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

Rotational Unit of Memory

Oct 26, 2017
Rumen Dangovski, Li Jing, Marin Soljacic

The concepts of unitary evolution matrices and associative memory have boosted the field of Recurrent Neural Networks (RNN) to state-of-the-art performance in a variety of sequential tasks. However, RNN still have a limited capacity to manipulate long-term memory. To bypass this weakness the most successful applications of RNN use external techniques such as attention mechanisms. In this paper we propose a novel RNN model that unifies the state-of-the-art approaches: Rotational Unit of Memory (RUM). The core of RUM is its rotational operation, which is, naturally, a unitary matrix, providing architectures with the power to learn long-term dependencies by overcoming the vanishing and exploding gradients problem. Moreover, the rotational unit also serves as associative memory. We evaluate our model on synthetic memorization, question answering and language modeling tasks. RUM learns the Copying Memory task completely and improves the state-of-the-art result in the Recall task. RUM's performance in the bAbI Question Answering task is comparable to that of models with attention mechanism. We also improve the state-of-the-art result to 1.189 bits-per-character (BPC) loss in the Character Level Penn Treebank (PTB) task, which is to signify the applications of RUM to real-world sequential data. The universality of our construction, at the core of RNN, establishes RUM as a promising approach to language modeling, speech recognition and machine translation.

  Access Paper or Ask Questions

Towards the effectiveness of Deep Convolutional Neural Network based Fast Random Forest Classifier

Sep 28, 2016
Mrutyunjaya Panda

Deep Learning is considered to be a quite young in the area of machine learning research, found its effectiveness in dealing complex yet high dimensional dataset that includes but limited to images, text and speech etc. with multiple levels of representation and abstraction. As there are a plethora of research on these datasets by various researchers , a win over them needs lots of attention. Careful setting of Deep learning parameters is of paramount importance in order to avoid the overfitting unlike conventional methods with limited parameter settings. Deep Convolutional neural network (DCNN) with multiple layers of compositions and appropriate settings might be is an efficient machine learning method that can outperform the conventional methods in a great way. However, due to its slow adoption in learning, there are also always a chance of overfitting during feature selection process, which can be addressed by employing a regularization method called dropout. Fast Random Forest (FRF) is a powerful ensemble classifier especially when the datasets are noisy and when the number of attributes is large in comparison to the number of instances, as is the case of Bioinformatics datasets. Several publicly available Bioinformatics dataset, Handwritten digits recognition and Image segmentation dataset are considered for evaluation of the proposed approach. The excellent performance obtained by the proposed DCNN based feature selection with FRF classifier on high dimensional datasets makes it a fast and accurate classifier in comparison the state-of-the-art.

* 11 pages, 9 figures, 1 table 

  Access Paper or Ask Questions

An End-to-End Neural Network for Polyphonic Piano Music Transcription

Feb 11, 2016
Siddharth Sigtia, Emmanouil Benetos, Simon Dixon

We present a supervised neural network model for polyphonic piano music transcription. The architecture of the proposed model is analogous to speech recognition systems and comprises an acoustic model and a music language model. The acoustic model is a neural network used for estimating the probabilities of pitches in a frame of audio. The language model is a recurrent neural network that models the correlations between pitch combinations over time. The proposed model is general and can be used to transcribe polyphonic music without imposing any constraints on the polyphony. The acoustic and language model predictions are combined using a probabilistic graphical model. Inference over the output variables is performed using the beam search algorithm. We perform two sets of experiments. We investigate various neural network architectures for the acoustic models and also investigate the effect of combining acoustic and music language model predictions using the proposed architecture. We compare performance of the neural network based acoustic models with two popular unsupervised acoustic models. Results show that convolutional neural network acoustic models yields the best performance across all evaluation metrics. We also observe improved performance with the application of the music language models. Finally, we present an efficient variant of beam search that improves performance and reduces run-times by an order of magnitude, making the model suitable for real-time applications.

