Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"speech": models, code, and papers

POSHAN: Cardinal POS Pattern Guided Attention for News Headline Incongruence

Nov 05, 2021
Rahul Mishra, Shuo Zhang

Automatic detection of click-bait and incongruent news headlines is crucial to maintaining the reliability of the Web and has raised much research attention. However, most existing methods perform poorly when news headlines contain contextually important cardinal values, such as a quantity or an amount. In this work, we focus on this particular case and propose a neural attention based solution, which uses a novel cardinal Part of Speech (POS) tag pattern based hierarchical attention network, namely POSHAN, to learn effective representations of sentences in a news article. In addition, we investigate a novel cardinal phrase guided attention, which uses word embeddings of the contextually-important cardinal value and neighbouring words. In the experiments conducted on two publicly available datasets, we observe that the proposed methodgives appropriate significance to cardinal values and outperforms all the baselines. An ablation study of POSHAN shows that the cardinal POS-tag pattern-based hierarchical attention is very effective for the cases in which headlines contain cardinal values.

* Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM '21), November 1--5, 2021, Virtual Event, QLD, Australia 

  Access Paper or Ask Questions

Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data

Oct 27, 2021
Pablo Gimeno, Victoria Mingote, Alfonso Ortega, Antonio Miguel, Eduardo Lleida

Area under the ROC curve (AUC) optimisation techniques developed for neural networks have recently demonstrated their capabilities in different audio and speech related tasks. However, due to its intrinsic nature, AUC optimisation has focused only on binary tasks so far. In this paper, we introduce an extension to the AUC optimisation framework so that it can be easily applied to an arbitrary number of classes, aiming to overcome the issues derived from training data limitations in deep learning solutions. Building upon the multiclass definitions of the AUC metric found in the literature, we define two new training objectives using a one-versus-one and a one-versus-rest approach. In order to demonstrate its potential, we apply them in an audio segmentation task with limited training data that aims to differentiate 3 classes: foreground music, background music and no music. Experimental results show that our proposal can improve the performance of audio segmentation systems significantly compared to traditional training criteria such as cross entropy.

* IEEE Signal Processing Letters, vol. 28, pp. 1135-1139, 2021 

  Access Paper or Ask Questions

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Oct 19, 2021
Mutian He, Jingzhou Yang, Lei He, Frank K. Soong

End-to-end TTS suffers from high data requirements as it is difficult for both costly speech corpora to cover all necessary knowledge and neural models to learn the knowledge, hence additional knowledge needs to be injected manually. For example, to capture pronunciation knowledge on languages without regular orthography, a complicated grapheme-to-phoneme pipeline needs to be built based on a structured, large pronunciation lexicon, leading to extra, sometimes high, costs to extend neural TTS to such languages. In this paper, we propose a framework to learn to extract knowledge from unstructured external resources using Token2Knowledge attention modules. The framework is applied to build a novel end-to-end TTS model named Neural Lexicon Reader that extracts pronunciations from raw lexicon texts. Experiments support the potential of our framework that the model significantly reduces pronunciation errors in low-resource, end-to-end Chinese TTS, and the lexicon-reading capability can be transferred to other languages with a smaller amount of data.

* 5 pages, 3 figures 

  Access Paper or Ask Questions

An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction

Sep 02, 2021
Samuel Mensah, Kai Sun, Nikolaos Aletras

Target-oriented opinion words extraction (TOWE) (Fan et al., 2019b) is a new subtask of target-oriented sentiment analysis that aims to extract opinion words for a given aspect in text. Current state-of-the-art methods leverage position embeddings to capture the relative position of a word to the target. However, the performance of these methods depends on the ability to incorporate this information into word representations. In this paper, we explore a variety of text encoders based on pretrained word embeddings or language models that leverage part-of-speech and position embeddings, aiming to examine the actual contribution of each component in TOWE. We also adapt a graph convolutional network (GCN) to enhance word representations by incorporating syntactic information. Our experimental results demonstrate that BiLSTM-based models can effectively encode position information into word representations while using a GCN only achieves marginal gains. Interestingly, our simple methods outperform several state-of-the-art complex neural structures.

* Accepted at EMNLP 2021 

  Access Paper or Ask Questions

Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning

Jul 25, 2021
Xubo Liu, Turab Iqbal, Jinzheng Zhao, Qiushi Huang, Mark D. Plumbley, Wenwu Wang

Deep generative models have recently achieved impressive performance in speech and music synthesis. However, compared to the generation of those domain-specific sounds, generating general sounds (such as siren, gunshots) has received less attention, despite their wide applications. In previous work, the SampleRNN method was considered for sound generation in the time domain. However, SampleRNN is potentially limited in capturing long-range dependencies within sounds as it only back-propagates through a limited number of samples. In this work, we propose a method for generating sounds via neural discrete time-frequency representation learning, conditioned on sound classes. This offers an advantage in efficiently modelling long-range dependencies and retaining local fine-grained structures within sound clips. We evaluate our approach on the UrbanSound8K dataset, compared to SampleRNN, with the performance metrics measuring the quality and diversity of generated sounds. Experimental results show that our method offers comparable performance in quality and significantly better performance in diversity.

