Search

Machine learning models are often criticized for their black-box nature, raising concerns about their applicability in critical decision-making scenarios. Consequently, there is a growing demand for interpretable models in such contexts. In this study, we introduce Model-based Deep Rule Forests (mobDRF), an interpretable representation learning algorithm designed to extract transparent models from data. By leveraging IF-THEN rules with multi-level logic expressions, mobDRF enhances the interpretability of existing models without compromising accuracy. We apply mobDRF to identify key risk factors for cognitive decline in an elderly population, demonstrating its effectiveness in subgroup analysis and local model optimization. Our method offers a promising solution for developing trustworthy and interpretable machine learning models, particularly valuable in fields like healthcare, where understanding differential effects across patient subgroups can lead to more personalized and effective treatments.

The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the field of Natural Language Processing (NLP). However, the speech processing community lacks a similar setup to explore the paradigm systematically. In this work, we establish the Speech processing Universal PERformance Benchmark (SUPERB) to study the effectiveness of the paradigm for speech. We propose a unified multi-tasking framework to address speech processing tasks in SUPERB using a frozen foundation model followed by task-specialized, lightweight prediction heads. Combining our results with community submissions, we verify that the foundation model paradigm is promising for speech, and our multi-tasking framework is simple yet effective, as the best-performing foundation model shows competitive generalizability across most SUPERB tasks. For reproducibility and extensibility, we have developed a long-term maintained platform that enables deterministic benchmarking, allows for result sharing via an online leaderboard, and promotes collaboration through a community-driven benchmark database to support new development cycles. Finally, we conduct a series of analyses to offer an in-depth understanding of SUPERB and speech foundation models, including information flows across tasks inside the models, the correctness of the weighted-sum benchmarking protocol and the statistical significance and robustness of the benchmark., Comment: The extended journal version for SUPERB and SUPERB-SG. Published in IEEE/ACM TASLP. The Arxiv version is preferred

Current automatic lyrics transcription (ALT) benchmarks focus exclusively on word content and ignore the finer nuances of written lyrics including formatting and punctuation, which leads to a potential misalignment with the creative products of musicians and songwriters as well as listeners' experiences. For example, line breaks are important in conveying information about rhythm, emotional emphasis, rhyme, and high-level structure. To address this issue, we introduce Jam-ALT, a new lyrics transcription benchmark based on the JamendoLyrics dataset. Our contribution is twofold. Firstly, a complete revision of the transcripts, geared specifically towards ALT evaluation by following a newly created annotation guide that unifies the music industry's guidelines, covering aspects such as punctuation, line breaks, spelling, background vocals, and non-word sounds. Secondly, a suite of evaluation metrics designed, unlike the traditional word error rate, to capture such phenomena. We hope that the proposed benchmark contributes to the ALT task, enabling more precise and reliable assessments of transcription systems and enhancing the user experience in lyrics applications such as subtitle renderings for live captioning or karaoke., Comment: 6 pages (3 pages main content); website: https://audioshake.github.io/jam-alt/; data: https://huggingface.co/datasets/audioshake/jam-alt; code: https://github.com/audioshake/alt-eval/

We study phrase structure induction from visually-grounded speech. The core idea is to first segment the speech waveform into sequences of word segments, and subsequently induce phrase structure using the inferred segment-level continuous representations. We present the Audio-Visual Neural Syntax Learner (AV-NSL) that learns phrase structure by listening to audio and looking at images, without ever being exposed to text. By training on paired images and spoken captions, AV-NSL exhibits the capability to infer meaningful phrase structures that are comparable to those derived by naturally-supervised text parsers, for both English and German. Our findings extend prior work in unsupervised language acquisition from speech and grounded grammar induction, and present one approach to bridge the gap between the two topics.

Conventional end-to-end Automatic Speech Recognition (ASR) models primarily focus on exact transcription tasks, lacking flexibility for nuanced user interactions. With the advent of Large Language Models (LLMs) in speech processing, more organic, text-prompt-based interactions have become possible. However, the mechanisms behind these models' speech understanding and "reasoning" capabilities remain underexplored. To study this question from the data perspective, we introduce instruction-following speech recognition, training a Listen-Attend-Spell model to understand and execute a diverse set of free-form text instructions. This enables a multitude of speech recognition tasks -- ranging from transcript manipulation to summarization -- without relying on predefined command sets. Remarkably, our model, trained from scratch on Librispeech, interprets and executes simple instructions without requiring LLMs or pre-trained speech modules. It also offers selective transcription options based on instructions like "transcribe first half and then turn off listening," providing an additional layer of privacy and safety compared to existing LLMs. Our findings highlight the significant potential of instruction-following training to advance speech foundation models.

