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

An Information-Theoretic View for Deep Learning

Oct 02, 2018
Jingwei Zhang, Tongliang Liu, Dacheng Tao

Deep learning has transformed computer vision, natural language processing, and speech recognition\cite{badrinarayanan2017segnet, dong2016image, ren2017faster, ji20133d}. However, two critical questions remain obscure: (1) why do deep neural networks generalize better than shallow networks; and (2) does it always hold that a deeper network leads to better performance? Specifically, letting $L$ be the number of convolutional and pooling layers in a deep neural network, and $n$ be the size of the training sample, we derive an upper bound on the expected generalization error for this network, i.e., \begin{eqnarray*} \mathbb{E}[R(W)-R_S(W)] \leq \exp{\left(-\frac{L}{2}\log{\frac{1}{\eta}}\right)}\sqrt{\frac{2\sigma^2}{n}I(S,W) } \end{eqnarray*} where $\sigma >0$ is a constant depending on the loss function, $0<\eta<1$ is a constant depending on the information loss for each convolutional or pooling layer, and $I(S, W)$ is the mutual information between the training sample $S$ and the output hypothesis $W$. This upper bound shows that as the number of convolutional and pooling layers $L$ increases in the network, the expected generalization error will decrease exponentially to zero. Layers with strict information loss, such as the convolutional layers, reduce the generalization error for the whole network; this answers the first question. However, algorithms with zero expected generalization error does not imply a small test error or $\mathbb{E}[R(W)]$. This is because $\mathbb{E}[R_S(W)]$ is large when the information for fitting the data is lost as the number of layers increases. This suggests that the claim `the deeper the better' is conditioned on a small training error or $\mathbb{E}[R_S(W)]$. Finally, we show that deep learning satisfies a weak notion of stability and the sample complexity of deep neural networks will decrease as $L$ increases.

* Add details in the proof of Theorem 2 

  Access Paper or Ask Questions

Efficient and Generic 1D Dilated Convolution Layer for Deep Learning

Apr 16, 2021
Narendra Chaudhary, Sanchit Misra, Dhiraj Kalamkar, Alexander Heinecke, Evangelos Georganas, Barukh Ziv, Menachem Adelman, Bharat Kaul

Convolutional neural networks (CNNs) have found many applications in tasks involving two-dimensional (2D) data, such as image classification and image processing. Therefore, 2D convolution layers have been heavily optimized on CPUs and GPUs. However, in many applications - for example genomics and speech recognition, the data can be one-dimensional (1D). Such applications can benefit from optimized 1D convolution layers. In this work, we introduce our efficient implementation of a generic 1D convolution layer covering a wide range of parameters. It is optimized for x86 CPU architectures, in particular, for architectures containing Intel AVX-512 and AVX-512 BFloat16 instructions. We use the LIBXSMM library's batch-reduce General Matrix Multiplication (BRGEMM) kernel for FP32 and BFloat16 precision. We demonstrate that our implementation can achieve up to 80% efficiency on Intel Xeon Cascade Lake and Cooper Lake CPUs. Additionally, we show the generalization capability of our BRGEMM based approach by achieving high efficiency across a range of parameters. We consistently achieve higher efficiency than the 1D convolution layer with Intel oneDNN library backend for varying input tensor widths, filter widths, number of channels, filters, and dilation parameters. Finally, we demonstrate the performance of our optimized 1D convolution layer by utilizing it in the end-to-end neural network training with real genomics datasets and achieve up to 6.86x speedup over the oneDNN library-based implementation on Cascade Lake CPUs. We also demonstrate the scaling with 16 sockets of Cascade/Cooper Lake CPUs and achieve significant speedup over eight V100 GPUs using a similar power envelop. In the end-to-end training, we get a speedup of 1.41x on Cascade Lake with FP32, 1.57x on Cooper Lake with FP32, and 2.27x on Cooper Lake with BFloat16 over eight V100 GPUs with FP32.