* Submitted to MLSP 2021, 6 pages, 1 figure 

  Access Paper or Ask Questions

How to Adapt Your Pretrained Multilingual Model to 1600 Languages

Jun 03, 2021
Abteen Ebrahimi, Katharina Kann

Pretrained multilingual models (PMMs) enable zero-shot learning via cross-lingual transfer, performing best for languages seen during pretraining. While methods exist to improve performance for unseen languages, they have almost exclusively been evaluated using amounts of raw text only available for a small fraction of the world's languages. In this paper, we evaluate the performance of existing methods to adapt PMMs to new languages using a resource available for over 1600 languages: the New Testament. This is challenging for two reasons: (1) the small corpus size, and (2) the narrow domain. While performance drops for all approaches, we surprisingly still see gains of up to $17.69\%$ accuracy for part-of-speech tagging and $6.29$ F1 for NER on average over all languages as compared to XLM-R. Another unexpected finding is that continued pretraining, the simplest approach, performs best. Finally, we perform a case study to disentangle the effects of domain and size and to shed light on the influence of the finetuning source language.

* Accepted to ACL 2021 

  Access Paper or Ask Questions

Policy Supervectors: General Characterization of Agents by their Behaviour

Dec 02, 2020
Anssi Kanervisto, Tomi Kinnunen, Ville Hautamäki

By studying the underlying policies of decision-making agents, we can learn about their shortcomings and potentially improve them. Traditionally, this has been done either by examining the agent's implementation, its behaviour while it is being executed, its performance with a reward/fitness function or by visualizing the density of states the agent visits. However, these methods fail to describe the policy's behaviour in complex, high-dimensional environments or do not scale to thousands of policies, which is required when studying training algorithms. We propose policy supervectors for characterizing agents by the distribution of states they visit, adopting successful techniques from the area of speech technology. Policy supervectors can characterize policies regardless of their design philosophy (e.g. rule-based vs. neural networks) and scale to thousands of policies on a single workstation machine. We demonstrate method's applicability by studying the evolution of policies during reinforcement learning, evolutionary training and imitation learning, providing insight on e.g. how the search space of evolutionary algorithms is also reflected in agent's behaviour, not just in the parameters.

* Code available at 

  Access Paper or Ask Questions

Representation Learning for Sequence Data with Deep Autoencoding Predictive Components

Oct 07, 2020
Junwen Bai, Weiran Wang, Yingbo Zhou, Caiming Xiong

We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations of sequence data should exhibit a simple structure in the latent space. We encourage this latent structure by maximizing an estimate of predictive information of latent feature sequences, which is the mutual information between past and future windows at each time step. In contrast to the mutual information lower bound commonly used by contrastive learning, the estimate of predictive information we adopt is exact under a Gaussian assumption. Additionally, it can be computed without negative sampling. To reduce the degeneracy of the latent space extracted by powerful encoders and keep useful information from the inputs, we regularize predictive information learning with a challenging masked reconstruction loss. We demonstrate that our method recovers the latent space of noisy dynamical systems, extracts predictive features for forecasting tasks, and improves automatic speech recognition when used to pretrain the encoder on large amounts of unlabeled data.

  Access Paper or Ask Questions

Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory

Jun 29, 2020
Antonio Carta, Alessandro Sperduti, Davide Bacciu

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be introduced into a neural architecture by an appropriate modularization of the dynamic memory. In this paper we propose a novel incrementally trained recurrent architecture targeting explicitly multi-scale learning. First, we show how to extend the architecture of a simple RNN by separating its hidden state into different modules, each subsampling the network hidden activations at different frequencies. Then, we discuss a training algorithm where new modules are iteratively added to the model to learn progressively longer dependencies. Each new module works at a slower frequency than the previous ones and it is initialized to encode the subsampled sequence of hidden activations. Experimental results on synthetic and real-world datasets on speech recognition and handwritten characters show that the modular architecture and the incremental training algorithm improve the ability of recurrent neural networks to capture long-term dependencies.

* accepted @ ECML 2020. arXiv admin note: substantial text overlap with arXiv:2001.11771 

  Access Paper or Ask Questions

Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR

Feb 14, 2020
Leda Sarı, Niko Moritz, Takaaki Hori, Jonathan Le Roux

We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR). The proposed model contains a memory block that holds speaker i-vectors extracted from the training data and reads relevant i-vectors from the memory through an attention mechanism. The resulting memory vector (M-vector) is concatenated to the acoustic features or to the hidden layer activations of an E2E neural network model. The E2E ASR system is based on the joint connectionist temporal classification and attention-based encoder-decoder architecture. M-vector and i-vector results are compared for inserting them at different layers of the encoder neural network using the WSJ and TED-LIUM2 ASR benchmarks. We show that M-vectors, which do not require an auxiliary speaker embedding extraction system at test time, achieve similar word error rates (WERs) compared to i-vectors for single speaker utterances and significantly lower WERs for utterances in which there are speaker changes.

* To appear in Proc. ICASSP 2020 

  Access Paper or Ask Questions