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

Overfitting Mechanism and Avoidance in Deep Neural Networks

Jan 19, 2019
Shaeke Salman, Xiuwen Liu

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and natural language processing. As they are being used in critical applications, understanding underlying mechanisms for their successes and limitations is imperative. In this paper, we show that overfitting, one of the fundamental issues in deep neural networks, is due to continuous gradient updating and scale sensitiveness of cross entropy loss. By separating samples into correctly and incorrectly classified ones, we show that they behave very differently, where the loss decreases in the correct ones and increases in the incorrect ones. Furthermore, by analyzing dynamics during training, we propose a consensus-based classification algorithm that enables us to avoid overfitting and significantly improve the classification accuracy especially when the number of training samples is limited. As each trained neural network depends on extrinsic factors such as initial values as well as training data, requiring consensus among multiple models reduces extrinsic factors substantially; for statistically independent models, the reduction is exponential. Compared to ensemble algorithms, the proposed algorithm avoids overgeneralization by not classifying ambiguous inputs. Systematic experimental results demonstrate the effectiveness of the proposed algorithm. For example, using only 1000 training samples from MNIST dataset, the proposed algorithm achieves 95% accuracy, significantly higher than any of the individual models, with 90% of the test samples classified.

* 8 pages, 8 figures 

  Access Paper or Ask Questions

Modeling of the Latent Embedding of Music using Deep Neural Network

May 12, 2017
Zhou Xing, Eddy Baik, Yan Jiao, Nilesh Kulkarni, Chris Li, Gautam Muralidhar, Marzieh Parandehgheibi, Erik Reed, Abhishek Singhal, Fei Xiao, Chris Pouliot

While both the data volume and heterogeneity of the digital music content is huge, it has become increasingly important and convenient to build a recommendation or search system to facilitate surfacing these content to the user or consumer community. Most of the recommendation models fall into two primary species, collaborative filtering based and content based approaches. Variants of instantiations of collaborative filtering approach suffer from the common issues of so called "cold start" and "long tail" problems where there is not much user interaction data to reveal user opinions or affinities on the content and also the distortion towards the popular content. Content-based approaches are sometimes limited by the richness of the available content data resulting in a heavily biased and coarse recommendation result. In recent years, the deep neural network has enjoyed a great success in large-scale image and video recognitions. In this paper, we propose and experiment using deep convolutional neural network to imitate how human brain processes hierarchical structures in the auditory signals, such as music, speech, etc., at various timescales. This approach can be used to discover the latent factor models of the music based upon acoustic hyper-images that are extracted from the raw audio waves of music. These latent embeddings can be used either as features to feed to subsequent models, such as collaborative filtering, or to build similarity metrics between songs, or to classify music based on the labels for training such as genre, mood, sentiment, etc.

  Access Paper or Ask Questions

Energy-Efficient AI over a Virtualized Cloud Fog Network

May 07, 2021
Barzan A. Yosuf, Sanaa H. Mohamed, Mohamed Alenazi, Taisir E. H. El-Gorashi, Jaafar M. H. Elmirghani

Deep Neural Networks (DNNs) have served as a catalyst in introducing a plethora of next-generation services in the era of Internet of Things (IoT), thanks to the availability of massive amounts of data collected by the objects on the edge. Currently, DNN models are used to deliver many Artificial Intelligence (AI) services that include image and natural language processing, speech recognition, and robotics. Accordingly, such services utilize various DNN models that make it computationally intensive for deployment on the edge devices alone. Thus, most AI models are offloaded to distant cloud data centers (CDCs), which tend to consolidate large amounts of computing and storage resources into one or more CDCs. Deploying services in the CDC will inevitably lead to excessive latencies and overall increase in power consumption. Instead, fog computing allows for cloud services to be extended to the edge of the network, which allows for data processing to be performed closer to the end-user device. However, different from cloud data centers, fog nodes have limited computational power and are highly distributed in the network. In this paper, using Mixed Integer Linear Programming (MILP), we formulate the placement of DNN inference models, which is abstracted as a network embedding problem in a Cloud Fog Network (CFN) architecture, where power savings are introduced through trade-offs between processing and networking. We study the performance of the CFN architecture by comparing the energy savings when compared to the baseline approach which is the CDC.

