Personalizing universal recurrent neural network language model with user characteristic features by social network crowdsourcing
Authors:
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 84-91
Abstract
With the popularity of mobile devices, personalized speech recognizer becomes more realizable today and highly attractive. Each mobile device is primarily used by a single user, so it's possible to have a personalized recognizer well matching to the characteristics of individual user. Although acoustic model personalization has been investigated for decades, much less work have been reported on personalizing language model, probably because of the difficulties in collecting enough personalized corpora. Previous work used the corpora collected from social networks to solve the problem, but constructing a personalized model for each user is troublesome. In this paper, we propose a universal recurrent neural network language model with user characteristic features, so all users share the same model, except each with different user characteristic features. These user characteristic features can be obtained by crowdsouring over social networks, which include huge quantity of texts posted by users with known friend relationships, who may share some subject topics and wording patterns. The preliminary experiments on Facebook corpus showed that this proposed approach not only drastically reduced the model perplexity, but offered very good improvement in recognition accuracy in n-best rescoring tests. This approach also mitigated the data sparseness problem for personalized language models.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Crowdsourcing systems on the World-Wide WebCommunications of the ACM, 2011
- User language model for collaborative personalized searchACM Transactions on Information Systems, 2009
- A model of a trust-based recommendation system on a social networkAutonomous Agents and Multi-Agent Systems, 2007
- Statistical language model adaptation: review and perspectivesSpeech Communication, 2004
- A personalized recommender system based on web usage mining and decision tree inductionExpert Systems with Applications, 2002
- Modeling long distance dependence in language: topic mixtures versus dynamic cache modelsIEEE Transactions on Speech and Audio Processing, 1999
- A maximum entropy approach to adaptive statistical language modellingComputer Speech & Language, 1996
- Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov modelsComputer Speech & Language, 1995
- Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chainsIEEE Transactions on Speech and Audio Processing, 1994
- A cache-based natural language model for speech recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990