Search

This paper delves into the emerging field of face-based voice conversion, leveraging the unique relationship between an individual's facial features and their vocal characteristics. We present a novel face-based voice conversion framework that particularly utilizes the average fundamental frequency of the target speaker, derived solely from their facial images. Through extensive analysis, our framework demonstrates superior speech generation quality and the ability to align facial features with voice characteristics, including tracking of the target speaker's fundamental frequency., Comment: Interspeech 2024

While a number of knowledge graph representation learning (KGRL) methods have been proposed over the past decade, very few theoretical analyses have been conducted on them. In this paper, we present the first PAC-Bayesian generalization bounds for KGRL methods. To analyze a broad class of KGRL models, we propose a generic framework named ReED (Relation-aware Encoder-Decoder), which consists of a relation-aware message passing encoder and a triplet classification decoder. Our ReED framework can express at least 15 different existing KGRL models, including not only graph neural network-based models such as R-GCN and CompGCN but also shallow-architecture models such as RotatE and ANALOGY. Our generalization bounds for the ReED framework provide theoretical grounds for the commonly used tricks in KGRL, e.g., parameter-sharing and weight normalization schemes, and guide desirable design choices for practical KGRL methods. We empirically show that the critical factors in our generalization bounds can explain actual generalization errors on three real-world knowledge graphs., Comment: 32 pages, 3 figures, 4 tables, The 41st International Conference on Machine Learning (ICML 2024)

Inductive knowledge graph completion has been considered as the task of predicting missing triplets between new entities that are not observed during training. While most inductive knowledge graph completion methods assume that all entities can be new, they do not allow new relations to appear at inference time. This restriction prohibits the existing methods from appropriately handling real-world knowledge graphs where new entities accompany new relations. In this paper, we propose an INductive knowledge GRAph eMbedding method, InGram, that can generate embeddings of new relations as well as new entities at inference time. Given a knowledge graph, we define a relation graph as a weighted graph consisting of relations and the affinity weights between them. Based on the relation graph and the original knowledge graph, InGram learns how to aggregate neighboring embeddings to generate relation and entity embeddings using an attention mechanism. Experimental results show that InGram outperforms 14 different state-of-the-art methods on varied inductive learning scenarios., Comment: 14 pages, 4 figures, 6 tables, 40th International Conference on Machine Learning (ICML 2023)

A hyper-relational knowledge graph has been recently studied where a triplet is associated with a set of qualifiers; a qualifier is composed of a relation and an entity, providing auxiliary information for a triplet. While existing hyper-relational knowledge graph embedding methods assume that the entities are discrete objects, some information should be represented using numeric values, e.g., (J.R.R., was born in, 1892). Also, a triplet (J.R.R., educated at, Oxford Univ.) can be associated with a qualifier such as (start time, 1911). In this paper, we propose a unified framework named HyNT that learns representations of a hyper-relational knowledge graph containing numeric literals in either triplets or qualifiers. We define a context transformer and a prediction transformer to learn the representations based not only on the correlations between a triplet and its qualifiers but also on the numeric information. By learning compact representations of triplets and qualifiers and feeding them into the transformers, we reduce the computation cost of using transformers. Using HyNT, we can predict missing numeric values in addition to missing entities or relations in a hyper-relational knowledge graph. Experimental results show that HyNT significantly outperforms state-of-the-art methods on real-world datasets., Comment: 11 pages, 5 figures, 12 tables. 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023). This version includes updated results after fixing a bug

Ensuring performance robustness for a variety of situations that can occur in real-world environments is one of the challenging tasks in sound event classification. One of the unpredictable and detrimental factors in performance, especially in indoor environments, is reverberation. To alleviate this problem, we propose a conditioning method that provides room impulse response (RIR) information to help the network become less sensitive to environmental information and focus on classifying the desired sound. Experimental results show that the proposed method successfully reduced performance degradation caused by the reverberation of the room. In particular, our proposed method works even with similar RIR that can be inferred from the room type rather than the exact one, which has the advantage of potentially being used in real-world applications., Comment: 5 pages, 3 figures, In Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

We describe Howl, an open-source wake word detection toolkit with native support for open speech datasets, like Mozilla Common Voice and Google Speech Commands. We report benchmark results on Speech Commands and our own freely available wake word detection dataset, built from MCV. We operationalize our system for Firefox Voice, a plugin enabling speech interactivity for the Firefox web browser. Howl represents, to the best of our knowledge, the first fully productionized yet open-source wake word detection toolkit with a web browser deployment target. Our codebase is at https://github.com/castorini/howl., Comment: The first two authors contributed equally