The identification of distinct charge transport features, deriving from nontrivial bulk band and surface states, has been a challenging subject in the field of topological systems. In topological Dirac and Weyl semimetals, nontrivial conical bands with Fermi-arc surface states give rise to negative longitudinal magnetoresistance due to chiral anomaly effect and unusual thickness dependent quantum oscillation from Weyl-orbit effect, which were demonstrated recently in experiments. In this work, we report the experimental observations of large nonlinear and nonreciprocal transport effects for both longitudinal and transverse channels in an untwinned Weyl metal of SrRuO$_3$ thin film grown on a SrTiO$_{3}$ substrate. From rigorous measurements with bias current applied along various directions with respect to the crystalline principal axes, the magnitude of nonlinear Hall signals from the transverse channel exhibits a simple sin$\alpha$ dependence at low temperatures, where $\alpha$ is the angle between bias current direction and orthorhombic [001]$_{\rm o}$, reaching a maximum when current is along orthorhombic [1-10]$_{\rm o}$. On the contrary, the magnitude of nonlinear and nonreciprocal signals in the longitudinal channel attains a maximum for bias current along [001]$_{\rm o}$, and it vanishes for bias current along [1-10]$_{\rm o}$. The observed $\alpha$-dependent nonlinear and nonreciprocal signals in longitudinal and transverse channels reveal a magnetic Weyl phase with an effective Berry curvature dipole along [1-10]$_{\rm o}$ from surface states, accompanied by 1D chiral edge modes along [001]$_{\rm o}$., Comment: 27 pages, 6 figures

Nutrition information is crucial in precision nutrition and the food industry. The current food composition compilation paradigm relies on laborious and experience-dependent methods. However, these methods struggle to keep up with the dynamic consumer market, resulting in delayed and incomplete nutrition data. In addition, earlier machine learning methods overlook the information in food ingredient statements or ignore the features of food images. To this end, we propose a novel vision-language model, UMDFood-VL, using front-of-package labeling and product images to accurately estimate food composition profiles. In order to empower model training, we established UMDFood-90k, the most comprehensive multimodal food database to date, containing 89,533 samples, each labeled with image and text-based ingredient descriptions and 11 nutrient annotations. UMDFood-VL achieves the macro-AUCROC up to 0.921 for fat content estimation, which is significantly higher than existing baseline methods and satisfies the practical requirements of food composition compilation. Meanwhile, up to 82.2% of selected products' estimated error between chemical analysis results and model estimation results are less than 10%. This performance sheds light on generalization towards other food and nutrition-related data compilation and catalyzation for the evolution of generative AI-based technology in other food applications that require personalization., Comment: 13 pages, 9 figures

Past work on unsupervised parsing is constrained to written form. In this paper, we present the first study on unsupervised spoken constituency parsing given unlabeled spoken sentences and unpaired textual data. The goal is to determine the spoken sentences' hierarchical syntactic structure in the form of constituency parse trees, such that each node is a span of audio that corresponds to a constituent. We compare two approaches: (1) cascading an unsupervised automatic speech recognition (ASR) model and an unsupervised parser to obtain parse trees on ASR transcripts, and (2) direct training an unsupervised parser on continuous word-level speech representations. This is done by first splitting utterances into sequences of word-level segments, and aggregating self-supervised speech representations within segments to obtain segment embeddings. We find that separately training a parser on the unpaired text and directly applying it on ASR transcripts for inference produces better results for unsupervised parsing. Additionally, our results suggest that accurate segmentation alone may be sufficient to parse spoken sentences accurately. Finally, we show the direct approach may learn head-directionality correctly for both head-initial and head-final languages without any explicit inductive bias., Comment: Accepted to ICASSP 2023; updated compute resource acknowledgements

Self-supervised learning (SSL) for rich speech representations has achieved empirical success in low-resource Automatic Speech Recognition (ASR) and other speech processing tasks, which can mitigate the necessity of a large amount of transcribed speech and thus has driven a growing demand for on-device ASR and other speech processing. However, advanced speech SSL models have become increasingly large, which contradicts the limited on-device resources. This gap could be more severe in multilingual/multitask scenarios requiring simultaneously recognizing multiple languages or executing multiple speech processing tasks. Additionally, strongly overparameterized speech SSL models tend to suffer from overfitting when being finetuned on low-resource speech corpus. This work aims to enhance the practical usage of speech SSL models towards a win-win in both enhanced efficiency and alleviated overfitting via our proposed S$^3$-Router framework, which for the first time discovers that simply discarding no more than 10\% of model weights via only finetuning model connections of speech SSL models can achieve better accuracy over standard weight finetuning on downstream speech processing tasks. More importantly, S$^3$-Router can serve as an all-in-one technique to enable (1) a new finetuning scheme, (2) an efficient multilingual/multitask solution, (3) a state-of-the-art ASR pruning technique, and (4) a new tool to quantitatively analyze the learned speech representation. We believe S$^3$-Router has provided a new perspective for practical deployment of speech SSL models. Our codes are available at: https://github.com/GATECH-EIC/S3-Router., Comment: Accepted at NeurIPS 2022