  Access Paper or Ask Questions

Edge AI without Compromise: Efficient, Versatile and Accurate Neurocomputing in Resistive Random-Access Memory

Aug 17, 2021
Weier Wan, Rajkumar Kubendran, Clemens Schaefer, S. Burc Eryilmaz, Wenqiang Zhang, Dabin Wu, Stephen Deiss, Priyanka Raina, He Qian, Bin Gao, Siddharth Joshi, Huaqiang Wu, H. -S. Philip Wong, Gert Cauwenberghs

Realizing today's cloud-level artificial intelligence functionalities directly on devices distributed at the edge of the internet calls for edge hardware capable of processing multiple modalities of sensory data (e.g. video, audio) at unprecedented energy-efficiency. AI hardware architectures today cannot meet the demand due to a fundamental "memory wall": data movement between separate compute and memory units consumes large energy and incurs long latency. Resistive random-access memory (RRAM) based compute-in-memory (CIM) architectures promise to bring orders of magnitude energy-efficiency improvement by performing computation directly within memory. However, conventional approaches to CIM hardware design limit its functional flexibility necessary for processing diverse AI workloads, and must overcome hardware imperfections that degrade inference accuracy. Such trade-offs between efficiency, versatility and accuracy cannot be addressed by isolated improvements on any single level of the design. By co-optimizing across all hierarchies of the design from algorithms and architecture to circuits and devices, we present NeuRRAM - the first multimodal edge AI chip using RRAM CIM to simultaneously deliver a high degree of versatility for diverse model architectures, record energy-efficiency $5\times$ - $8\times$ better than prior art across various computational bit-precisions, and inference accuracy comparable to software models with 4-bit weights on all measured standard AI benchmarks including accuracy of 99.0% on MNIST and 85.7% on CIFAR-10 image classification, 84.7% accuracy on Google speech command recognition, and a 70% reduction in image reconstruction error on a Bayesian image recovery task. This work paves a way towards building highly efficient and reconfigurable edge AI hardware platforms for the more demanding and heterogeneous AI applications of the future.

* 34 pages, 14 figures, 1 table 

  Access Paper or Ask Questions

Multi-Task Text Classification using Graph Convolutional Networks for Large-Scale Low Resource Language

May 02, 2022
Mounika Marreddy, Subba Reddy Oota, Lakshmi Sireesha Vakada, Venkata Charan Chinni, Radhika Mamidi

Graph Convolutional Networks (GCN) have achieved state-of-art results on single text classification tasks like sentiment analysis, emotion detection, etc. However, the performance is achieved by testing and reporting on resource-rich languages like English. Applying GCN for multi-task text classification is an unexplored area. Moreover, training a GCN or adopting an English GCN for Indian languages is often limited by data availability, rich morphological variation, syntax, and semantic differences. In this paper, we study the use of GCN for the Telugu language in single and multi-task settings for four natural language processing (NLP) tasks, viz. sentiment analysis (SA), emotion identification (EI), hate-speech (HS), and sarcasm detection (SAR). In order to evaluate the performance of GCN with one of the Indian languages, Telugu, we analyze the GCN based models with extensive experiments on four downstream tasks. In addition, we created an annotated Telugu dataset, TEL-NLP, for the four NLP tasks. Further, we propose a supervised graph reconstruction method, Multi-Task Text GCN (MT-Text GCN) on the Telugu that leverages to simultaneously (i) learn the low-dimensional word and sentence graph embeddings from word-sentence graph reconstruction using graph autoencoder (GAE) and (ii) perform multi-task text classification using these latent sentence graph embeddings. We argue that our proposed MT-Text GCN achieves significant improvements on TEL-NLP over existing Telugu pretrained word embeddings, and multilingual pretrained Transformer models: mBERT, and XLM-R. On TEL-NLP, we achieve a high F1-score for four NLP tasks: SA (0.84), EI (0.55), HS (0.83) and SAR (0.66). Finally, we show our model's quantitative and qualitative analysis on the four NLP tasks in Telugu.

