How to Do Things With Words

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

A grammar of spoken Chinese = 中國話的文法

This paper describes the fifth year of the Sentiment Analysis in Twitter task. SemEval-2017 Task 4 continues with a rerun of the subtasks of SemEval-2016 Task 4, which include identifying the overall sentiment of the tweet, sentiment towards a topic with classification on a two-point and on a five-point ordinal scale, and quantification of the distribution of sentiment towards a topic across a number of tweets: again on a two-point and on a five-point ordinal scale. Compared to 2016, we made two changes: (i) we introduced a new language, Arabic, for all subtasks, and (ii) we made available information from the profiles of the Twitter users who posted the target tweets. The task continues to be very popular, with a total of 48 teams participating this year.

/pdf/semeval-2017-task-4-sentiment-analysis-in-twitter-5294l6x1f7.pdf

SemEval-2017 Task 4: Sentiment Analysis in Twitter

Formulation of speech separation as a supervised learning problem has shown considerable promise. In its simplest form, a supervised learning algorithm, typically a deep neural network, is trained to learn a mapping from noisy features to a time-frequency representation of the target of interest. Traditionally, the ideal binary mask (IBM) is used as the target because of its simplicity and large speech intelligibility gains. The supervised learning framework, however, is not restricted to the use of binary targets. In this study, we evaluate and compare separation results by using different training targets, including the IBM, the target binary mask, the ideal ratio mask (IRM), the short-time Fourier transform spectral magnitude and its corresponding mask (FFT-MASK), and the Gammatone frequency power spectrum. Our results in various test conditions reveal that the two ratio mask targets, the IRM and the FFT-MASK, outperform the other targets in terms of objective intelligibility and quality metrics. In addition, we find that masking based targets, in general, are significantly better than spectral envelope based targets. We also present comparisons with recent methods in non-negative matrix factorization and speech enhancement, which show clear performance advantages of supervised speech separation.

/pdf/on-training-targets-for-supervised-speech-separation-1vd9kby2kl.pdf

On training targets for supervised speech separation

In this paper, we investigate a technique consisting of mean subtraction, variance normalization and time sequence filtering. Unlike other techniques, it applies auto-regression moving-average (ARMA) filtering directly in the cepstral domain. We call this technique mean subtraction, variance normalization, and ARMA filtering (MVA) post-processing, and speech features with MVA post-processing are called MVA features. Overall, compared to raw features without post-processing, MVA features achieve an error rate reduction of 45% on matched tasks and 65% on mismatched tasks on the Aurora 2.0 noisy speech database, and an average 57% error reduction on the Aurora 3.0 database. These improvements are comparable to the results of much more complicated techniques even though MVA is relatively simple and requires practically no additional computational cost. In this paper, in addition to describing MVA processing, we also present a novel analysis of the distortion of mel-frequency cepstral coefficients and the log energy in the presence of different types of noise. The effectiveness of MVA is extensively investigated with respect to several variations: the configurations used to extract and the type of raw features, the domains where MVA is applied, the filters that are used, the ARMA filter orders, and the causality of the normalization process. Specifically, it is argued and demonstrated that MVA works better when applied to the zeroth-order cepstral coefficient than to log energy, that MVA works better in the cepstral domain, that an ARMA filter is better than either a designed finite impulse response filter or a data-driven filter, and that a five-tap ARMA filter is sufficient to achieve good performance in a variety of settings. We also investigate and evaluate a multi-domain MVA generalization

MVA Processing of Speech Features

We present a highly effective and extremely simple noiserobust front end based on novel post-processing of standard MFC C features. It performs remarkably well on the Aurora 2.0 noisydigits database without requiring any increase in model complexity. Compared to the Aurora 2.0 baseline system, our technique improves the average word error rate by 45% in the multicondition training case, (matched training/testing conditions) and 60% in the clean training case (mismatched training/testing conditions) — this is an improvement that rivals some of the best known results on this database. Our method, moreover, improves the performances in all cases, regardless of clean or noisy speech, matched or mis-matched environments. Our technique is entirely general because it makes no assumptions about the existence, type, or level of noise in the speech signal. Moreover, its simplicity means that it should be easy to integrate with other techniques in order to yield further improvements.

Low-resource noise-robust feature post-processing on Aurora 2.0.

Frontend post-processing and backend model enhancement on the Aurora 2.0/3.0 databases.

We propose to integrate the attention mechanism into deep recurrent neural network models for speech emotion recognition. This is based on the intuition that it is beneficial to emphasize the expressive part of the speech signal for emotion recognition. By introducing attention mechanism, we make the system learn how to focus on the more robust or informative segments in the input signal. The proposed recognition model is evaluated on the FAU-Aibo tasks as defined in Interspeech 2009 Emotion Challenge. Our baseline deep recurrent neural network model achieves 37.0% unweighted averaged (UA) recall rate, which is on par with the official HMM baseline system for dynamic modeling framework. The proposed integration of attention mechanism on top of the baseline deep RNN model achieves 46.3% UA recall rate. As far as we know, this is the best UA recall rate ever achieved on FAU-Aibo tasks within the dynamic modeling framework.

Effective Attention Mechanism in Dynamic Models for Speech Emotion Recognition

We evaluate smoothing within the context of the MVA (mean subtraction, variance normalization, and ARMA filtering) post-processing scheme for noise-robust automatic speech recognition. MVA has shown great success in the past on the Aurora 2.0 and 3.0 corpora, even though it is computationally inexpensive. MVA is applied to many acoustic feature extraction methods, and is evaluated using Aurora 2.0. We evaluate MVA post-processing on MFCCs, LPCs, PLPs, RASTA, Tandem, modulation-filtered spectrogram, and modulation cross-correlogram features. We conclude that, while effectiveness does depend on the extraction method, the majority of features benefit significantly from MVA, and the smoothing ARMA filter is an important component. It appears that the effectiveness of normalization and smoothing depends on the domain in which it is applied, being most fruitfully applied just before being scored by a probabilistic model. Moreover, since it is both effective and simple, our ARMA filter should be considered a candidate method in most noise-robust speech recognition tasks.

/pdf/speech-feature-smoothing-for-robust-asr-2grj6rmewe.pdf

Chia-Ping Chen

Papers

MVA Processing of Speech Features

Low-resource noise-robust feature post-processing on Aurora 2.0.

Frontend post-processing and backend model enhancement on the Aurora 2.0/3.0 databases.

Effective Attention Mechanism in Dynamic Models for Speech Emotion Recognition

Speech feature smoothing for robust ASR