Publication

MAP Combination of Multi-Stream HMM or HMM/ANN Experts

Hervé Bourlard
2001
Reports

Abstract

Automatic speech recognition (ASR) performance falls dramatically with the level of mismatch between training and test data. The human ability to recognise speech when a large proportion of frequencies are dominated by noise has inspired the "missing data" and "multi-band" approaches to noise robust ASR. "Missing data" ASR identifies low SNR spectral data in each data frame and then ignores it. Multi-band ASR trains a separate model for each position of missing data, estimates a reliability weight for each model, then combines model outputs in a weighted sum. A problem with both approaches is that local data reliability estimation is inherently inaccurate and also assumes that all of the training data was clean. In this article we present a model in which adaptive multi-band expert weighting is incorporated naturally into the maximum a posteriori (MAP) decoding process.

Official source

https://infoscience.epfl.ch/entities/publication/749e1292-da5b-4d2e-8a6c-94096a79784e

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Hervé Bourlard
2001
Reports

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/749e1292-da5b-4d2e-8a6c-94096a79784e

About this result

Related concepts (32)

Missing data

In statistics, missing data, or missing values, occur when no data value is stored for the variable in an observation. Missing data are a common occurrence and can have a significant effect on the conclusions that can be drawn from the data. Missing data can occur because of nonresponse: no information is provided for one or more items or for a whole unit ("subject"). Some items are more likely to generate a nonresponse than others: for example items about private subjects such as income.

Training, validation, and test data sets

In machine learning, a common task is the study and construction of algorithms that can learn from and make predictions on data. Such algorithms function by making data-driven predictions or decisions, through building a mathematical model from input data. These input data used to build the model are usually divided into multiple data sets. In particular, three data sets are commonly used in different stages of the creation of the model: training, validation, and test sets.

Human variability

Human variability, or human variation, is the range of possible values for any characteristic, physical or mental, of human beings. Frequently debated areas of variability include cognitive ability, personality, physical appearance (body shape, skin color, etc.) and immunology. Variability is partly heritable and partly acquired (nature vs. nurture debate). As the human species exhibits sexual dimorphism, many traits show significant variation not just between populations but also between the sexes.

Related publications (16)

MAP Combination of Multi-Stream HMM or HMM/ANN Experts

Chat with Graph Search

Robust, Generalizable, and Reproducible Computational Imaging: A Lensless Perspective

Privacy-preserving and Personalized Federated Machine Learning for Medical Data

COMPARISON OF SUBWORD SEGMENTATION METHODS FOR OPEN-VOCABULARYEND-TO-END SPEECH RECOGNITION