Speech Commands Dataset Research Articles

Isolated word recognition based on PNCC with different classifiers in a noisy environment

Speech Recognition is one of the important methods to control robotics, mobile applications, automobile, etc. Nevertheless, still, the Speech recognition rate needs to be improved especially in noisy environments. The main goal of this paper is to investigate the best features for isolated word recognition between the most common features extraction technique Mel Frequency Cepstral Coefficient MFCC and noise immunity features extraction technique Power Normalized Cepstral Coefficient PNCC, with the aid of four classifiers, Weighted KNN, Medium KNN, Linear SVM, Quadratic SVM in different levels of noise. The database that is used for this study is Speech Commands Data Set v0.01 which is containing 64,727 audio files to get a good estimation of the recognition rate. The algorithm based on MFCC is recommended for Speaker dependent speech recognition a little bit better (1.1%) than the algorithm based on PNCC in a noise-free environment. Nevertheless, the proposed algorithm based on PNCC is more efficient than the algorithm based on MFCC for Speaker independent speech recognition, and overall Recognition accuracy. Moreover, it has more immunity to noise and it is more accurate than MFCC by 8.7% on average with already trained speakers and 18.528% on average with new trained speakers’ tests. Finally, the proposed algorithm based on the PNCC feature extraction with aid of Weighted KNN is more accurate than other algorithms for Speaker independent speech recognition and overall Recognition accuracy. Moreover, it has more immunity to noise.

Small-Footprint Keyword Spotting Based on Gated Channel Transformation Sandglass Residual Neural Network

Keyword spotting plays a crucial role in realizing voice-based user interaction on intelligent equipment terminals and service robots. In this task, it remains challenging to achieve the balance between low memory and high precision. To better satisfy this requirement, we propose an end-to-end neural architecture with sandglass residual blocks embedded with the gated channel-wise attention mechanism. The sandglass residual blocks utilize 1D separable convolutions to extract bottleneck temporal features, which can effectively drive the model to focus more on the speech segment with lower parameters. Especially, the gated attention mechanism helps the model enhance the critical speech temporal features and suppress the useless ones and further focus on the most important part of the human speech region for keyword spotting. The experimental results on Google Speech Commands Dataset show that our proposed model has an accuracy of 97.4[Formula: see text] with only 46K parameters. Compared with the baseline method with the highest accuracy, our model parameters are decreased by 54[Formula: see text] and accuracy is increased by 0.8[Formula: see text]. That makes us take further step in achieving the goal of low memory and high precision.

Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks

Keyword spotting (KWS) is a crucial function enabling the interaction with the many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as a human-computer interface. For many applications, KWS is the entry point for our interactions with the device and, thus, an always-on workload. Many smart devices are mobile and their battery lifetime is heavily impacted by continuously running services. KWS and similar always-on services are thus the focus when optimizing the overall power consumption. This work addresses KWS energy-efficiency on low-cost microcontroller units (MCUs). We combine analog binary feature extraction with binary neural networks. By replacing the digital preprocessing with the proposed analog front-end, we show that the energy required for data acquisition and preprocessing can be reduced by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$29\times $ </tex-math></inline-formula> , cutting its share from a dominating 85% to a mere 16% of the overall energy consumption for our reference KWS application. Experimental evaluations on the Speech Commands Dataset show that the proposed system outperforms state-of-the-art accuracy and energy efficiency, respectively, by 1% and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4.3\times $ </tex-math></inline-formula> on a 10-class dataset while providing a compelling accuracy-energy trade-off including a 2% accuracy drop for a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$71\times $ </tex-math></inline-formula> energy reduction.