In natural language processing, a recently popular line of work explores how to best report the experimental results of neural networks. One exemplar publication, titled "Show Your Work: Improved Reporting of Experimental Results," advocates for reporting the expected validation effectiveness of the best-tuned model, with respect to the computational budget. In the present work, we critically examine this paper. As far as statistical generalizability is concerned, we find unspoken pitfalls and caveats with this approach. We analytically show that their estimator is biased and uses error-prone assumptions. We find that the estimator favors negative errors and yields poor bootstrapped confidence intervals. We derive an unbiased alternative and bolster our claims with empirical evidence from statistical simulation. Our codebase is at http://github.com/castorini/meanmax., Comment: Accepted to ACL 2020

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We propose a simple but effective method, DeeBERT, to accelerate BERT inference. Our approach allows samples to exit earlier without passing through the entire model. Experiments show that DeeBERT is able to save up to ~40% inference time with minimal degradation in model quality. Further analyses show different behaviors in the BERT transformer layers and also reveal their redundancy. Our work provides new ideas to efficiently apply deep transformer-based models to downstream tasks. Code is available at https://github.com/castorini/DeeBERT., Comment: Accepted at ACL 2020

Pretrained transformer-based language models have achieved state of the art across countless tasks in natural language processing. These models are highly expressive, comprising at least a hundred million parameters and a dozen layers. Recent evidence suggests that only a few of the final layers need to be fine-tuned for high quality on downstream tasks. Naturally, a subsequent research question is, "how many of the last layers do we need to fine-tune?" In this paper, we precisely answer this question. We examine two recent pretrained language models, BERT and RoBERTa, across standard tasks in textual entailment, semantic similarity, sentiment analysis, and linguistic acceptability. We vary the number of final layers that are fine-tuned, then study the resulting change in task-specific effectiveness. We show that only a fourth of the final layers need to be fine-tuned to achieve 90% of the original quality. Surprisingly, we also find that fine-tuning all layers does not always help., Comment: 5 pages

In this paper, we propose a novel method that exploits music listening log data for general-purpose music feature extraction. Despite the wealth of information available in the log data of user-item interactions, it has been mostly used for collaborative filtering to find similar items or users and was not fully investigated for content-based music applications. We resolve this problem by extending intra-domain knowledge distillation to cross-domain: i.e., by transferring knowledge obtained from the user-item domain to the music content domain. The proposed system first trains the model that estimates log information from the audio contents; then it uses the model to improve other task-specific models. The experiments on various music classification and regression tasks show that the proposed method successfully improves the performances of the task-specific models., Comment: 5 pages, 4 figures, and 1 table. Accepted paper at the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2019

Used for simple commands recognition on devices from smart routers to mobile phones, keyword spotting systems are everywhere. Ubiquitous as well are web applications, which have grown in popularity and complexity over the last decade with significant improvements in usability under cross-platform conditions. However, despite their obvious advantage in natural language interaction, voice-enabled web applications are still far and few between. In this work, we attempt to bridge this gap by bringing keyword spotting capabilities directly into the browser. To our knowledge, we are the first to demonstrate a fully-functional implementation of convolutional neural networks in pure JavaScript that runs in any standards-compliant browser. We also apply network slimming, a model compression technique, to explore the accuracy-efficiency tradeoffs, reporting latency measurements on a range of devices and software. Overall, our robust, cross-device implementation for keyword spotting realizes a new paradigm for serving neural network applications, and one of our slim models reduces latency by 66% with a minimal decrease in accuracy of 4% from 94% to 90%., Comment: 5 pages, 3 figures

In a stochastic process, noise often modifies the picture offered by the mean field dynamics. In particular, when there is an absorbing state, the noise erases a stable fixed point of the mean field equation from the stationary distribution, and turns it into a transient peak. We make a quantitative analysis of this effect for a simple genetic regulatory network with positive feedback, where the proteins become extinct in the presence of stochastic noise, contrary to the prediction of the deterministic rate equation that the protein number converges to a non-zero value. We show that the transient peak appears near the stable fixed point of the rate equation, and the extinction time diverges exponentially as the stochastic noise approaches zero. We also show how the baseline production from the inactive gene ameliorates the effect of the stochastic noise, and interpret the opposite effects of the noise and the baseline production in terms of the position shift of the unstable fixed point. The order of magnitude estimates using biological parameters suggest that for a real gene regulatory network, the stochastic noise is sufficiently small so that not only is the extinction time much larger than biologically relevant time-scales, but also the effect of the baseline production dominates over that of the stochastic noise, leading to the protection from the catastrophic rare event of protein extinction., Comment: 48 pages, 13 figures. Major revision (previously 22 pages, 4 figures). Time-scale separations are explained in detail. Biological implications are also discussed (v5: References were added)

This paper suggests an effective method for facial recognition using fuzzy theory and Shannon entropy. Combination of fuzzy theory and Shannon entropy eliminates the complication of other methods. Shannon entropy calculates the ratio of an element between faces, and fuzzy theory calculates the member ship of the entropy with 1. More details will be mentioned in Section 3. The learning performance is better than others as it is very simple, and only need two data per learning. By using factors that don't usually change during the life, the method will have a high accuracy., Comment: 5 pages