Report

HEŘMANSKÝ Hynek, BURGET Lukáš, SCHWARZ Petr, MATĚJKA Pavel, HANNEMANN Mirko, RASTROW Ariya, WHITE Christopher, KHUDANPUR Sanjeev and ČERNOCKÝ Jan. Recovery from Model Inconsistency in Multilingual Speech Recognition. Baltimore: Johns Hopkins University, 2007.
Publication language:english
Original title:Recovery from Model Inconsistency in Multilingual Speech Recognition
Title (cs):Překonání inkonzistence modelů v multilingválním rozpoznávání řeči
Pages:32
Place:Baltimore, US
Year:2007
Publisher:Johns Hopkins University
Keywords
speech recognition
Annotation
The report deals with Recovery from Model Inconsistency in Multilingual Speech Recognition
Abstract
Current ASR has difficulties in handling unexpected words that are typically replaced by acoustically acceptable high prior probability words. Identifying parts of the message where such a replacement could have happened may allow for corrective strategies.

We aim to develop data-guided techniques that would yield unconstrained estimates of posterior probabilities of sub-word classes employed in the stochastic model solely from the acoustic evidence, i.e. without use of higher level language constraints.

These posterior probabilities then could be compared with the constrained estimates of posterior probabilities derived with the constraints implied by the underlying stochastic model. Parts of the message where any significant mismatch between these two probability distributions is found should be re-examined and corrective strategies applied.

This may allow for development of systems that are able to indicate when they "do not know" and eventually may be able to "learn-as-you-go" in applications encountering new situations and new languages.

During the 2007 Summer Workshop we intend to focus on detection and description of out-of-vocabulary and mispronounced words in the 6 language Call-home database. Additionally, in order to describe the suspect parts of the message, we will work on language-independent recognizer of speech sounds that could be applied for phonetic transcription of identified suspect parts of the recognized message.

BibTeX:
@TECHREPORT{
   author = {Hynek He{\v{r}}mansk{\'{y}} and Luk{\'{a}}{\v{s}} Burget and
	Petr Schwarz and Pavel Mat{\v{e}}jka and Mirko Hannemann and
	Ariya Rastrow and Christopher White and Sanjeev Khudanpur
	and Jan {\v{C}}ernock{\'{y}}},
   title = {Recovery from Model Inconsistency in Multilingual Speech
	Recognition},
   pages = {32},
   year = {2007},
   location = {Baltimore, US},
   publisher = {Johns Hopkins University},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=8895}
}

Your IPv4 address: 54.158.55.5
Switch to IPv6 connection

DNSSEC [dnssec]