Two-stage streaming keyword detection and localization with multi-scale depthwise temporal convolution

A keyword spotting (KWS) system running on smart devices should accurately detect the appearances and predict the locations of predefined keywords from audio streams, with small footprint and high efficiency. To this end, this paper proposes a new two-stage KWS method which combines a novel multi-scale depthwise temporal convolution (MDTC) feature extractor and a two-stage keyword detection and localization module. The MDTC feature extractor learns multi-scale feature representation efficiently with dilated depthwise temporal convolution, modeling both the temporal context and the speech rate variation. We use a region proposal network (RPN) as the first-stage KWS. At each frame, we design multiple time regions, which all take the current frame as the end position but have different start positions. These time regions (or formally anchors) are used to indicate rough location candidates of keyword. With frame level features from the MDTC feature extractor as inputs, RPN learns to propose keyword region proposals based on the designed anchors. To alleviate the keyword/non-keyword class imbalance problem, we specifically introduce a hard example mining algorithm to select effective negative anchors in RPN training. The keyword region proposals from the first-stage RPN contain keyword location information which is subsequently used to explicitly extract keyword related sequential features to train the second-stage KWS. The second-stage system learns to classify and transform region proposal to keyword IDs and ground-truth keyword region respectively. Experiments on the Google Speech Command dataset show that the proposed MDTC feature extractor surpasses several competitive feature extractors with a new state-of-the-art command classification error rate of 1.74%. With the MDTC feature extractor, we further conduct wake-up word (WuW) detection and localization experiments on a commercial WuW dataset. Compared to a strong baseline, our proposed two-stage method achieves relatively 27–32% better false rejection rate at one false alarm per hour, while for keyword localization, the two-stage approach achieves more than 0.95 mean intersection-over-union ratio, which is clearly better than the one-stage RPN method.

Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks

Keyword spotting (KWS) is a crucial function enabling the interaction with the many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as a human-computer interface. For many applications, KWS is the entry point for our interactions with the device and, thus, an always-on workload. Many smart devices are mobile and their battery lifetime is heavily impacted by continuously running services. KWS and similar always-on services are thus the focus when optimizing the overall power consumption. This work addresses KWS energy-efficiency on low-cost microcontroller units (MCUs). We combine analog binary feature extraction with binary neural networks. By replacing the digital preprocessing with the proposed analog front-end, we show that the energy required for data acquisition and preprocessing can be reduced by 29x, cutting its share from a dominating 85% to a mere 16% of the overall energy consumption for our reference KWS application. Experimental evaluations on the Speech Commands Dataset show that the proposed system outperforms state-of-the-art accuracy and energy efficiency, respectively, by 1% and 4.3x on a 10-class dataset while providing a compelling accuracy-energy trade-off including a 2% accuracy drop for a 71x energy reduction.

An Innovative Approach Utilizing Binary-View Transformer for Speech Recognition Task

The deep learning advancements have greatly improved the performance of speech recognition systems, and most recent systems are based on the Recurrent Neural Network (RNN). Overall, the RNN works fine with the small sequence data, but suffers from the gradient vanishing problem in case of large sequence. The transformer networks have neutralized this issue and have shown state-of-the-art results on sequential or speech-related data. Generally, in speech recognition, the input audio is converted into an image using Mel-spectrogram to illustrate frequencies and intensities. The image is classified by the machine learning mechanism to generate a classification transcript. However, the audio frequency in the image has low resolution and causing inaccurate predictions. This paper presents a novel end-to-end binary view transformer-based architecture for speech recognition to cope with the frequency resolution problem. Firstly, the input audio signal is transformed into a 2D image using Mel-spectrogram. Secondly, the modified universal transformers utilize the multi-head attention to derive contextual information and derive different speech-related features. Moreover, a feed-forward neural network is also deployed for classification. The proposed system has generated robust results on Google's speech command dataset with an accuracy of 95.16% and with minimal loss. The binary-view transformer eradicates the eventuality of the over-fitting problem by deploying a multi-view mechanism to diversify the input data, and multi-head attention captures multiple contexts from the data's feature map.

