Mandarin telephone speech utterance verification.  ...  INTRODUCTION Recently. research into algorithms that are able to spot keywords has been focused on constructing hidden Markov model (HMM) based speaker independent keyword spotting systems using either  ... 
doi:10.1109/icassp.1999.759762 dblp:conf/icassp/ChenWY99 fatcat:zwnnm36it5dfritpavak5qapxu

Fast Keyword Spotting in Telephone Speech

J. Nouza, J. Silovsky
2009 Radioengineering  
In the paper, we present a system designed for detecting keywords in telephone speech. We focus not only on achieving high accuracy but also on very short processing time.  ...  Its performance is evaluated on recordings of Czech spontaneous telephone speech using rather large and complex keyword lists.  ...  Introduction Keyword spotting (KWS) has become an important branch of speech technology.  ... 
doaj:14b2ae1d747f452dbf3a404aa848e053 fatcat:prskw3c5hzam7a24cbnpxynhqi

Integration of phonetic and prosodic information for robust utterance verification

C.-H. Wu, Y.-J. Chen, G.-L. Yan
2000 IEE Proceedings - Vision Image and Signal Processing  
Driven by this propcrty, phonetic and prosodic information are integrated and used for Mandarin telephone speech keyword spotting.  ...  For keyword recognition, 132 subsyllable models, two general acoustic filler models and one background/silence model are separately trained and used as the basic recognition units.  ...  As the technology improves, a user-friendly speech recognition system is equipped with a keyword spotting capability that allows users the flexibility to give a wide range of response and behaviour.  ... 
doi:10.1049/ip-vis:20000099 fatcat:qggelngzjjfvvoh2feai4o6mve

An Application of Recurrent Neural Networks to Discriminative Keyword Spotting [chapter]

Santiago Fernández, Alex Graves, Jürgen Schmidhuber
2007 Lecture Notes in Computer Science  
In a keyword spotting task in a large database of unconstrained speech where an HMM-based speech recogniser achieves a word accuracy of only 65 %, the system achieved a keyword spotting accuracy of 84.5  ...  Keyword spotting is a detection task consisting in discovering the presence of specific spoken words in unconstrained speech.  ...  We have opted to tackle a realistic keyword spotting task in a large database of spontaneous and unconstrained speech where an HMM-based speech recogniser achieves a word accuracy of only 65 %.  ... 
doi:10.1007/978-3-540-74695-9_23 fatcat:dofqjetmorh5blmzrrhpdos6jq

Tandem decoding of children's speech for keyword detection in a child-robot interaction scenario

Martin Wöllmer, Björn Schuller, Anton Batliner, Stefan Steidl, Dino Seppi
2011 ACM Transactions on Speech and Language Processing  
We use the FAU Aibo Emotion Corpus which contains emotionally colored spontaneous children's speech recorded in a child-robot interaction scenario and investigate various recent keyword spotting techniques  ...  In this article, we focus on keyword detection in children's speech as it is needed in voice command systems.  ...  The disadvantage of the method proposed by Fernandez et al. [2007a] is that it is not vocabulary independent, as it has a separate output unit for each keyword.  ... 
doi:10.1145/1998384.1998386 dblp:journals/tslp/WollmerSBSS11 fatcat:vrgrjzvptvdmjm7b7pfuuznrri

Confidence measure improvement using useful predictor features and support vector machines

Yasser Shekofteh, Jahanshah Kabudian, Mohammad Mohsen Goodarzi, Iman Sarraf Rezaei
2012 20th Iranian Conference on Electrical Engineering (ICEE2012)  
In this paper a discriminative and probabilistic computation of CM based upon some useful predictor features and support vector machines (SVM) is presented for Persian conversational telephone speech KWS  ...  In traditional keyword spotting (KWS) systems, confidence measure (CM) of each keyword is computed from normalized acoustic likelihoods.  ...  Speech Recognition Systems A conventional HTK recognizer is used for the implementation of a speaker independent continuous speech recognizer with the following points: -Initial monophone models are first  ... 
doi:10.1109/iraniancee.2012.6292531 fatcat:dfnhd4ltjrd5bh45uknwigxsbu