Abt Associates evaluated the Bridges to Career Opportunities (BCO) program, developed by the Local Initiatives Support Corporation (LISC), to determine whether adults with low incomes and low skills who participate in BCO services are more likely to increase their employment and financial stability than do adults who participate in LISC's Financial Opportunity Center® (FOC) services alone. Overall, participants who were in the BCO programs were 19 percentage points more likely to have a "job improvement" than were participants in FOC-only programs (56 percent versus 37 percent). [This report was submitted to and supported by the Local Initiatives Support Corporation (LISC).]

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks of SSL learning in speech largely focus on the content information in speech, the most desirable speech representations should be able to disentangle unwanted variations, such as speaker variations, from the content. However, disentangling speakers is very challenging, because removing the speaker information could easily result in a loss of content as well, and the damage of the latter usually far outweighs the benefit of the former. In this paper, we propose a new SSL method that can achieve speaker disentanglement without severe loss of content. Our approach is adapted from the HuBERT framework, and incorporates disentangling mechanisms to regularize both the teacher labels and the learned representations. We evaluate the benefit of speaker disentanglement on a set of content-related downstream tasks, and observe a consistent and notable performance advantage of our speaker-disentangled representations.

We introduce the first unsupervised speech synthesis system based on a simple, yet effective recipe. The framework leverages recent work in unsupervised speech recognition as well as existing neural-based speech synthesis. Using only unlabeled speech audio and unlabeled text as well as a lexicon, our method enables speech synthesis without the need for a human-labeled corpus. Experiments demonstrate the unsupervised system can synthesize speech similar to a supervised counterpart in terms of naturalness and intelligibility measured by human evaluation., Comment: preprint, equal contribution from first two authors

Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks. However, the lack of a consistent evaluation methodology is limiting towards a holistic understanding of the efficacy of such models. SUPERB was a step towards introducing a common benchmark to evaluate pre-trained models across various speech tasks. In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabilities of pre-trained models by increasing task diversity and difficulty over SUPERB. We use a lightweight methodology to test the robustness of representations learned by pre-trained models under shifts in data domain and quality across different types of tasks. It entails freezing pre-trained model parameters, only using simple task-specific trainable heads. The goal is to be inclusive of all researchers, and encourage efficient use of computational resources. We also show that the task diversity of SUPERB-SG coupled with limited task supervision is an effective recipe for evaluating the generalizability of model representation., Comment: ACL 2022 main conference

In order to offer a customized script tool and inspire professional scriptwriters, we present VScript. It is a controllable pipeline that generates complete scripts, including dialogues and scene descriptions, as well as presents visually using video retrieval. With an interactive interface, our system allows users to select genres and input starting words that control the theme and development of the generated script. We adopt a hierarchical structure, which first generates the plot, then the script and its visual presentation. A novel approach is also introduced to plot-guided dialogue generation by treating it as an inverse dialogue summarization. The experiment results show that our approach outperforms the baselines on both automatic and human evaluations, especially in genre control.

The U.S. Department of Education's Office of Career, Technical, and Adult Education (OCTAE) funded Manhattan Strategy Group and Abt Associates to conduct the Advancing Innovation in Adult Education project. The goal is to inspire and promote the development and use of innovate approaches in adult education that can result in high quality services and positive outcomes for adult learners. The five adult education practices highlighted in this report provide integrated education and training program as well as bridge services that support adults' development of the knowledge, skills, and abilities they need to enroll and be successful in postsecondary education or occupational training, earn short-term credentials, and obtain employment. The programs, which are part of local school districts, have developed strong partnerships with a range of stakeholders, including community and technical colleges, universities, workforce development providers, and employers. The five practices and the programs in which they are being implemented include: (1) Bridges to Careers Expansion, Rochester Adult Literacy at Hawthorne, Rochester, Minnesota; (2) Career Pathways, South Bay Adult School, Redondo Beach, California; (3) Certified Clinical Medical Assistant (CCMA), Jennings County Education Center, North Vernon, Indiana; (4) Connections 101, Great Falls College and Career Readiness Center, Great Falls, Montana; and and (5) PluggedIn Virginia (PIVA) Boot Camp, Peninsula Regional Education Program, Newport News, Virginia. This compendium describes the project's criteria for the selection of innovative practices, and provides context for the practices that were selected and profiles each of the innovative practices.