A Multi-Stage Ensembled-Learning Approach for Signal Classification Based on Deep CNN and LGBM Models

In this paper, we propose a novel ensembled-learning architecture incorporating a hybrid multi-stage concatenation of the deep Convolutional Neural Network (CNN) model and the Light Gradient-Boosting-Machine (LGBM) model for the task of signal classification. It is well known that CNN is capable of learning discriminant features in various domains of signal representations. On the other hand, the LGBM model possess notable advantages such as the feasibility of parallel implementations and the potential of achieving comparable accuracies over various benchmark datasets. For the purpose of leveraging the advantages of both frameworks, we propose three steps to construct the proposed architecture. First, a Mel spectrogram is constructed as a two-dimensional (2-D) three-channel image and employed at the input to a CNN model featuring the squeeze-and-excitation (SE) attention mechanism (i.e., SeResNet) to derive the one-dimensional (1-D) deep feature of the raw signal from the final convolution layer. Secondly, we directly extract a number of 1-D statistical features based on the prior expert knowledge from the source domain of acoustics. Finally, the learned deep features and the extracted statistical features are fused and concatenated to form an input vector for the LGBM model to further improve classification accuracies. The proposed architecture is experimented on the Google Speech Commands Dataset and the Urbansound8K Dataset. Numerical results show that the proposed approach achieves the state-of-the-art accuracies and shows non-negligible performance gains over the standalone schemes.

Low Latency Based Convolutional Recurrent Neural Network Model for Speech Command Recognition

The presented paper proposes a new speech command recognition model for novel engineering applications with limited resources. We built the proposed model with the help of a Convolutional Recurrent Neural Network (CRNN). The use of CRNN instead of Convolutional Neural Network (CNN) helps us to reduce the model parameters and memory requirement as per resource constraints. Furthermore, we insert transmute and curtailment layer between the layers of CRNN. By doing this we further reduce model parameters and float number of operations to half of the CRNN requirement. The proposed model is tested on Google’s speech command dataset. The obtained result shows that the proposed CRNN model requires 1/3 parameters as compared to the CNN model. The number of parameters of the CRNN model is further reduced by 45% and the float numbers of operations between 2% to 12 % in different recognition tasks. The recognition accuracy of the proposed model is 96% on Google’s speech command dataset, and on laboratory recording, its recognition accuracy is 89%.

An adaptive threshold neuron for recurrent spiking neural networks with nanodevice hardware implementation

We propose a Double EXponential Adaptive Threshold (DEXAT) neuron model that improves the performance of neuromorphic Recurrent Spiking Neural Networks (RSNNs) by providing faster convergence, higher accuracy and a flexible long short-term memory. We present a hardware efficient methodology to realize the DEXAT neurons using tightly coupled circuit-device interactions and experimentally demonstrate the DEXAT neuron block using oxide based non-filamentary resistive switching devices. Using experimentally extracted parameters we simulate a full RSNN that achieves a classification accuracy of 96.1% on SMNIST dataset and 91% on Google Speech Commands (GSC) dataset. We also demonstrate full end-to-end real-time inference for speech recognition using real fabricated resistive memory circuit based DEXAT neurons. Finally, we investigate the impact of nanodevice variability and endurance illustrating the robustness of DEXAT based RSNNs.

Building and benchmarking an Arabic Speech Commands dataset for small-footprint keyword spotting

The introduction of the Google Speech Commands dataset accelerated research and resulted in a variety of new deep learning approaches that address keyword spotting tasks. The main contribution of this work is the building of an Arabic Speech Commands dataset, a counterpart to Google’s dataset. Our dataset consists of 12000 instances, collected from 30 contributors, and grouped into 40 keywords. We also report different experiments to benchmark this dataset using classical machine learning and deep learning approaches, the best of which is a Convolutional Neural Network with Mel-Frequency Cepstral Coefficients that achieved an accuracy of ∼98%. Additionally, we point out some key ideas to be considered in such tasks.

