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: Bubble Cooperative Networks for Identifying Important Speech Cues
Predicting the intelligibility of noisy recordings is difficult and most current algorithms treat all speech energy as equally important to intelligibility. Our previous work on human perception used a listening test paradigm and correlational analysis to show that some energy is more important to intelligibility than other energy. In this paper, we propose a system called the Bubble Cooperative Network (BCN), which aims to predict important areas of individual utterances directly from clean speech. Given such a prediction, noise is added to the utterance in unimportant regions and then presented to a recognizer. The BCN is trained with a loss that encourages it to add as much noise as possible while preserving recognition performance, encouraging it to identify important regions precisely and place the noise everywhere else. Empirical evaluation shows that the BCN can obscure 97.7% of the spectrogram with noise while maintaining recognition accuracy for a simple speech recognizer that compares a noisy test utterance with a clean reference utterance. The masks predicted by a single BCN on several utterances show patterns that are similar to analyses derived from human listening tests that analyze each utterance separately, while exhibiting better generalization and less context-dependence than previous approaches.  more » « less
Award ID(s):
1750383 1618061
PAR ID:
10087661
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Interspeech 2018
Page Range / eLocation ID:
1616 to 1620
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, Proceedings of Interspeech)
    null (Ed.)
    Human listeners use specific cues to recognize speech and recent experiments have shown that certain time-frequency regions of individual utterances are more important to their correct identification than others. A model that could identify such cues or regions from clean speech would facilitate speech recognition and speech enhancement by focusing on those important regions. Thus, in this paper we present a model that can predict the regions of individual utterances that are important to an automatic speech recognition (ASR) “listener” by learning to add as much noise as possible to these utterances while still permitting the ASR to correctly identify them. This work utilizes a continuous speech recognizer to recognize multi-word utterances and builds upon our previous work that performed the same process for an isolated word recognizer. Our experimental results indicate that our model can apply noise to obscure 90.5% of the spectrogram while leaving recognition performance nearly unchanged. 
    more » « less
  2. ; (, Proceedings of Interspeech)
    null (Ed.)
    This paper proposes a metric that we call the structured saliency benchmark (SSBM) to evaluate importance maps computed for automatic speech recognizers on individual utterances. These maps indicate time-frequency points of the utterance that are most important for correct recognition of a target word. Our evaluation technique is not only suitable for standard classification tasks, but is also appropriate for structured prediction tasks like sequence-to-sequence models. Additionally, we use this approach to perform a comparison of the importance maps created by our previously introduced technique using “bubble noise” to identify important points through correlation with a baseline approach based on smoothed speech energy and forced alignment. Our results show that the bubble analysis approach is better at identifying important speech regions than this baseline on 100 sentences from the AMI corpus. 
    more » « less
  3. (, Interspeech 2018)
    Building on previous work in subset selection of training data for text-to-speech (TTS), this work compares speaker-level and utterance-level selection of TTS training data, using acoustic features to guide selection. We find that speaker-based selection is more effective than utterance-based selection, regardless of whether selection is guided by a single feature or a combination of features. We use US English telephone data collected for automatic speech recognition to simulate the conditions of TTS training on low-resource languages. Our best voice achieves a human-evaluated WER of 29.0% on semantically-unpredictable sentences. This constitutes a significant improvement over our baseline voice trained on the same amount of randomly selected utterances, which performed at 42.4% WER. In addition to subjective voice evaluations with Amazon Mechanical Turk, we also explored objective voice evaluation using mel-cepstral distortion. We found that this measure correlates strongly with human evaluations of intelligibility, indicating that it may be a useful method to evaluate or pre-select voices in future work. 
    more » « less
  4. ; ; (, IEEE International Conference on Acoustics, Speech and Signal Processing)
    We introduce ImportantAug, a technique to augment training data for speech classification and recognition models by adding noise to unimportant regions of the speech and not to important regions. Importance is predicted for each utterance by a data augmentation agent that is trained to maximize the amount of noise it adds while minimizing its impact on recognition performance. The effectiveness of our method is illustrated on version two of the Google Speech Commands (GSC) dataset. On the standard GSC test set, it achieves a 23.3% relative error rate reduction compared to conventional noise augmentation which applies noise to speech without regard to where it might be most effective. It also provides a 25.4% error rate reduction compared to a baseline without data augmentation. Additionally, the proposed ImportantAug outperforms the conventional noise augmentation and the baseline on two test sets with additional noise added. 
    more » « less
  5. ; (, Guarant International)
    Radek Skarnitzl & Jan Volín (Ed.)
    Unfamiliar native and non-native accents can cause word recognition challenges, particularly in noisy environments, but few studies have incorporated quantitative pronunciation distance metrics to explain intelligibility differences across accents. Here, intelligibility was measured for 18 talkers -- two from each of three native, one bilingual, and five non- native accents -- in three listening conditions (quiet and two noise conditions). Two variations of the Levenshtein pronunciation distance metric, which quantifies phonemic differences from a reference accent, were assessed for their ability to predict intelligibility. An unweighted Levenshtein distance metric was the best intelligibility predictor; talker accent further predicted performance. Accuracy did not fall along a native - non-native divide. Thus, phonemic differences from the listener’s home accent primarily determine intelligibility, but other accent- specific pronunciation features, including suprasegmental characteristics, must be quantified to fully explain intelligibility across talkers and listening conditions. These results have implications for pedagogical practices and speech perception theories. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email