Search

This paper introduces a novel reference-free (RF) audio quality metric called the RF-Generative Machine Listener (RF-GML), designed to evaluate coded mono, stereo, and binaural audio at a 48 kHz sample rate. RF-GML leverages transfer learning from a state-of-the-art full-reference (FR) Generative Machine Listener (GML) with minimal architectural modifications. The term "generative" refers to the model's ability to generate an arbitrary number of simulated listening scores. Unlike existing RF models, RF-GML accurately predicts subjective quality scores across diverse content types and codecs. Extensive evaluations demonstrate its superiority in rating unencoded audio and distinguishing different levels of coding artifacts. RF-GML's performance and versatility make it a valuable tool for coded audio quality assessment and monitoring in various applications, all without the need for a reference signal., Comment: Pre-review version submitted to ICASSP 2025

API call generation is the cornerstone of large language models' tool-using ability that provides access to the larger world. However, existing supervised and in-context learning approaches suffer from high training costs, poor data efficiency, and generated API calls that can be unfaithful to the API documentation and the user's request. To address these limitations, we propose an output-side optimization approach called FANTASE. Two of the unique contributions of FANTASE are its State-Tracked Constrained Decoding (SCD) and Reranking components. SCD dynamically incorporates appropriate API constraints in the form of Token Search Trie for efficient and guaranteed generation faithfulness with respect to the API documentation. The Reranking component efficiently brings in the supervised signal by leveraging a lightweight model as the discriminator to rerank the beam-searched candidate generations of the large language model. We demonstrate the superior performance of FANTASE in API call generation accuracy, inference efficiency, and context efficiency with DSTC8 and API Bank datasets.

While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected to communicate with multiple users simultaneously who make decisions collaboratively. To facilitate development of such systems, we release the Multi-User MultiWOZ dataset: task-oriented dialogues among two users and one agent. To collect this dataset, each user utterance from MultiWOZ 2.2 was replaced with a small chat between two users that is semantically and pragmatically consistent with the original user utterance, thus resulting in the same dialogue state and system response. These dialogues reflect interesting dynamics of collaborative decision-making in task-oriented scenarios, e.g., social chatter and deliberation. Supported by this data, we propose the novel task of multi-user contextual query rewriting: to rewrite a task-oriented chat between two users as a concise task-oriented query that retains only task-relevant information and that is directly consumable by the dialogue system. We demonstrate that in multi-user dialogues, using predicted rewrites substantially improves dialogue state tracking without modifying existing dialogue systems that are trained for single-user dialogues. Further, this method surpasses training a medium-sized model directly on multi-user dialogues and generalizes to unseen domains., Comment: To Appear in EMNLP-Findings 2023

We show how a neural network can be trained on individual intrusive listening test scores to predict a distribution of scores for each pair of reference and coded input stereo or binaural signals. We nickname this method the Generative Machine Listener (GML), as it is capable of generating an arbitrary amount of simulated listening test data. Compared to a baseline system using regression over mean scores, we observe lower outlier ratios (OR) for the mean score predictions, and obtain easy access to the prediction of confidence intervals (CI). The introduction of data augmentation techniques from the image domain results in a significant increase in CI prediction accuracy as well as Pearson and Spearman rank correlation of mean scores., Comment: Accepted to 155th Audio Engineering Society (AES) Convention, New York, NY, USA, October 2023

Video Multimethod Assessment Fusion (VMAF) [1], [2], [3] is a popular tool in the industry for measuring coded video quality. In this study, we propose an auditory-inspired frontend in existing VMAF for creating videos of reference and coded spectrograms, and extended VMAF for measuring coded audio quality. We name our system AudioVMAF. We demonstrate that image replication is capable of further enhancing prediction accuracy, especially when band-limited anchors are present. The proposed method significantly outperforms all existing visual quality features repurposed for audio, and even demonstrates a significant overall improvement of 7.8% and 2.0% of Pearson and Spearman rank correlation coefficient, respectively, over a dedicated audio quality metric (ViSQOL-v3 [4]) also inspired from the image domain., Comment: Accepted to 155th Audio Engineering Society (AES), New York, NY, USA, October 2023