EdgeCRNN: an edge-computing oriented model of acoustic feature enhancement for keyword spotting

Keyword Spotting (KWS) is a significant branch of Automatic Speech Recognition (ASR) and has been widely used in edge computing devices. The goal of KWS is to provide high accuracy with a low False Alarm Rate (FAR), while reducing the costs of memory, computation, and latency. However, limited resources are challenging for KWS applications on edge computing devices. Lightweight models and structures for deep learning have achieved good results in the KWS branch while maintaining efficient performances. In this paper, we present a new Convolutional Recurrent Neural Network (CRNN) architecture named EdgeCRNN for edge computing devices. EdgeCRNN, which is based on depthwise separable convolution and residual structure, uses a feature enhanced method. On the Google Speech Commands Dataset, the experimental results depict that EdgeCRNN can test 11.1 audio data per second on Raspberry Pi 3B+, which is 2.2 times than that of Tpool2. Compared with Tpool2, the accuracy of EdgeCRNN reaches 98.05% whilst its performance is also competitive.

Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks

Trojan attacks on deep neural networks (DNNs) exploit a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">backdoor</i> embedded in a DNN model that can hijack any input with an attacker’s chosen signature trigger. Emerging defence mechanisms are mainly designed and validated on vision domain tasks (e.g., image classification) on 2D Convolutional Neural Network (CNN) model architectures; a defence mechanism that is general across vision, text, and audio domain tasks is demanded. This work designs and evaluates a run-time Trojan detection method exploiting <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">STR</u> ong <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">I</u> ntentional <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">P</u> erturbation of inputs that is a multi-domain input-agnostic Trojan detection defence across <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Vi</u> sion, <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</u> ext and <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</u> udio domains—thus termed as STRIP-ViTA. Specifically, STRIP-ViTA is demonstratively independent of not only task domain but also model architectures. Most importantly, unlike other detection mechanisms, it requires neither machine learning expertise nor expensive computational resource, which are the reason behind DNN model outsourcing scenario—one main attack surface of Trojan attack. We have extensively evaluated the performance of STRIP-ViTA over: i) CIFAR10 and GTSRB datasets using 2D CNNs for vision tasks; ii) IMDB and consumer complaint datasets using both LSTM and 1D CNNs for text tasks; and iii) speech command dataset using both 1D CNNs and 2D CNNs for audio tasks. Experimental results based on more than 30 tested Trojaned models (including publicly Trojaned model) corroborate that STRIP-ViTA performs well across all nine architectures and five datasets. Overall, STRIP-ViTA can effectively detect trigger inputs with small false acceptance rate (FAR) with an acceptable preset false rejection rate (FRR). In particular, for vision tasks, we can always achieve a 0 percent FRR and FAR given strong attack success rate always preferred by the attacker. By setting FRR to be 3 percent, average FAR of 1.1 and 3.55 percent are achieved for text and audio tasks, respectively. Moreover, we have evaluated STRIP-ViTA against a number of advanced backdoor attacks and compare its effectiveness with other recent state-of-the-arts.

Guided Generative Adversarial Neural Network for Representation Learning and Audio Generation Using Fewer Labelled Audio Data

The Generation power of Generative Adversarial Neural Networks (GANs) has shown great promise to learn representations from unlabelled data while guided by a small amount of labelled data. We aim to utilise the generation power of GANs to learn Audio Representations. Most existing studies are, however, focused on images. Some studies use GANs for speech generation, but they are conditioned on text or acoustic features, limiting their use for other audio, such as instruments, and even for speech where transcripts are limited. This paper proposes a novel GAN-based model that we named Guided Generative Adversarial Neural Network (GGAN), which can learn powerful representations and generate good-quality samples using a small amount of labelled data as guidance. Experimental results based on a speech [Speech Command Dataset (S09)] and a non-speech [Musical Instrument Sound dataset (Nsyth)] dataset demonstrate that using only 5% of labelled data as guidance, GGAN learns significantly better representations than the state-of-the-art models.

