Method of speaker adaptation for a hidden markov model based...

Details Method of speaker adaptation for a hidden markov model based... Method of speaker adaptation for a hidden markov model based...

2005-09-22

2011-10-18

Armstrong, Angela A (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S256500

Reexamination Certificate

active

08041567

ABSTRACT:
Commercially available voice recognition systems are generally speaker-dependent, with the voice recognition system first being trained to the voice of the speaker before it can be used. A disadvantage with this method is that modified reference data has to be buffered and permanently saved in several steps when the speaker adaptation algorithm is executed, and thus requires a lot of memory space. This primarily negatively affects applications on devices with restricted processor power and limited memory space, such as mobile radio terminals for example. A method of speaker adaptation for a Hidden Markov Model based voice recognition system may address these issues. In the method, the memory space requirement and thus also the processor power required can be considerably reduced. This is achieved by using modified reference data in a speaker adaptation algorithm to adapt a new speaker to a reference speaker. The modified reference data is processed in compressed form.

REFERENCES:
patent: 6711543 (2004-03-01), Cameron
patent: 6751590 (2004-06-01), Chaudhari et al.
patent: 2004/0230424 (2004-11-01), Gunawardana
patent: 42 22 916 (1993-06-01), None
Bub et al, “In-service adaptation of multilingual hidden-markov-models”, in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, (Munich), pp. 1451-1454, 1997.
Satoshi Takahashi et al., “ Four-Level Tied-Structure for Efficient Representation of Acoustic Modeling” pp. 520-523, Acoustics, Speech and Signal Processing , Conference on Detroit, IEEE, 1995.
M.J.F. Gales “Maximum Likelihood Linear Transformations for HMM-Based Speech Recognition” Techn. Rep. CUEDFINFENG/TR291/ Cambridge University 1997.
U. Bub et al. “In Service Adaptation of Multilingual Hidden-Markov-Models”, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP) vol. 2, pp. 1451-1454, 1997 Munich.
Astov “Memory Space Reduction for Hidden Markov Models in Low-Resource Speech Recognition Systems,” Proc. Int. Conf. on Spoken Language Processing (CSLP), pp. 1585-1588, 2002.
“Huffman Coding” Wikipedia.org, Jun. 17, 2009; pp. 1-8.
“Adaptive Huffman Coding” Wikipedia.org, Jun. 17, 2009; pp. 1-3.

Affiliated with

Also associated with

Rating

Method of speaker adaptation for a hidden markov model based... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method of speaker adaptation for a hidden markov model based..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of speaker adaptation for a hidden markov model based... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4261063