59 citations found. Retrieving documents...
Young, S., Evermann, G., Hain, T., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., and Woodland, P., The HTK Book (for HTK Version 3.2.1), Cambridge University, Cambridge, UK, 2002.

 Home/Search   Document Not in Database   Summary   Related Articles   Check  

This paper is cited in the following contexts:

First 50 documents  Next 50

The Impact of Spectral and Energy Mismatch on the . . . - de Wet, al. (2003)   (Correct)

....20##CITEEND##02 IEEE. Published in the 2003 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2003) scheduled for April 6 1l 2003 in Hong Kong SAR, China. Personal use of this material is permitted. However, permission to reprint republish this material for advertising or ....

....2002 IEEE. Published in the 2003 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2003) scheduled for April 6 1l 2003 in Hong Kong SAR, China. Personal use of this material is permitted. However, permission to reprint republish this material for advertising or promotional purposes or for creating ....

[Article contains additional citation context not shown here]

S. Young, J. Jansen, J. Odell, D. Ollason, and P.Woodland, TheHTKBook (for HTKVersion 2.1), Cambridge University, Cambridge, UK,1


Speech-Gesture Driven Multimodal Interfaces for.. - Sharma, Yeasin..   (Correct)

....are combined into sentence models by appropriately connecting Hidden Markov Models into larger state transition networks. Using this network representation, speech recognition is performed by determining the most likely state transition sequence through this network given observed speech features [89]. In commercial speech recognition systems, the end user is commonly only confronted with the final most probable utterances, however, systems internally maintain a whole set of possible utterances defined as a confusion network. As the quality of the acquired speech signal deteriorates, obtained ....

S. Young, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book (for HTK Version 2.1): Cambridge University, 1995.


Factor analysed hidden Markov models for speech recognition - Rosti, Gales (2003)   (Correct)

....as with standard HMMs. The likelihood of an observation o t given only the state q t = j can be obtained by marginalising the likelihood in Equation 7 as follows b j (o t ) p(o t t = j) jn b jmn (o t ) 12) Any Viterbi algorithm based decoder such as token passing algorithm [20] can be easily modified to support FAHMMs this way. The modifications to forward backward algorithm are discussed in the training section below. 2.4 Optimising FAHMM Parameters A maximum likelihood (ML) criterion is used to optimise the FAHMM parameters. It is also possible to find ....

....matrix can be shared globally or between classes of states as in semi tied covariance HMMs [4] A global observation noise distribution could represent a stationary noise environment corrupting all the speech data. Implementing an arbitrary tying scheme is closely related to standard HMM systems [20]. The su#cient statistics required for the tied parameter are accumulated over the entire class sharing it before updating. If the mean vectors and the covariance matrices of the state space noise are tied on a di#erent level, all the cross terms between the first order accumulates and the updated ....

[Article contains additional citation context not shown here]

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland. The HTK Book (for HTK Version 3.0). Cambridge University, 2000. 16


Automatic Transcription of Conversational.. - Hain, Woodland.. (2003)   (1 citation)  Self-citation (Evermann Hain Moore Povey Woodland)   (Correct)

No context found.

S.J. Young, G. Evermann, T. Hain, D. Kershaw, G.L. Moore, J.J. Odell, D. Ollason, D. Povey, V. Valtchev, P.C. Woodland (2003). The HTK Book. Cambridge University, http://htk.eng.cam.ac.uk. 22


Automatic Transcription of Conversational.. - Hain, Woodland.. (2003)   (1 citation)  Self-citation (Evermann Hain Moore Povey Woodland)   (Correct)

No context found.

S.J. Young, G. Evermann, T. Hain, D. Kershaw, G.L. Moore, J.J. Odell, D. Ollason, D. Povey, V. Valtchev, P.C. Woodland (2003). The HTK Book. Cambridge University, http://htk.eng.cam.ac.uk. 22


Pronunciation Variant --Based Multi-Path HMMs for Syllables - Annika Hmlinen Louis   (Correct)

No context found.