FantastIC4: A Hardware-Software Co-Design Approach for Efficiently Running 4Bit-Compact Multilayer Perceptrons

With the growing demand for deploying Deep Learning models to the “edge”, it is paramount to develop techniques that allow to execute state-of-the-art models within very tight and limited resource constraints. In this work we propose a software-hardware optimization paradigm for obtaining a highly efficient execution engine of deep neural networks (DNNs) that are based on fully-connected layers. The work's approach is centred around compression as a means for reducing the area as well as power requirements of, concretely, multilayer perceptrons (MLPs) with high predictive performances. Firstly, we design a novel hardware architecture named FantastIC4, which (1) supports the efficient on-chip execution of multiple compact representations of fully-connected layers and (2) minimizes the required number of multipliers for inference down to only 4 (thus the name). Moreover, in order to make the models amenable for efficient execution on FantastIC4, we introduce a novel entropy-constrained training method that renders them to be robust to 4bit quantization and highly compressible in size simultaneously. The experimental results show that we can achieve throughputs of 2.45 TOPS with a total power consumption of 3.6W on a Virtual Ultrascale FPGA XCVU440 device implementation, and achieve a total power efficiency of 20.17 TOPS/W on a 22nm process ASIC version. When compared to other state-of-the-art accelerators designed for the Google Speech Command (GSC) dataset, FantastIC4 is better by 51× in terms of throughput and 145× in terms of area efficiency (GOPS/mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ).

A Novel Loss Function and Training Strategy for Noise-Robust Keyword Spotting

The development of keyword spotting (KWS) systems that are accurate in noisy conditions remains a challenge. Towards this goal, in this paper we propose a novel training strategy relying on multi-condition training for noise-robust KWS. By this strategy, we think of the state-of-the-art KWS models as the composition of a keyword embedding extractor and a linear classifier that are successively trained. To train the keyword embedding extractor, we also propose a new (C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N,2</sub> +1)-pair loss function extending the concept behind related loss functions like triplet and N-pair losses to reach larger inter-class and smaller intra-class variation. Experimental results on a noisy version of the Google Speech Commands Dataset show that our proposal achieves around 12% KWS accuracy relative improvement with respect to standard end-to-end multi-condition training when speech is distorted by unseen noises. This performance improvement is achieved without increasing the computational complexity of the KWS model.

A 510-nW Wake-Up Keyword-Spotting Chip Using Serial-FFT-Based MFCC and Binarized Depthwise Separable CNN in 28-nm CMOS

We propose a sub-μW always-ON keyword spotting (μKWS) chip for audio wake-up systems. It is mainly composed of a neural network (NN) and a feature extraction (FE) circuit. For significantly reducing the memory footprint and computational load, four techniques are used to achieve ultralow-power consumption: 1) a serial-FFT-based Mel-frequency cepstrum coefficient circuit is designed for FE, instead of the common parallel FFT. 2) A small-sized binarized depthwise separable convolutional NN (DSCNN) is designed as the classifier. 3) A framewise incremental computation technique is devised in contrast to the conventional whole-word processing. 4) Reduced computation allows a low system clock frequency, which enables near-threshold voltage operation, and low leakage memory blocks are designed to minimize the leakage power. Implemented in 28-nm CMOS technology, this μKWS consumes 0.51 μW at a 40-kHz frequency and a 0.41-V supply, with an area of 0.23 mm2. Using the Google speech command data set, 97.3% accuracy is reached for a one-word KWS task and 94.6% for a two-word task.

UltraTrail: A Configurable Ultralow-Power TC-ResNet AI Accelerator for Efficient Keyword Spotting

Recent advances in machine learning show the superior behavior of temporal convolutional networks (TCNs) and especially their combination with residual networks (TC-ResNet) for intelligent sensor signal processing in comparison to classical CNNs and LSTMs. In this article, we propose UltraTrail, a configurable, ultralow-power TC-ResNet AI accelerator for sensor signal processing and its application to efficient keyword spotting (KWS). Following a strict hardware/model co-design approach, we have derived an optimized low-power hardware architecture for generalized TC-ResNet topologies consisting of a configurable array of processing elements and a distributed memory with dynamic content reallocation. We additionally extend the network with conditional computing to reduce the number of operations during inference and to provide the possibility for power-gating. The final accelerator implementation in Globalfoundries' 22FDX technology achieves a power consumption of 8.2 μW for the task of always-on KWS meeting the real-time requirement of 100 ms per inference with an accuracy of 93% on the Google Speech Command Dataset.