  Access Paper or Ask Questions

CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion

Oct 22, 2020
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo

Non-parallel voice conversion (VC) is a technique for learning mappings between source and target speeches without using a parallel corpus. Recently, cycle-consistent adversarial network (CycleGAN)-VC and CycleGAN-VC2 have shown promising results regarding this problem and have been widely used as benchmark methods. However, owing to the ambiguity of the effectiveness of CycleGAN-VC/VC2 for mel-spectrogram conversion, they are typically used for mel-cepstrum conversion even when comparative methods employ mel-spectrogram as a conversion target. To address this, we examined the applicability of CycleGAN-VC/VC2 to mel-spectrogram conversion. Through initial experiments, we discovered that their direct applications compromised the time-frequency structure that should be preserved during conversion. To remedy this, we propose CycleGAN-VC3, an improvement of CycleGAN-VC2 that incorporates time-frequency adaptive normalization (TFAN). Using TFAN, we can adjust the scale and bias of the converted features while reflecting the time-frequency structure of the source mel-spectrogram. We evaluated CycleGAN-VC3 on inter-gender and intra-gender non-parallel VC. A subjective evaluation of naturalness and similarity showed that for every VC pair, CycleGAN-VC3 outperforms or is competitive with the two types of CycleGAN-VC2, one of which was applied to mel-cepstrum and the other to mel-spectrogram. Audio samples are available at

* Accepted to Interspeech 2020. Project page: 

  Access Paper or Ask Questions

More Grounded Image Captioning by Distilling Image-Text Matching Model

Apr 01, 2020
Yuanen Zhou, Meng Wang, Daqing Liu, Zhenzhen Hu, Hanwang Zhang

Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a captioner can fix its attentive gaze on the correct objects while generating the corresponding words. This ability is also known as grounded image captioning. However, the grounding accuracy of existing captioners is far from satisfactory. To improve the grounding accuracy while retaining the captioning quality, it is expensive to collect the word-region alignment as strong supervision. To this end, we propose a Part-of-Speech (POS) enhanced image-text matching model (SCAN \cite{lee2018stacked}): POS-SCAN, as the effective knowledge distillation for more grounded image captioning. The benefits are two-fold: 1) given a sentence and an image, POS-SCAN can ground the objects more accurately than SCAN; 2) POS-SCAN serves as a word-region alignment regularization for the captioner's visual attention module. By showing benchmark experimental results, we demonstrate that conventional image captioners equipped with POS-SCAN can significantly improve the grounding accuracy without strong supervision. Last but not the least, we explore the indispensable Self-Critical Sequence Training (SCST) \cite{Rennie_2017_CVPR} in the context of grounded image captioning and show that the image-text matching score can serve as a reward for more grounded captioning \footnote{}.

* Accepted by CVPR 2020 

  Access Paper or Ask Questions

Multimodal Intelligence: Representation Learning, Information Fusion, and Applications

Nov 10, 2019
Chao Zhang, Zichao Yang, Xiaodong He, Li Deng

Deep learning has revolutionized speech recognition, image recognition, and natural language processing since 2010, each involving a single modality in the input signal. However, many applications in artificial intelligence involve more than one modality. It is therefore of broad interest to study the more difficult and complex problem of modeling and learning across multiple modalities. In this paper, a technical review of the models and learning methods for multimodal intelligence is provided. The main focus is the combination of vision and natural language, which has become an important area in both computer vision and natural language processing research communities. This review provides a comprehensive analysis of recent work on multimodal deep learning from three new angles - learning multimodal representations, the fusion of multimodal signals at various levels, and multimodal applications. On multimodal representation learning, we review the key concept of embedding, which unifies the multimodal signals into the same vector space and thus enables cross-modality signal processing. We also review the properties of the many types of embedding constructed and learned for general downstream tasks. On multimodal fusion, this review focuses on special architectures for the integration of the representation of unimodal signals for a particular task. On applications, selected areas of a broad interest in current literature are covered, including caption generation, text-to-image generation, and visual question answering. We believe this review can facilitate future studies in the emerging field of multimodal intelligence for the community.

  Access Paper or Ask Questions

Two-level Attention with Two-stage Multi-task Learning for Facial Emotion Recognition

Nov 29, 2018
Xiaohua Wang, Muzi Peng, Lijuan Pan, Min Hu, Chunhua Jin, Fuji Ren

Compared with facial emotion recognition on categorical model, the dimensional emotion recognition can describe numerous emotions of the real world more accurately. Most prior works of dimensional emotion estimation only considered laboratory data and used video, speech or other multi-modal features. The effect of these methods applied on static images in the real world is unknown. In this paper, a two-level attention with two-stage multi-task learning (2Att-2Mt) framework is proposed for facial emotion estimation on only static images. Firstly, the features of corresponding region(position-level features) are extracted and enhanced automatically by first-level attention mechanism. In the following, we utilize Bi-directional Recurrent Neural Network(Bi-RNN) with self-attention(second-level attention) to make full use of the relationship features of different layers(layer-level features) adaptively. Owing to the inherent complexity of dimensional emotion recognition, we propose a two-stage multi-task learning structure to exploited categorical representations to ameliorate the dimensional representations and estimate valence and arousal simultaneously in view of the correlation of the two targets. The quantitative results conducted on AffectNet dataset show significant advancement on Concordance Correlation Coefficient(CCC) and Root Mean Square Error(RMSE), illustrating the superiority of the proposed framework. Besides, extensive comparative experiments have also fully demonstrated the effectiveness of different components.