Singing melody extraction is an important problem in the field of music information retrieval. Existing methods typically rely on frequency-domain representations to estimate the sung frequencies. However, this design does not lead to human-level performance in the perception of melody information for both tone (pitch-class) and octave. In this paper, we propose TONet, a plug-and-play model that improves both tone and octave perceptions by leveraging a novel input representation and a novel network architecture. First, we present an improved input representation, the Tone-CFP, that explicitly groups harmonics via a rearrangement of frequency-bins. Second, we introduce an encoder-decoder architecture that is designed to obtain a salience feature map, a tone feature map, and an octave feature map. Third, we propose a tone-octave fusion mechanism to improve the final salience feature map. Experiments are done to verify the capability of TONet with various baseline backbone models. Our results show that tone-octave fusion with Tone-CFP can significantly improve the singing voice extraction performance across various datasets -- with substantial gains in octave and tone accuracy., Comment: Preprint Version for ICASSP 2022, Singapore

A music piece is both comprehended hierarchically, from sonic events to melodies, and sequentially, in the form of repetition and variation. Music from different cultures establish different aesthetics by having different style conventions on these two aspects. We propose a framework that could be used to quantitatively compare music from different cultures by looking at these two aspects. The framework is based on an Music Information Dynamics model, a Variable Markov Oracle (VMO), and is extended with a variational representation learning of audio. A variational autoencoder (VAE) is trained to map audio fragments into a latent representation. The latent representation is fed into a VMO. The VMO then learns a clustering of the latent representation via a threshold that maximizes the information rate of the quantized latent representation sequence. This threshold effectively controls the sensibility of the predictive step to acoustic changes, which determines the framework's ability to track repetitions on longer time scales. This approach allows characterization of the overall information contents of a musical signal at each level of acoustic sensibility. Our findings under this framework show that sensibility to subtle acoustic changes is higher for East-Asian musical traditions, while the Western works exhibit longer motivic structures at higher thresholds of differences in the latent space. This suggests that a profile of information contents, analyzed as a function of the level of acoustic detail can serve as a possible cultural characteristic.

Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending the success of Transformers, which were originally developed for language processing, to the vision domain. A recent study showed that a similar methodology can also be applied to the audio domain. Specifically, the Audio Spectrogram Transformer (AST) achieves state-of-the-art results on various audio classification benchmarks. However, pure Transformer models tend to require more training data compared to CNNs, and the success of the AST relies on supervised pretraining that requires a large amount of labeled data and a complex training pipeline, thus limiting the practical usage of AST. This paper focuses on audio and speech classification, and aims to reduce the need for large amounts of labeled data for AST by leveraging self-supervised learning using unlabeled data. Specifically, we propose to pretrain the AST model with joint discriminative and generative masked spectrogram patch modeling (MSPM) using unlabeled audio from AudioSet and Librispeech. We evaluate our pretrained models on both audio and speech classification tasks including audio event classification, keyword spotting, emotion recognition, and speaker identification. The proposed self-supervised framework significantly boosts AST performance on all tasks, with an average improvement of 60.9%, leading to similar or even better results than a supervised pretrained AST. To the best of our knowledge, it is the first patch-based self-supervised learning framework in the audio and speech domain, and also the first self-supervised learning framework for AST., Comment: Accepted at AAAI2022. Code at https://github.com/YuanGongND/ssast

Are end-to-end text-to-speech (TTS) models over-parametrized? To what extent can these models be pruned, and what happens to their synthesis capabilities? This work serves as a starting point to explore pruning both spectrogram prediction networks and vocoders. We thoroughly investigate the tradeoffs between sparsity and its subsequent effects on synthetic speech. Additionally, we explored several aspects of TTS pruning: amount of finetuning data versus sparsity, TTS-Augmentation to utilize unspoken text, and combining knowledge distillation and pruning. Our findings suggest that not only are end-to-end TTS models highly prunable, but also, perhaps surprisingly, pruned TTS models can produce synthetic speech with equal or higher naturalness and intelligibility, with similar prosody. All of our experiments are conducted on publicly available models, and findings in this work are backed by large-scale subjective tests and objective measures. Code and 200 pruned models are made available to facilitate future research on efficiency in TTS.