* 9 pages, 6 figures 

  Access Paper or Ask Questions

Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks

Oct 26, 2018
Yingyezhe Jin, Wenrui Zhang, Peng Li

Spiking neural networks (SNNs) are positioned to enable spatio-temporal information processing and ultra-low power event-driven neuromorphic hardware. However, SNNs are yet to reach the same performances of conventional deep artificial neural networks (ANNs), a long-standing challenge due to complex dynamics and non-differentiable spike events encountered in training. The existing SNN error backpropagation (BP) methods are limited in terms of scalability, lack of proper handling of spiking discontinuities, and/or mismatch between the rate-coded loss function and computed gradient. We present a hybrid macro/micro level backpropagation (HM2-BP) algorithm for training multi-layer SNNs. The temporal effects are precisely captured by the proposed spike-train level post-synaptic potential (S-PSP) at the microscopic level. The rate-coded errors are defined at the macroscopic level, computed and back-propagated across both macroscopic and microscopic levels. Different from existing BP methods, HM2-BP directly computes the gradient of the rate-coded loss function w.r.t tunable parameters. We evaluate the proposed HM2-BP algorithm by training deep fully connected and convolutional SNNs based on the static MNIST [14] and dynamic neuromorphic N-MNIST [26]. HM2-BP achieves an accuracy level of 99.49% and 98.88% for MNIST and N-MNIST, respectively, outperforming the best reported performances obtained from the existing SNN BP algorithms. Furthermore, the HM2-BP produces the highest accuracies based on SNNs for the EMNIST [3] dataset, and leads to high recognition accuracy for the 16-speaker spoken English letters of TI46 Corpus [16], a challenging patio-temporal speech recognition benchmark for which no prior success based on SNNs was reported. It also achieves competitive performances surpassing those of conventional deep learning models when dealing with asynchronous spiking streams.

* 11 pages, 5 figures. Accepted by NIPS 2018. Code available: 

  Access Paper or Ask Questions

Automatic Tuberculosis and COVID-19 cough classification using deep learning

May 11, 2022
Madhurananda Pahar, Marisa Klopper, Byron Reeve, Rob Warren, Grant Theron, Andreas Diacon, Thomas Niesler

We present a deep learning based automatic cough classifier which can discriminate tuberculosis (TB) coughs from COVID-19 coughs and healthy coughs. Both TB and COVID-19 are respiratory disease, have cough as a predominant symptom and claim thousands of lives each year. The cough audio recordings were collected at both indoor and outdoor settings and also uploaded using smartphones from subjects around the globe, thus contain various levels of noise. This cough data include 1.68 hours of TB coughs, 18.54 minutes of COVID-19 coughs and 1.69 hours of healthy coughs from 47 TB patients, 229 COVID-19 patients and 1498 healthy patients and were used to train and evaluate a CNN, LSTM and Resnet50. These three deep architectures were also pre-trained on 2.14 hours of sneeze, 2.91 hours of speech and 2.79 hours of noise for improved performance. The class-imbalance in our dataset was addressed by using SMOTE data balancing technique and using performance metrics such as F1-score and AUC. Our study shows that the highest F1-scores of 0.9259 and 0.8631 have been achieved from a pre-trained Resnet50 for two-class (TB vs COVID-19) and three-class (TB vs COVID-19 vs healthy) cough classification tasks, respectively. The application of deep transfer learning has improved the classifiers' performance and makes them more robust as they generalise better over the cross-validation folds. Their performances exceed the TB triage test requirements set by the world health organisation (WHO). The features producing the best performance contain higher order of MFCCs suggesting that the differences between TB and COVID-19 coughs are not perceivable by the human ear. This type of cough audio classification is non-contact, cost-effective and can easily be deployed on a smartphone, thus it can be an excellent tool for both TB and COVID-19 screening.

