skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Towards Large Scale Ecoacoustic Monitoring with Small Amounts of Labeled Data
Arctic boreal forests are warming at a rate 2–3 times faster than the global average. It is important to understand the effects of this warming on the activities of animals that migrate to these environments annually to reproduce. Acoustic sensors can monitor a wide area relatively cheaply, producing large amounts of data that need to be automatically analyzed. In such scenarios, only a small proportion of the recorded data can be labeled by hand, thus we explore two methods for utilizing labels more efficiently: self-supervised learning using wav2vec 2.0 and data valuation using k-nearest neighbors approximations to compute Shapley values. We confirm that data augmentation and global temporal pooling improve performance by more than 30%, demonstrate for the first time the utility of Shapley data valuation for audio classification, and find that our wav2vec 2.0 model trained from scratch does not improve performance.  more » « less
Award ID(s):
1839185
PAR ID:
10354645
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
Page Range / eLocation ID:
181 to 185
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, The Journal of the Acoustical Society of America)
    Anticipatory coarticulation is a highly informative cue to upcoming linguistic information: listeners can identify that the word is ben and not bed by hearing the vowel alone. The present study compares the relative performances of human listeners and a self-supervised pre-trained speech model (wav2vec 2.0) in the use of nasal coarticulation to classify vowels. Stimuli consisted of nasalized (from CVN words) and non-nasalized (from CVCs) American English vowels produced by 60 humans and generated in 36 TTS voices. wav2vec 2.0 performance is similar to human listener performance, in aggregate. Broken down by vowel type: both wav2vec 2.0 and listeners perform higher for non-nasalized vowels produced naturally by humans. However, wav2vec 2.0 shows higher correct classification performance for nasalized vowels, than for non-nasalized vowels, for TTS voices. Speaker-level patterns reveal that listeners' use of coarticulation is highly variable across talkers. wav2vec 2.0 also shows cross-talker variability in performance. Analyses also reveal differences in the use of multiple acoustic cues in nasalized vowel classifications across listeners and the wav2vec 2.0. Findings have implications for understanding how coarticulatory variation is used in speech perception. Results also can provide insight into how neural systems learn to attend to the unique acoustic features of coarticulation. 
    more » « less
  2. ; (, IEEE International Conference on Acoustics Speech and Signal Processing)
    Data Valuation in machine learning is concerned with quantifying the relative contribution of a training example to a model’s performance. Quantifying the importance of training examples is useful for identifying high and low quality data to curate training datasets and for address data quality issues. Shapley values have gained traction in machine learning for curating training data and identifying data quality issues. While computing the Shapley values of training examples is computationally prohibitive, approximation methods have been used successfully for classification models in computer vision tasks. We investigate data valuation for Automatic Speech Recognition models which perform a structured prediction task and propose a method for estimating Shapley values for these models. We show that a proxy model can be learned for the acoustic model component of an end-to-end ASR and used to estimate Shapley values for acoustic frames. We present a method for using the proxy acoustic model to estimate Shapley values for variable length utterances and demonstrate that the Shapley values provide a signal of example quality. 
    more » « less
  3. ; ; ; ; (, Advances in neural information processing systems)
    Data valuation, a growing field that aims at quantifying the usefulness of individual data sources for training machine learning (ML) models, faces notable yet often overlooked privacy challenges. This paper studies these challenges with a focus on KNN-Shapley, one of the most practical data valuation methods nowadays. We first emphasize the inherent privacy risks of KNN-Shapley, and demonstrate the significant technical challenges in adapting KNN-Shapley to accommodate differential privacy (DP). To overcome these challenges, we introduce TKNN-Shapley, a refined variant of KNN-Shapley that is privacy-friendly, allowing for straightforward modifications to incorporate DP guarantee (DP-TKNN-Shapley). We show that DP-TKNN-Shapley has several advantages and offers a superior privacy-utility tradeoff compared to naively privatized KNN-Shapley. Moreover, even non-private TKNN-Shapley matches KNN-Shapley's performance in discerning data quality. Overall, our findings suggest that TKNN-Shapley is a promising alternative to KNN-Shapley, particularly for real-world applications involving sensitive data. 
    more » « less
  4. ; ; ; ; ; ; (, Proceedings of the VLDB Endowment)
    The increasing demand for data-driven machine learning (ML) models has led to the emergence of model markets, where a broker collects personal data from data owners to produce high-usability ML models. To incentivize data owners to share their data, the broker needs to price data appropriately while protecting their privacy. For equitable data valuation , which is crucial in data pricing, Shapley value has become the most prevalent technique because it satisfies all four desirable properties in fairness: balance, symmetry, zero element, and additivity. For the right to be forgotten , which is stipulated by many data privacy protection laws to allow data owners to unlearn their data from trained models, the sharded structure in ML model training has become a de facto standard to reduce the cost of future unlearning by avoiding retraining the entire model from scratch. In this paper, we explore how the sharded structure for the right to be forgotten affects Shapley value for equitable data valuation in model markets. To adapt Shapley value for the sharded structure, we propose S-Shapley value, a sharded structure-based Shapley value, which satisfies four desirable properties for data valuation. Since we prove that computing S-Shapley value is #P-complete, two sampling-based methods are developed to approximate S-Shapley value. Furthermore, to efficiently update valuation results after data owners unlearn their data, we present two delta-based algorithms that estimate the change of data value instead of the data value itself. Experimental results demonstrate the efficiency and effectiveness of the proposed algorithms. 
    more » « less
  5. ; ; (, IEEE Signal Processing Society)
    Recently, speech foundation models have gained popularity due to their superiority in finetuning downstream ASR tasks. However, models finetuned on certain domains, such as LibriSpeech (adult read speech), behave poorly on other domains (child or noisy speech). One solution could be collecting as much labeled and diverse data as possible for joint finetuning on various domains. However, collecting target domain speech-text paired data and retraining the model is often costly and computationally expensive. In this paper, we introduce a simple yet effective method, speech only adaptation (SOA), based on speech foundation models (Wav2vec 2.0), which requires only speech input data from the target domain. Specifically, the Wav2vec 2.0 feature encoder is continually pretrained with the Wav2vec 2.0 loss on both the source and target domain data for domain adaptation, while the contextual encoder is frozen. Compared to a source domain finetuned model with the feature encoder being frozen during training, we find that replacing the frozen feature encoder with the adapted one provides significant WER improvements to the target domain while preserving the performance of the source domain. The effectiveness of SOA is examined on various low resource or domain mismatched ASR settings, including adult-child and clean-noisy speech. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email