  Access Paper or Ask Questions

Blind Signal Separation in the Presence of Gaussian Noise

Jun 09, 2013
Mikhail Belkin, Luis Rademacher, James Voss

A prototypical blind signal separation problem is the so-called cocktail party problem, with n people talking simultaneously and n different microphones within a room. The goal is to recover each speech signal from the microphone inputs. Mathematically this can be modeled by assuming that we are given samples from an n-dimensional random variable X=AS, where S is a vector whose coordinates are independent random variables corresponding to each speaker. The objective is to recover the matrix A^{-1} given random samples from X. A range of techniques collectively known as Independent Component Analysis (ICA) have been proposed to address this problem in the signal processing and machine learning literature. Many of these techniques are based on using the kurtosis or other cumulants to recover the components. In this paper we propose a new algorithm for solving the blind signal separation problem in the presence of additive Gaussian noise, when we are given samples from X=AS+\eta, where \eta is drawn from an unknown, not necessarily spherical n-dimensional Gaussian distribution. Our approach is based on a method for decorrelating a sample with additive Gaussian noise under the assumption that the underlying distribution is a linear transformation of a distribution with independent components. Our decorrelation routine is based on the properties of cumulant tensors and can be combined with any standard cumulant-based method for ICA to get an algorithm that is provably robust in the presence of Gaussian noise. We derive polynomial bounds for the sample complexity and error propagation of our method.

* 16 pages 

  Access Paper or Ask Questions

On the Efficacy of Co-Attention Transformer Layers in Visual Question Answering

Jan 11, 2022
Ankur Sikarwar, Gabriel Kreiman

In recent years, multi-modal transformers have shown significant progress in Vision-Language tasks, such as Visual Question Answering (VQA), outperforming previous architectures by a considerable margin. This improvement in VQA is often attributed to the rich interactions between vision and language streams. In this work, we investigate the efficacy of co-attention transformer layers in helping the network focus on relevant regions while answering the question. We generate visual attention maps using the question-conditioned image attention scores in these co-attention layers. We evaluate the effect of the following critical components on visual attention of a state-of-the-art VQA model: (i) number of object region proposals, (ii) question part of speech (POS) tags, (iii) question semantics, (iv) number of co-attention layers, and (v) answer accuracy. We compare the neural network attention maps against human attention maps both qualitatively and quantitatively. Our findings indicate that co-attention transformer modules are crucial in attending to relevant regions of the image given a question. Importantly, we observe that the semantic meaning of the question is not what drives visual attention, but specific keywords in the question do. Our work sheds light on the function and interpretation of co-attention transformer layers, highlights gaps in current networks, and can guide the development of future VQA models and networks that simultaneously process visual and language streams.

  Access Paper or Ask Questions

A Study On Data Augmentation In Voice Anti-Spoofing

Oct 20, 2021
Ariel Cohen, Inbal Rimon, Eran Aflalo, Haim Permuter

In this paper, we perform an in-depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel variability, different audio compressions, different band-widths, and unseen spoofing attacks, which have all been shown to significantly degrade the performance of audio-based systems and Anti-Spoofing systems. Our results are based on the ASVspoof 2021 challenge, in the Logical Access (LA) and Deep Fake (DF) categories. Our study is Data-Centric, meaning that the models are fixed and we significantly improve the results by making changes in the data. We introduce two forms of data augmentation - compression augmentation for the DF part, compression & channel augmentation for the LA part. In addition, a new type of online data augmentation, SpecAverage, is introduced in which the audio features are masked with their average value in order to improve generalization. Furthermore, we introduce a Log spectrogram feature design that improved the results. Our best single system and fusion scheme both achieve state-of-the-art performance in the DF category, with an EER of 15.46% and 14.46% respectively. Our best system for the LA task reduced the best baseline EER by 50% and the min t-DCF by 16%. Our techniques to deal with spoofed data from a wide variety of distributions can be replicated and can help anti-spoofing and speech-based systems enhance their results.

  Access Paper or Ask Questions

MusicNet: Compact Convolutional Neural Network for Real-time Background Music Detection

Oct 08, 2021
Chandan K. A. Reddy, Vishak Gopa, Harishchandra Dubey, Sergiy Matusevych, Ross Cutler, Robert Aichner

With the recent growth of remote and hybrid work, online meetings often encounter challenging audio contexts such as background noise, music, and echo. Accurate real-time detection of music events can help to improve the user experience in such scenarios, e.g., by switching to high-fidelity music-specific codec or selecting the optimal noise suppression model. In this paper, we present MusicNet -- a compact high-performance model for detecting background music in the real-time communications pipeline. In online video meetings, which is our main use case, music almost always co-occurs with speech and background noises, making the accurate classification quite challenging. The proposed model is a binary classifier that consists of a compact convolutional neural network core preceded by an in-model featurization layer. It takes 9 seconds of raw audio as input and does not require any model-specific featurization on the client. We train our model on a balanced subset of the AudioSet data and use 1000 crowd-sourced real test clips to validate the model. Finally, we compare MusicNet performance to 20 other state-of-the-art models. Our classifier gives a true positive rate of 81.3% at a 0.1% false positive rate, which is significantly better than any other model in the study. Our model is also 10x smaller and has 4x faster inference than the comparable baseline.