  Access Paper or Ask Questions

EDEN: Enabling Energy-Efficient, High-Performance Deep Neural Network Inference Using Approximate DRAM

Oct 12, 2019
Skanda Koppula, Lois Orosa, Abdullah Giray Yağlıkçı, Roknoddin Azizi, Taha Shahroodi, Konstantinos Kanellopoulos, Onur Mutlu

The effectiveness of deep neural networks (DNN) in vision, speech, and language processing has prompted a tremendous demand for energy-efficient high-performance DNN inference systems. Due to the increasing memory intensity of most DNN workloads, main memory can dominate the system's energy consumption and stall time. One effective way to reduce the energy consumption and increase the performance of DNN inference systems is by using approximate memory, which operates with reduced supply voltage and reduced access latency parameters that violate standard specifications. Using approximate memory reduces reliability, leading to higher bit error rates. Fortunately, neural networks have an intrinsic capacity to tolerate increased bit errors. This can enable energy-efficient and high-performance neural network inference using approximate DRAM devices. Based on this observation, we propose EDEN, a general framework that reduces DNN energy consumption and DNN evaluation latency by using approximate DRAM devices, while strictly meeting a user-specified target DNN accuracy. EDEN relies on two key ideas: 1) retraining the DNN for a target approximate DRAM device to increase the DNN's error tolerance, and 2) efficient mapping of the error tolerance of each individual DNN data type to a corresponding approximate DRAM partition in a way that meets the user-specified DNN accuracy requirements. We evaluate EDEN on multi-core CPUs, GPUs, and DNN accelerators with error models obtained from real approximate DRAM devices. For a target accuracy within 1% of the original DNN, our results show that EDEN enables 1) an average DRAM energy reduction of 21%, 37%, 31%, and 32% in CPU, GPU, and two DNN accelerator architectures, respectively, across a variety of DNNs, and 2) an average (maximum) speedup of 8% (17%) and 2.7% (5.5%) in CPU and GPU architectures, respectively, when evaluating latency-bound DNNs.

* This work is to appear at MICRO 2019 

  Access Paper or Ask Questions

Speech Controlled Quadruped

Jun 24, 2015
Devashish Kulkarni, Sagar Paldhe, Vinod Kamat

The project which we have performed is based on voice recognition and we desire to create a four legged robot that can acknowledge the given instructions which are given through vocal commands and perform the tasks. The main processing unit of the robot will be Arduino Uno. We are using 8 servos for the movement of its legs while two servos will be required for each leg. The interface between a human and the robot is generated through Python programming and Eclipse software and it is implemented by using Bluetooth module HC 06.

* 7 pages 

  Access Paper or Ask Questions

Heterogeneous Target Speech Separation

Apr 07, 2022
Efthymios Tzinis, Gordon Wichern, Aswin Subramanian, Paris Smaragdis, Jonathan Le Roux

We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e.g., loudness, gender, language, spatial location, etc). Our proposed heterogeneous separation framework can seamlessly leverage datasets with large distribution shifts and learn cross-domain representations under a variety of concepts used as conditioning. Our experiments show that training separation models with heterogeneous conditions facilitates the generalization to new concepts with unseen out-of-domain data while also performing substantially higher than single-domain specialist models. Notably, such training leads to more robust learning of new harder source separation discriminative concepts and can yield improvements over permutation invariant training with oracle source selection. We analyze the intrinsic behavior of source separation training with heterogeneous metadata and propose ways to alleviate emerging problems with challenging separation conditions. We release the collection of preparation recipes for all datasets used to further promote research towards this challenging task.

* Submitted to Interspeech 2022 

  Access Paper or Ask Questions

Luganda Text-to-Speech Machine

May 11, 2020
Irene Nandutu, Ernest Mwebaze

In Uganda, Luganda is the most spoken native language. It is used for communication in informal as well as formal business transactions. The development of technology startups globally related to TTS has mainly been with languages like English, French, etc. These are added in TTS engines by Google, Microsoft among others, allowing developers in these regions to innovate TTS products. Luganda is not supported because the language is not built and trained on these engines. In this study, we analyzed the Luganda language structure and constructions and then proposed and developed a Luganda TTS. The system was built and trained using locally sourced Luganda language text and audio. The engine is now able to capture text and reads it aloud. We tested the accuracy using MRT and MOS. MRT and MOS tests results are quite good with MRT having better results. The results general score was 71%. This study will enhance previous solutions to NLP gaps in Uganda, as well as provide raw data such that other research in this area can take place.

  Access Paper or Ask Questions