What exactly is artificial intelligence (AI)? The replication of human intellectual processes by machines, particularly computer systems, is known as artificial intelligence. Expert systems, natural language processing, speech recognition, and machine vision are examples of AI applications. How does artificial intelligence work? As the excitement surrounding AI has grown, businesses have been scurrying to showcase how their goods and services include AI. What they call AI is frequently just one component of AI, such as machine learning. AI requires specialized hardware and software to write and train machine learning algorithms.

It helps us reduce the requirement of manually annotated training data. Spoken Language Understanding (SLU) systems In this work, we adapt an E2E ASR model to that extract the intent from a spoken utterance are build an E2E S2I model for Flipkart's on-call customer integral in various voicebot applications such as support. An overview of our contributions is automated on-call customer support, voice assistants, as follows: home or vehicle automation systems, etc. The extracted intent triggers a standard operating An efficient extension of end-to-end BiLSTM procedure (SOP) as defined by the respective application, and CTC based ASR models for S2I task on e.g. an e-commerce customer query "I want noisy datasets; to return my phone" maps to "Return" intent which A demonstration of how the idea can outperform triggers the SOP to help the user with returns. It conventional pipeline in customer support helps us reduce the reliance on human agents and voicebot in real-world settings; provide faster resolutions. More elaborate examples are shown in Table 4. An investigation on how ASR pre-training, Conventionally, such systems consist of two offline active learning and pseudo labelling components - an Automatic Speech Recognition reduce data labeling requirements for S2I.

In visual question answering (VQA), a machine must answer a question given an associated image. Recently, accessibility researchers have explored whether VQA can be deployed in a real-world setting where users with visual impairments learn about their environment by capturing their visual surroundings and asking questions. However, most of the existing benchmarking datasets for VQA focus on machine "understanding" and it remains unclear how progress on those datasets corresponds to improvements in this real-world use case. We aim to answer this question by evaluating discrepancies between machine "understanding" datasets (VQA-v2) and accessibility datasets (VizWiz) by evaluating a variety of VQA models. Based on our findings, we discuss opportunities and challenges in VQA for accessibility and suggest directions for future work.

Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing. Recent work shows that the attention mechanism inside Transformer may not be necessary, both convolutional neural networks and multi-layer perceptron based models have also been investigated as Transformer alternatives. In this paper, we consider a graph recurrent network for language model pre-training, which builds a graph structure for each sequence with local token-level communications, together with a sentence-level representation decoupled from other tokens. The original model performs well in domain-specific text classification under supervised training, however, its potential in learning transfer knowledge by self-supervised way has not been fully exploited. We fill this gap by optimizing the architecture and verifying its effectiveness in more general language understanding tasks, for both English and Chinese languages. As for model efficiency, instead of the quadratic complexity in Transformer-based models, our model has linear complexity and performs more efficiently during inference. Moreover, we find that our model can generate more diverse outputs with less contextualized feature redundancy than existing attention-based models.

Recent works have shown the capability of deep generative models to tackle general audio synthesis from a single label, producing a variety of impulsive, tonal, and environmental sounds. Such models operate on band-limited signals and, as a result of an autoregressive approach, they are typically conformed by pre-trained latent encoders and/or several cascaded modules. In this work, we propose a diffusion-based generative model for general audio synthesis, named DAG, which deals with full-band signals end-to-end in the waveform domain. Results show the superiority of DAG over existing label-conditioned generators in terms of both quality and diversity. More specifically, when compared to the state of the art, the band-limited and full-band versions of DAG achieve relative improvements that go up to 40 and 65%, respectively. We believe DAG is flexible enough to accommodate different conditioning schemas while providing good quality synthesis.

Class imbalance has a detrimental effect on the predictive performance of most supervised learning algorithms as the imbalanced distribution can lead to a bias preferring the majority class. To solve this problem, we propose a Supervised Contrastive Learning (SCL) method with Tree-structured Parzen Estimator (TPE) technique for imbalanced tabular datasets. Contrastive learning (CL) can extract the information hidden in data even without labels and has shown some potential for imbalanced learning tasks. SCL further considers the label information based on CL, which also addresses the insufficient data augmentation techniques of tabular data. Therefore, in this work, we propose to use SCL to learn a discriminative representation of imbalanced tabular data. Additionally, the hyper-parameter temperature of SCL has a decisive influence on the performance and is difficult to tune. We introduce TPE, a well-known Bayesian optimization technique, to automatically select the best temperature. Experiments are conducted on both binary and multi-class imbalanced tabular datasets. As shown in the results obtained, TPE outperforms three other hyper-parameter optimization (HPO) methods such as grid search, random search, and genetic algorithm. More importantly, the proposed SCL-TPE method achieves much-improved performance compared with the state-of-the-art methods.

Self-Supervised Learning (SSL) from speech data has produced models that have achieved remarkable performance in many tasks, and that are known to implicitly represent many aspects of information latently present in speech signals. However, relatively little is known about the suitability of such models for prosody-related tasks or the extent to which they encode prosodic information. We present a new evaluation framework, SUPERB-prosody, consisting of three prosody-related downstream tasks and two pseudo tasks. We find that 13 of the 15 SSL models outperformed the baseline on all the prosody-related tasks. We also show good performance on two pseudo tasks: prosody reconstruction and future prosody prediction. We further analyze the layerwise contributions of the SSL models. Overall we conclude that SSL speech models are highly effective for prosody-related tasks.

Despite tremendous progress in automatic summarization, state-of-the-art methods are predominantly trained to excel in summarizing short newswire articles, or documents with strong layout biases such as scientific articles or government reports. Efficient techniques to summarize financial documents, including facts and figures, have largely been unexplored, majorly due to the unavailability of suitable datasets. In this work, we present ECTSum, a new dataset with transcripts of earnings calls (ECTs), hosted by publicly traded companies, as documents, and short experts-written telegram-style bullet point summaries derived from corresponding Reuters articles. ECTs are long unstructured documents without any prescribed length limit or format. We benchmark our dataset with state-of-the-art summarizers across various metrics evaluating the content quality and factual consistency of the generated summaries. Finally, we present a simple-yet-effective approach, ECT-BPS, to generate a set of bullet points that precisely capture the important facts discussed in the calls.

The goal of speech emotion recognition (SER) is to identify the emotional aspects of speech. The SER challenge for Brazilian Portuguese speech was proposed with short snippets of Portuguese which are classified as neutral, non-neutral female and non-neutral male according to paralinguistic elements (laughing, crying, etc). This dataset contains about $50$ minutes of Brazilian Portuguese speech. As the dataset leans on the small side, we investigate whether a combination of transfer learning and data augmentation techniques can produce positive results. Thus, by combining a data augmentation technique called SpecAugment, with the use of Pretrained Audio Neural Networks (PANNs) for transfer learning we are able to obtain interesting results. The PANNs (CNN6, CNN10 and CNN14) are pretrained on a large dataset called AudioSet containing more than $5000$ hours of audio. They were finetuned on the SER dataset and the best performing model (CNN10) on the validation set was submitted to the challenge, achieving an $F1$ score of $0.73$ up from $0.54$ from the baselines provided by the challenge. Moreover, we also tested the use of Transformer neural architecture, pretrained on about $600$ hours of Brazilian Portuguese audio data. Transformers, as well as more complex models of PANNs (CNN14), fail to generalize to the test set in the SER dataset and do not beat the baseline. Considering the limitation of the dataset sizes, currently the best approach for SER is using PANNs (specifically, CNN6 and CNN10).

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable streaming. We directly compare global-attention and different segmental-attention modeling variants. We develop and compare two separate time-synchronous decoders, one specifically taking the segmental nature into account, yielding further improvements. Using time-synchronous decoding for segmental models is novel and a step towards streaming applications. Our experiments show the importance of a length model to predict the segment boundaries. The final best segmental-attention model using segmental decoding performs better than global-attention, in contrast to other monotonic attention approaches in the literature. Further, we observe that the segmental model generalizes much better to long sequences of up to several minutes.