Automatic coded audio quality predictors are typically designed for evaluating single channels without considering any spatial aspects. With InSE-NET [1], we demonstrated mimicking a state-of-the-art coded audio quality metric (ViSQOL-v3 [2]) with deep neural networks (DNN) and subsequently improving it - completely with programmatically generated data. In this study, we take steps towards building a DNN-based coded stereo audio quality predictor and we propose an extension of the InSE-NET for handling stereo signals. The design considers stereo/spatial aspects by conditioning the model with left, right, mid, and side channels; and we name our model Stereo InSE-NET. By transferring selected weights from the pre-trained mono InSE-NET and retraining with both real and synthetically augmented listening tests, we demonstrate a significant improvement of 12% and 6% of Pearson and Spearman Rank correlation coefficient, respectively, over the latest ViSQOL-v3 [3]., Comment: Accepted to 153rd Audio Engineering Society (AES), New York, NY, USA, October 2022

Most popular goal-oriented dialogue agents are capable of understanding the conversational context. However, with the surge of virtual assistants with screen, the next generation of agents are required to also understand screen context in order to provide a proper interactive experience, and better understand users' goals. In this paper, we propose a novel multimodal conversational framework, where the dialogue agent's next action and their arguments are derived jointly conditioned both on the conversational and the visual context. Specifically, we propose a new model, that can reason over the visual context within a conversation and populate API arguments with visual entities given the user query. Our model can recognize visual features such as color and shape as well as the metadata based features such as price or star rating associated with a visual entity. In order to train our model, due to a lack of suitable multimodal conversational datasets, we also propose a novel multimodal dialog simulator to generate synthetic data and also collect realistic user data from MTurk to improve model robustness. The proposed model achieves a reasonable 85% model accuracy, without high inference latency. We also demonstrate the proposed approach in a prototypical furniture shopping experience for a multimodal virtual assistant.

Automatic coded audio quality assessment is an important task whose progress is hampered by the scarcity of human annotations, poor generalization to unseen codecs, bitrates, content-types, and a lack of flexibility of existing approaches. One of the typical human-perception-related metrics, ViSQOL v3 (ViV3), has been proven to provide a high correlation to the quality scores rated by humans. In this study, we take steps to tackle problems of predicting coded audio quality by completely utilizing programmatically generated data that is informed with expert domain knowledge. We propose a learnable neural network, entitled InSE-NET, with a backbone of Inception and Squeeze-and-Excitation modules to assess the perceived quality of coded audio at a 48kHz sample rate. We demonstrate that synthetic data augmentation is capable of enhancing the prediction. Our proposed method is intrusive, i.e. it requires Gammatone spectrograms of unencoded reference signals. Besides a comparable performance to ViV3, our approach provides a more robust prediction towards higher bitrates., Comment: Accepted to 151st Audio Engineering Society (AES), Las Vegas, NV, USA, October 2021

Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Training each component requires annotations which are hard to obtain for every new domain, limiting scalability of such systems. Similarly, rule-based dialogue systems require extensive writing and maintenance of rules and do not scale either. End-to-End dialogue systems, on the other hand, do not require module-specific annotations but need a large amount of data for training. To overcome these problems, in this demo, we present Alexa Conversations, a new approach for building goal-oriented dialogue systems that is scalable, extensible as well as data efficient. The components of this system are trained in a data-driven manner, but instead of collecting annotated conversations for training, we generate them using a novel dialogue simulator based on a few seed dialogues and specifications of APIs and entities provided by the developer. Our approach provides out-of-the-box support for natural conversational phenomena like entity sharing across turns or users changing their mind during conversation without requiring developers to provide any such dialogue flows. We exemplify our approach using a simple pizza ordering task and showcase its value in reducing the developer burden for creating a robust experience. Finally, we evaluate our system using a typical movie ticket booking task and show that the dialogue simulator is an essential component of the system that leads to over $50\%$ improvement in turn-level action signature prediction accuracy.

Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding, state tracking and action prediction (policy learning). These models are trained through a combination of supervised or reinforcement learning methods and therefore require collection of labeled domain specific datasets. However, collecting annotated datasets with language and dialog-flow variations is expensive, time-consuming and scales poorly due to human involvement. In this paper, we propose an approach for automatically creating a large corpus of annotated dialogs from a few thoroughly annotated sample dialogs and the dialog schema. Our approach includes a novel goal-sampling technique for sampling plausible user goals and a dialog simulation technique that uses heuristic interplay between the user and the system (Alexa), where the user tries to achieve the sampled goal. We validate our approach by generating data and training three different downstream conversational ML models. We achieve 18 ? 50% relative accuracy improvements on a held-out test set compared to a baseline dialog generation approach that only samples natural language and entity value variations from existing catalogs but does not generate any novel dialog flow variations. We also qualitatively establish that the proposed approach is better than the baseline. Moreover, several different conversational experiences have been built using this method, which enables customers to have a wide variety of conversations with Alexa., Comment: To be presented at Human in the Loop Dialogue Systems Workshop, NeurIPS 2020

Audio codecs are typically transform-domain based and efficiently code stationary audio signals, but they struggle with speech and signals containing dense transient events such as applause. Specifically, with these two classes of signals as examples, we demonstrate a technique for restoring audio from coding noise based on generative adversarial networks (GAN). A primary advantage of the proposed GAN-based coded audio enhancer is that the method operates end-to-end directly on decoded audio samples, eliminating the need to design any manually-crafted frontend. Furthermore, the enhancement approach described in this paper can improve the sound quality of low-bit rate coded audio without any modifications to the existent standard-compliant encoders. Subjective tests illustrate that the proposed enhancer improves the quality of speech and difficult to code applause excerpts significantly., Comment: Accepted to 45th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 04-08 May 2020

Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep generative models such as WaveNet and SampleRNN have been used as speech vocoders to scale up the perceptual quality of the reconstructed signals without increasing the coding rate. However, such models suffer from a very slow signal generation mechanism due to their sample-by-sample modelling approach. In this work, we introduce a new methodology for neural speech vocoding based on generative adversarial networks (GANs). A fake speech signal is generated from a very compressed representation of the glottal excitation using conditional GANs as a deep generative model. This fake speech is then refined using the LPC parameters of the original speech signal to obtain a natural reconstruction. The reconstructed speech waveforms based on this approach show a higher perceptual quality than the classical vocoder counterparts according to subjective and objective evaluation scores for a dataset of 30 male and female speakers. Moreover, the usage of GANs enables to generate signals in one-shot compared to autoregressive generative models. This makes GANs promising for exploration to implement high-quality neural vocoders., Comment: Accepted to Interspeech 2019

E-commerce companies such as Amazon, Alibaba and Flipkart process billions of orders every year. However, these orders represent only a small fraction of all plausible orders. Exploring the space of all plausible orders could help us better understand the relationships between the various entities in an e-commerce ecosystem, namely the customers and the products they purchase. In this paper, we propose a Generative Adversarial Network (GAN) for orders made in e-commerce websites. Once trained, the generator in the GAN could generate any number of plausible orders. Our contributions include: (a) creating a dense and low-dimensional representation of e-commerce orders, (b) train an ecommerceGAN (ecGAN) with real orders to show the feasibility of the proposed paradigm, and (c) train an ecommerce-conditional-GAN (ec^2GAN) to generate the plausible orders involving a particular product. We propose several qualitative methods to evaluate ecGAN and demonstrate its effectiveness. The ec^2GAN is used for various kinds of characterization of possible orders involving a product that has just been introduced into the e-commerce system. The proposed approach ec^2GAN performs significantly better than the baseline in most of the scenarios.