Young, S., Evermann, G., Hain, T., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., and Woodland, P., The HTK Book (for HTK Version 3.2.1), Cambridge University, Cambridge, UK, 2002.


Syllable-Length Acoustic Units in Large-Vocabulary Continuous - Speech Recognition Annika   (Correct)

No context found.

Young, S., Evermann, G., Hain, T., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., and Woodland, P., The HTK Book (for HTK Version 3.2.1). Cambridge University, Cambridge, UK, 2002.


Chapter 6: Acoustic Backing-off as an - Implementation Of Missing   (Correct)

No context found.

Young, S., Jansen, J., Odell, J., Ollason, D., Woodland, P., 1995. The HTK book (for HTK version 2.0). Cambridge University, UK.


Rule-Based Categorial Analysis of Unprompted Speech - A.. - Beringer   (Correct)

No context found.

S. Young. The HTK Book. Cambridge University, 1995.


Speaker Verification Based on the German VeriDat Database - Ulrich Urk Florian   (Correct)

No context found.

Steve Young et al (1995): The HTK Book. Cambridge University, htk.eng.cam.ac.uk


Recognizing Sloppy Speech - Yu (2004)   (Correct)

No context found.

S. Young, G. Evermann, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland. The HTK Book. Cambridge University, 1995.


Recognizing Sloppy Speech - Hua Yu Cmu-Lti-   (Correct)

No context found.

S. Young, G. Evermann, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland. The HTK Book. Cambridge University, 1995.


Speaker Verification Based on the German VeriDat Database - Ulrich Urk Florian   (Correct)

No context found.

Steve Young et al (1995): The HTK Book. Cambridge University, htk.eng.cam.ac.uk


Rule-Based Categorial Analysis of Unprompted Speech - A.. - Beringer   (Correct)

No context found.

S. Young. The HTK Book. Cambridge University, 1995.


Factor Analysed Hidden Markov Models - Rosti And Gales (2002)   (Correct)

No context found.

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book (for HTK Version 3.0), Cambridge University, 2000.


Factor Analysed Hidden Markov Models - Rosti And Gales (2002)   (Correct)

No context found.

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book (for HTK Version 3.0), Cambridge University, 2000.


Basis Superposition Precision Matrix Modelling For Large.. - Sim And Gales (2004)   (Correct)

No context found.

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book (for HTK version 3.0), Cambridge University, 1997.


A Comparison between Spiking and Differentiable.. - Graves, Beringer.. (2004)   (Correct)

No context found.

S. Young. The HTK Book. Cambridge University, 1995.


Generalised Linear Gaussian Models - Rosti, Gales (2001)   (3 citations)  (Correct)

No context found.

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland. The HTK Book (for HTK Version 3.0). Cambridge University, 2000.


Switching Linear Dynamical Systems For Speech Recognition - Rosti, Gales (2003)   (Correct)

No context found.

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland. The HTK Book (for HTK Version 3.0). Cambridge University, 2000.


Biologically Plausible Speech Recognition with LSTM.. - Graves, Eck, Beringer, .. (2004)   (2 citations)  (Correct)

No context found.

Young, S.: The HTK Book. Cambridge University (1995/1996)


Linear Gaussian Models for Speech Recognition - Rosti (2004)   (Correct)

No context found.

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland. The HTK Book (for HTK Version 3.0). Cambridge University, 2000.


The Czech Speech and Prosody Database Both for ASR and TTS .. - Kolar, Romportl, Psutka (2003)   (Correct)

No context found.

Young, S. et al.: The HTK Book (for HTK Version 3.1). Cambridge University, 2002


Generalised Linear Gaussian Models - Rosti, Gales (2001)   (3 citations)  (Correct)

No context found.

S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland. The HTK Book (for HTK Version 3.0). Cambridge University, 2000.


A Comparison Of Two Strategies For Asr In Additive Noise .. - Data And Spectral   (Correct)

No context found.

Steve Young. The HTK Book. Cambridge University, March 1997.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC