Sorry, you need to enable JavaScript to visit this website.

The subjectivity and variability exist in the human emotion perception differs from person to person. In this work, we propose a framework that models the majority of emotion annotation integrated with modeling of subjectivity in improving emotion categorization performances. Our method achieves a promising accuracy of 61.48% on a four-class emotion recognition task. To the best of our knowledge, while there are many works in studying annotator subjectivity, this is one of the first works that have explicitly modeled jointly the consensus with individuality in emotion perception to demonstrate its improvement in classifying emotion in a benchmark corpus.

In our immediate future work, we will evaluate the proposed framework on other public large-scaled emotional database with multiple annotators, e.g., NNIME, to further justify its robustness. We also plan to extend our framework to includ other behavior attributes, e.g., lexical content and body movements. Furthermore, the subjective nature of emotion perception has been shown to be related to the rater personality, a joint modeling of rater’s characteristics with his/her subjectivity in emotion perception may lead to further advancement in robust emotion recognition.


Recurrent neural network language models (RNNLMs) have shown superior performance across a range of speech recognition tasks. At the heart of all RNNLMs, the activation functions play a vital role to control the information flows and tracking longer history contexts that are useful for predicting the following words. Long short-term memory (LSTM) units are well known for such ability and thus widely used in current RNNLMs. However, the deterministic parameter estimates in LSTM RNNLMs are prone to over-fitting and poor generalization when given limited training data.


In this paper we describe an extension of the Kaldi software toolkit to support neural-based language modeling, intended for use in automatic speech recognition (ASR) and related tasks. We combine the use of subword features (letter ngrams) and one-hot encoding of frequent words so that the models can handle large vocabularies containing infrequent words. We propose a new objective function that allows for training of unnormalized probabilities. An importance sampling based method is supported to speed up training when the vocabulary is large.


In this paper, we present a pruning technique for maximum en- tropy (MaxEnt) language models. It is based on computing the exact entropy loss when removing each feature from the model, and it ex- plicitly supports backoff features by replacing each removed feature with its backoff. The algorithm computes the loss on the training data, so it is not restricted to models with n-gram like features, al- lowing models with any feature, including long range skips, triggers, and contextual features such as device location.


We propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without considering dialog interactions. We design recurrent neural network (RNN) based contextual language models that specially track the interactions between speakers in a dialog. Experiment results on Switchboard Dialog Act Corpus show that the proposed model outperforms conventional single turn based RNN language model by 3.3% on perplexity.


Recurrent neural network (RNN) based character-level language models (CLMs) are extremely useful for modeling out-of-vocabulary words by nature. However, their performance is generally much worse than the word-level language models (WLMs), since CLMs need to consider longer history of tokens to properly predict the next one. We address this problem by proposing hierarchical RNN architectures, which consist of multiple modules with different timescales.


In automatic speech recognition (ASR), error correction after the initial search stage is a commonly used technique to improve performance. Whilst completely automatic error correction, such as full second pass rescoring using complex language models, is widely used, directed error correction, where the error locations are manually given, is of great interest in many scenarios. Previous works on directed error correction usually uses the error location information to change search space with original ASR models.


Spoken keyword search in low-resource condition suffers from out-of-vocabulary (OOV) problem and insufficient text data for language model (LM) training. Web-crawled text data is used to expand vocabulary and to augment language model. However, the mismatching between web text and the target speech data brings difficulties to effective utilization. New words from web data need an evaluation to exclude noisy words or introduce proper probabilities. In this paper, several criteria to rank new words from web data are investigated and are used as features


A simple but powerful language model called fixed-size
ordinally-forgetting encoding (FOFE) based feedforward neural
network language models (FNN-LMs) has been proposed recently.
Experimental results have shown that FOFE based FNNLMs
can outperform not only the standard FNN-LMs but also
the popular recurrent neural network language models (RNNLMs).
In this paper, we extend FOFE based FNN-LMs from
several aspects. Firstly, we have proposed a new method to
further improve the performance of FOFE based FNN-LMs by