E-commerce websites such as Amazon, Alibaba, Flipkart, and Walmart sell billions of products. Machine learning (ML) algorithms involving products are often used to improve the customer experience and increase revenue, e.g., product similarity, recommendation, and price estimation. The products are required to be represented as features before training an ML algorithm. In this paper, we propose an approach called MRNet-Product2Vec for creating generic embeddings of products within an e-commerce ecosystem. We learn a dense and low-dimensional embedding where a diverse set of signals related to a product are explicitly injected into its representation. We train a Discriminative Multi-task Bidirectional Recurrent Neural Network (RNN), where the input is a product title fed through a Bidirectional RNN and at the output, product labels corresponding to fifteen different tasks are predicted. The task set includes several intrinsic characteristics about a product such as price, weight, size, color, popularity, and material. We evaluate the proposed embedding quantitatively and qualitatively. We demonstrate that they are almost as good as sparse and extremely high-dimensional TF-IDF representation in spite of having less than 3% of the TF-IDF dimension. We also use a multimodal autoencoder for comparing products from different language-regions and show preliminary yet promising qualitative results., Comment: Published in ECML-PKDD 2017 (Applied Data Science Track)

Given an image, we would like to learn to detect objects belonging to particular object categories. Common object detection methods train on large annotated datasets which are annotated in terms of bounding boxes that contain the object of interest. Previous works on object detection model the problem as a structured regression problem which ranks the correct bounding boxes more than the background ones. In this paper we develop algorithms which actively obtain annotations from human annotators for a small set of images, instead of all images, thereby reducing the annotation effort. Towards this goal, we make the following contributions: 1. We develop a principled version space based active learning method that solves for object detection as a structured prediction problem in a weakly supervised setting 2. We also propose two variants of the margin sampling strategy 3. We analyse the results on standard object detection benchmarks that show that with only 20% of the data we can obtain more than 95% of the localization accuracy of full supervision. Our methods outperform random sampling and the classical uncertainty-based active learning algorithms like entropy

Data generated from real world events are usually temporal and contain multimodal information such as audio, visual, depth, sensor etc. which are required to be intelligently combined for classification tasks. In this paper, we propose a novel generalized deep neural network architecture where temporal streams from multiple modalities are combined. There are total M+1 (M is the number of modalities) components in the proposed network. The first component is a novel temporally hybrid Recurrent Neural Network (RNN) that exploits the complimentary nature of the multimodal temporal information by allowing the network to learn both modality specific temporal dynamics as well as the dynamics in a multimodal feature space. M additional components are added to the network which extract discriminative but non-temporal cues from each modality. Finally, the predictions from all of these components are linearly combined using a set of automatically learned weights. We perform exhaustive experiments on three different datasets spanning four modalities. The proposed network is relatively 3.5%, 5.7% and 2% better than the best performing temporal multimodal baseline for UCF-101, CCV and Multimodal Gesture datasets respectively., Comment: To appear in ECCV workshop on Computer Vision for Audio-Visual Media, 2016

Typical textual descriptions that accompany online videos are 'weak': i.e., they mention the main concepts in the video but not their corresponding spatio-temporal locations. The concepts in the description are typically heterogeneous (e.g., objects, persons, actions). Certain location constraints on these concepts can also be inferred from the description. The goal of this paper is to present a generalization of the Indian Buffet Process (IBP) that can (a) systematically incorporate heterogeneous concepts in an integrated framework, and (b) enforce location constraints, for efficient classification and localization of the concepts in the videos. Finally, we develop posterior inference for the proposed formulation using mean-field variational approximation. Comparative evaluations on the Casablanca and the A2D datasets show that the proposed approach significantly outperforms other state-of-the-art techniques: 24% relative improvement for pairwise concept classification in the Casablanca dataset and 9% relative improvement for localization in the A2D dataset as compared to the most competitive baseline., Comment: To appear at ECCV 2016