* 10 pages, 4 figures 

  Access Paper or Ask Questions

RAPIDNN: In-Memory Deep Neural Network Acceleration Framework

Aug 09, 2018
Mohsen Imani, Mohammad Samragh, Yeseong Kim, Saransh Gupta, Farinaz Koushanfar, Tajana Rosing

Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-theart DNNs on current systems mostly relies on either generalpurpose processors, ASIC designs, or FPGA accelerators, all of which suffer from data movements due to the limited onchip memory and data transfer bandwidth. In this work, we propose a novel framework, called RAPIDNN, which processes all DNN operations within the memory to minimize the cost of data movement. To enable in-memory processing, RAPIDNN reinterprets a DNN model and maps it into a specialized accelerator, which is designed using non-volatile memory blocks that model four fundamental DNN operations, i.e., multiplication, addition, activation functions, and pooling. The framework extracts representative operands of a DNN model, e.g., weights and input values, using clustering methods to optimize the model for in-memory processing. Then, it maps the extracted operands and their precomputed results into the accelerator memory blocks. At runtime, the accelerator identifies computation results based on efficient in-memory search capability which also provides tunability of approximation to further improve computation efficiency. Our evaluation shows that RAPIDNN achieves 68.4x, 49.5x energy efficiency improvement and 48.1x, 10.9x speedup as compared to ISAAC and PipeLayer, the state-of-the-art DNN accelerators, while ensuring less than 0.3% of quality loss.

  Access Paper or Ask Questions

A Critical Review of Recurrent Neural Networks for Sequence Learning

Oct 17, 2015
Zachary C. Lipton, John Berkowitz, Charles Elkan

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, and music generation all require that a model produce outputs that are sequences. In other domains, such as time series prediction, video analysis, and musical information retrieval, a model must learn from inputs that are sequences. Interactive tasks, such as translating natural language, engaging in dialogue, and controlling a robot, often demand both capabilities. Recurrent neural networks (RNNs) are connectionist models that capture the dynamics of sequences via cycles in the network of nodes. Unlike standard feedforward neural networks, recurrent networks retain a state that can represent information from an arbitrarily long context window. Although recurrent neural networks have traditionally been difficult to train, and often contain millions of parameters, recent advances in network architectures, optimization techniques, and parallel computation have enabled successful large-scale learning with them. In recent years, systems based on long short-term memory (LSTM) and bidirectional (BRNN) architectures have demonstrated ground-breaking performance on tasks as varied as image captioning, language translation, and handwriting recognition. In this survey, we review and synthesize the research that over the past three decades first yielded and then made practical these powerful learning models. When appropriate, we reconcile conflicting notation and nomenclature. Our goal is to provide a self-contained explication of the state of the art together with a historical perspective and references to primary research.

  Access Paper or Ask Questions

Noun2Verb: Probabilistic frame semantics for word class conversion

May 12, 2022
Lei Yu, Yang Xu

Humans can flexibly extend word usages across different grammatical classes, a phenomenon known as word class conversion. Noun-to-verb conversion, or denominal verb (e.g., to Google a cheap flight), is one of the most prevalent forms of word class conversion. However, existing natural language processing systems are impoverished in interpreting and generating novel denominal verb usages. Previous work has suggested that novel denominal verb usages are comprehensible if the listener can compute the intended meaning based on shared knowledge with the speaker. Here we explore a computational formalism for this proposal couched in frame semantics. We present a formal framework, Noun2Verb, that simulates the production and comprehension of novel denominal verb usages by modeling shared knowledge of speaker and listener in semantic frames. We evaluate an incremental set of probabilistic models that learn to interpret and generate novel denominal verb usages via paraphrasing. We show that a model where the speaker and listener cooperatively learn the joint distribution over semantic frame elements better explains the empirical denominal verb usages than state-of-the-art language models, evaluated against data from 1) contemporary English in both adult and child speech, 2) contemporary Mandarin Chinese, and 3) the historical development of English. Our work grounds word class conversion in probabilistic frame semantics and bridges the gap between natural language processing systems and humans in lexical creativity.

  Access Paper or Ask Questions