Maximum a posteriori adaptation for large scale HMM recognizers

Zavaliagkos, G.; Schwartz, Richard; McDonough, John

doi:10.1109/icassp.1996.543223

Cited by 29 publications

(20 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A popular technique is to estimate a linear transformation of the model parameters using a maximum likelihood (ML) criterion (Leggetter and Woodland, 1995). A maximum a posteriori (MAP) objective function may also be used Zavaliagkos et al, 1996).…”

Section: Adaptationmentioning

confidence: 99%

Automatic speech recognition and speech variability: A review

BenZeghiba

Mori

Deroo

et al. 2007

Speech Communication

428

207

View full text Add to dashboard Cite

Major progress is being recorded regularly on both the technology and exploitation of automatic speech recognition (ASR) and spoken language systems. However, there are still technological barriers to flexible solutions and user satisfaction under some circumstances. This is related to several factors, such as the sensitivity to the environment (background noise), or the weak representation of grammatical and semantic knowledge.Current research is also emphasizing deficiencies in dealing with variation naturally present in speech. For instance, the lack of robustness to foreign accents precludes the use by specific populations. Also, some applications, like directory assistance, particularly stress the core recognition technology due to the very high active vocabulary (application perplexity). There are actually many factors affecting the speech realization: regional, sociolinguistic, or related to the environment or the speaker herself. These create a wide range of variations that may not be modeled correctly (speaker, gender, speaking rate, vocal effort, regional accent, speaking style, non-stationarity, etc.), especially when resources for system training are scarce. This paper outlines current advances related to these topics.

show abstract

Section: Adaptationmentioning

confidence: 99%

Automatic speech recognition and speech variability: A review

BenZeghiba

Mori

Deroo

et al. 2007

Speech Communication

428

207

View full text Add to dashboard Cite

show abstract

“…EMAP (Extended MAP) [46], [84] uses the joint probability of more than one model parameter as the prior probability for MAP estimation. In speech recognition, the joint probability of each pair of mean vectors of mixture components is estimated from many speakers' utterances [102]. A method of selecting pairs for adaptation was also proposed [76].…”

Section: Predictive Adaptation Emapmentioning

confidence: 99%

Acoustic Model Adaptation for Speech Recognition

Sairyo

2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYStatistical speech recognition using continuous-density hidden Markov models (CDHMMs) has yielded many practical applications. However, in general, mismatches between the training data and input data significantly degrade recognition accuracy. Various acoustic model adaptation techniques using a few input utterances have been employed to overcome this problem. In this article, we survey these adaptation techniques, including maximum a posteriori (MAP) estimation, maximum likelihood linear regression (MLLR), and eigenvoice. We also present a schematic view called the adaptation pyramid to illustrate how these methods relate to each other. key words: speech recognition, acoustic model adaptation, hidden Markov models

show abstract

“…Since data is costly for a fully trained acoustic model for a specific accent, we have used a small amount of transcribed Korean children's speech (17 hours) to adapt acoustic models that were originally trained on the Wall Street Journal corpus using standard adaptation techniques, both of maximum likelihood linear regression (MLLR) [19] and maximum a posteriori (MAP) adaptation [20]. The occurrence of pronunciation variants was detected with a speech recognizer in forced-alignment using a lexicon expanded according to all the possible substitutions between confusable phonemes.…”

Section: Automatic Speech Recognitionmentioning

confidence: 99%

Foreign Language Tutoring in Oral Conversations Using Spoken Dialog Systems

Lee

Noh

Lee

et al. 2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYAlthough there have been enormous investments into English education all around the world, not many differences have been made to change the English instruction style. Considering the shortcomings for the current teaching-learning methodology, we have been investigating advanced computer-assisted language learning (CALL) systems. This paper aims at summarizing a set of POSTECH approaches including theories, technologies, systems, and field studies and providing relevant pointers. On top of the state-of-the-art technologies of spoken dialog system, a variety of adaptations have been applied to overcome some problems caused by numerous errors and variations naturally produced by non-native speakers. Furthermore, a number of methods have been developed for generating educational feedback that help learners develop to be proficient. Integrating these efforts resulted in intelligent educational robots -Mero and Engkey -and virtual 3D language learning games, Pomy. To verify the effects of our approaches on students' communicative abilities, we have conducted a field study at an elementary school in Korea. The results showed that our CALL approaches can be enjoyable and fruitful activities for students. Although the results of this study bring us a step closer to understanding computer-based education, more studies are needed to consolidate the findings. key words: intelligent computer-assisted language learning, robot-assisted language learning, language learning game, grammatical error detection, corrective feedback

show abstract

Maximum a posteriori adaptation for large scale HMM recognizers

Cited by 29 publications

References 4 publications

Automatic speech recognition and speech variability: A review

Automatic speech recognition and speech variability: A review

Acoustic Model Adaptation for Speech Recognition

Foreign Language Tutoring in Oral Conversations Using Spoken Dialog Systems

Contact Info

Product

Resources

About