  Access Paper or Ask Questions

Fluent: An AI Augmented Writing Tool for People who Stutter

Aug 23, 2021
Bhavya Ghai, Klaus Mueller

Stuttering is a speech disorder which impacts the personal and professional lives of millions of people worldwide. To save themselves from stigma and discrimination, people who stutter (PWS) may adopt different strategies to conceal their stuttering. One of the common strategies is word substitution where an individual avoids saying a word they might stutter on and use an alternative instead. This process itself can cause stress and add more burden. In this work, we present Fluent, an AI augmented writing tool which assists PWS in writing scripts which they can speak more fluently. Fluent embodies a novel active learning based method of identifying words an individual might struggle pronouncing. Such words are highlighted in the interface. On hovering over any such word, Fluent presents a set of alternative words which have similar meaning but are easier to speak. The user is free to accept or ignore these suggestions. Based on such user interaction (feedback), Fluent continuously evolves its classifier to better suit the personalized needs of each user. We evaluated our tool by measuring its ability to identify difficult words for 10 simulated users. We found that our tool can identify difficult words with a mean accuracy of over 80% in under 20 interactions and it keeps improving with more feedback. Our tool can be beneficial for certain important life situations like giving a talk, presentation, etc. The source code for this tool has been made publicly accessible at

* Accepted to ACM ASSETS 2021 conference 

  Access Paper or Ask Questions

Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction

May 20, 2021
Patrick Lumban Tobing, Tomoki Toda

This paper presents a low-latency real-time (LLRT) non-parallel voice conversion (VC) framework based on cyclic variational autoencoder (CycleVAE) and multiband WaveRNN with data-driven linear prediction (MWDLP). CycleVAE is a robust non-parallel multispeaker spectral model, which utilizes a speaker-independent latent space and a speaker-dependent code to generate reconstructed/converted spectral features given the spectral features of an input speaker. On the other hand, MWDLP is an efficient and a high-quality neural vocoder that can handle multispeaker data and generate speech waveform for LLRT applications with CPU. To accommodate LLRT constraint with CPU, we propose a novel CycleVAE framework that utilizes mel-spectrogram as spectral features and is built with a sparse network architecture. Further, to improve the modeling performance, we also propose a novel fine-tuning procedure that refines the frame-rate CycleVAE network by utilizing the waveform loss from the MWDLP network. The experimental results demonstrate that the proposed framework achieves high-performance VC, while allowing for LLRT usage with a single-core of $2.1$--$2.7$~GHz CPU on a real-time factor of $0.87$--$0.95$, including input/output, feature extraction, on a frame shift of $10$ ms, a window length of $27.5$ ms, and $2$ lookup frames.

* Submitted to SSW11 

  Access Paper or Ask Questions

Multilingual Offensive Language Identification for Low-resource Languages

May 20, 2021
Tharindu Ranasinghe, Marcos Zampieri

Offensive content is pervasive in social media and a reason for concern to companies and government organizations. Several studies have been recently published investigating methods to detect the various forms of such content (e.g. hate speech, cyberbullying, and cyberaggression). The clear majority of these studies deal with English partially because most annotated datasets available contain English data. In this paper, we take advantage of available English datasets by applying cross-lingual contextual word embeddings and transfer learning to make predictions in low-resource languages. We project predictions on comparable data in Arabic, Bengali, Danish, Greek, Hindi, Spanish, and Turkish. We report results of 0.8415 F1 macro for Bengali in TRAC-2 shared task, 0.8532 F1 macro for Danish and 0.8701 F1 macro for Greek in OffensEval 2020, 0.8568 F1 macro for Hindi in HASOC 2019 shared task and 0.7513 F1 macro for Spanish in in SemEval-2019 Task 5 (HatEval) showing that our approach compares favourably to the best systems submitted to recent shared tasks on these three languages. Additionally, we report competitive performance on Arabic, and Turkish using the training and development sets of OffensEval 2020 shared task. The results for all languages confirm the robustness of cross-lingual contextual embeddings and transfer learning for this task.

* Accepted to ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP). This is an extended version of a paper accepted to EMNLP. arXiv admin note: substantial text overlap with arXiv:2010.05324 

  Access Paper or Ask Questions