A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge

Valentin Smirnov, Dmitry Ignatov, Michael Gusev, Mais Farkhadov, Natalia Rumyantseva, Mukhabbat Farkhadova
2016 Journal of Electrical and Computer Engineering  
The paper describes the key concepts of a word spotting system for Russian based on large vocabulary continuous speech recognition.  ...  The system is based on CMU Sphinx open-source speech recognition platform and on the linguistic models and algorithms developed by Speech Drive LLC.  ...  Acknowledgments The authors would like to thank SpRecord LLC authorities for providing real-world telephone-quality data used in training and testing of the keyword spotting system described in this paper  ... 
doi:10.1155/2016/4062786 fatcat:7jhohy6kerbuln7drrwcqfizcq

Intelligent Call Manager Based On The Integration Of Computer Telephony, Internet And Speech Processing

Chung-Hsien Wu, Yeou-Jiunn Chen, Gwo-Lang Yan
1998 International Conference on Consumer Electronics  
The keyword spotting subsystem was evaluated in a test set of 2400 conversational speech utterances from 20 speakers (12 males and 8 females).  ...  As the technology improves, a user friendly speech recognition system is equipped with a keyword spotting capability which allows users the flexibility to give a wide range of response and behavior [1,  ...  Acknowledgment The authors would like to thank the National Science Council, the Republic of China, for financial support of this work under contract No. NSC86-2622-E-006-003.  ... 
doi:10.1109/icce.1998.678264 fatcat:ta5pvcuq4jdgvibqeogw6nhqte

A more efficient and optimal LLR for decoding and verification

Lam Kwok Leung, Pascale Fung
1999 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)  
Since the traditional log likelihood ratio (LLR) is borrowed from speaker verification technique, it may not be apropriate for decoding because we do not have a good modelling and definition of LLR for  ...  We propose a new confidence score for decoding and verification.  ...  INTRODUCTION Nowadays, keyword spotting plays an important role in the speech recognition because it is useful for dealing with spontaneous speech.  ... 
doi:10.1109/icassp.1999.759760 dblp:conf/icassp/LamF99 fatcat:3w2njh5itnagpd4nus54a6xtou

Retrieving spoken documents by combining multiple index sources

G. J. F. Jones, J. T. Foote, K. Spärck Jones, S. J. Young
1996 Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '96  
Both a continuous-speech large vocabulary recognition system, and a phone-lattice word spotter, are used to locate index units within an experimental corpus of voice messages.  ...  Di erent w ays of combining them are investigated, and it is shown that the best of these can increase retrieval average precision for a speakerindependent retrieval system to 85% of that achieved for  ...  for the speaker-dependent monophones used in this work.  ... 
doi:10.1145/243199.243208 dblp:conf/sigir/JonesFJY96 fatcat:wp7tiy52wfbb7agrz7rpcgi43u

Multi-stream LSTM-HMM decoding and histogram equalization for noise robust keyword spotting

Martin Wöllmer, Erik Marchi, Stefano Squartini, Björn Schuller
2011 Cognitive Neurodynamics  
Highly spontaneous, conversational, and potentially emotional and noisy speech is known to be a challenge for today's automatic speech recognition (ASR) systems, which highlights the need for advanced  ...  In this article, we propose to combine histogram equalization and multi-condition training for robust keyword detection in noisy speech.  ...  In this article, we focus on keyword spotting as needed for spontaneous human-machine interaction and investigate the recognition performance when adapting both, features and acoustic models to noisy conditions  ... 
doi:10.1007/s11571-011-9166-9 pmid:22942915 pmcid:PMC3179540 fatcat:lfqo5jvmavgfdasr3my2j4xjvi

A multi-stream ASR framework for BLSTM modeling of conversational speech

Martin Wollmer, Florian Eyben, Bjorn Schuller, Gerhard Rigoll
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme prediction.  ...  In this paper, we extend the principle of joint BLSTM and triphone modeling to a multi-stream system which uses MFCC features and BLSTM predictions as observations originating from two independent data  ...  ] , keyword spotting [12] , and emotion recognition from speech [17] .  ... 
doi:10.1109/icassp.2011.5947444 dblp:conf/icassp/WollmerESR11 fatcat:lk62prmowjfedg6smfqo2osaay
« Previous Showing results 1 — 15 out of 1,788 results