Improving approximate neural networks for perception tasks through specialized optimization

Approximate Computing has been proven successful in reducing the energy consumption of Deep Neural Networks (DNNs) implemented in embedded systems. For efficient DNN approximation at software and hardware levels, a specialized simulation environment and optimization methodology are required, to reduce execution and optimization times, as well as to maximize energy savings. Traditional frameworks for cross-layer approximate computation of DNNs are generally built only for simulation of convolutional and fully-connected layers, limiting the DNN types to be optimized through approximations. In this work, we present a specialized simulation environment for approximate DNNs, which allows for optimization of several DNN architectures built with more complex DNN layers such as depthwise convolutions and Recurrent Neural Units (RNNs) for time series processing. Low execution time overhead is achieved hereby through efficient GPU acceleration. Additionally, we deliver an analysis of approximate DNN and RNN robustness against quantization noise and different approximation levels. Finally, through specialized approximate retraining, we achieve promising energy savings and negligible accuracy losses with highly complex DNNs for image classification with ImageNet, such as MobileNet, and RNNs for keyword spotting with the Speech Commands Dataset.

Incorporating Noise Robustness in Speech Command Recognition by Noise Augmentation of Training Data.

The advent of new devices, technology, machine learning techniques, and the availability of free large speech corpora results in rapid and accurate speech recognition. In the last two decades, extensive research has been initiated by researchers and different organizations to experiment with new techniques and their applications in speech processing systems. There are several speech command based applications in the area of robotics, IoT, ubiquitous computing, and different human-computer interfaces. Various researchers have worked on enhancing the efficiency of speech command based systems and used the speech command dataset. However, none of them catered to noise in the same. Noise is one of the major challenges in any speech recognition system, as real-time noise is a very versatile and unavoidable factor that affects the performance of speech recognition systems, particularly those that have not learned the noise efficiently. We thoroughly analyse the latest trends in speech recognition and evaluate the speech command dataset on different machine learning based and deep learning based techniques. A novel technique is proposed for noise robustness by augmenting noise in training data. Our proposed technique is tested on clean and noisy data along with locally generated data and achieves much better results than existing state-of-the-art techniques, thus setting a new benchmark.

TimeScaleNet: A Multiresolution Approach for Raw Audio Recognition Using Learnable Biquadratic IIR Filters and Residual Networks of Depthwise-Separable One-Dimensional Atrous Convolutions

In this paper, we show the benefit of a multi-resolution approach that allows us to encode the relevant information contained in unprocessed time-domain acoustic signals. TimeScaleNet aims at learning an efficient representation of a sound, by learning time dependencies both at the sample level and at the frame level. The proposed approach allows us to improve the interpretability of the learning scheme, by unifying advanced deep learning and signal processing techniques. In particular, TimeScaleNet's architecture introduces a new form of recurrent neural layer, which is directly inspired from digital infinite impulse-response (IIR) signal processing. This layer acts as a learnable passband biquadratic digital IIR filterbank. The learnable filterbank allows us to build a time-frequency-like feature map that self-adapts to the specific recognition task and dataset, with a large receptive field and very few learnable parameters. The obtained frame-level feature map is then processed using a residual network of depthwise separable atrous convolutions. This second scale of analysis aims at efficiently encoding relationships between the time fluctuations at the frame timescale, in different learnt pooled frequency bands, in the range of [20 ms ; 200 ms]. TimeScaleNet is tested both using the Speech Commands Dataset and the ESC-10 Dataset. We report a high mean accuracy of $94.87 \pm 0.24 \%$ (macro averaged F1-score : $94.9 \pm 0.24 \%$ ) for speech recognition, and a rather moderate accuracy of $69.71 \pm 1.91 \%$ (macro averaged F1-score : $70.14 \pm 1.57 \%$ ) for the environmental sound classification task.