An official website of the United States government
Purpose The “bubble noise” technique has recently been introduced as a method to identify the regions in time–frequency maps (i.e., spectrograms) of speech that are especially important for listeners in speech recognition. This technique identifies regions of “importance” that are specific to the speech stimulus and the listener, thus permitting these regions to be compared across different listener groups. For example, in cross-linguistic and second-language (L2) speech perception, this method identifies differences in regions of importance in accomplishing decisions of phoneme category membership. This research note describes the application of bubble noise to the study of language learning for 3 different language pairs: Hindi English bilinguals' perception of the /v/–/w/ contrast in American English, native English speakers' perception of the tense/lax contrast for Korean fricatives and affricates, and native English speakers' perception of Mandarin lexical tone. Conclusion We demonstrate that this technique provides insight on what information in the speech signal is important for native/first-language listeners compared to nonnative/L2 listeners. Furthermore, the method can be used to examine whether L2 speech perception training is effective in bringing the listener's attention to the important cues.
more »
« less
Large Scale Evaluation of Importance Maps in Automatic Speech Recognition
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
- Award ID(s):
- 1750383
- PAR ID:
- 10277024
- Date Published:
- Journal Name:
- Proceedings of Interspeech
- Page Range / eLocation ID:
- 1166 to 1170
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recurrent neural networks (RNNs), temporal convolutions, and neural differential equations (NDEs) are popular families of deep learning models for time-series data, each with unique strengths and tradeoffs in modeling power and computational efficiency. We introduce a simple sequence model inspired by control systems that generalizes these approaches while addressing their shortcomings. The Linear State-Space Layer (LSSL) maps a sequence u↦y by simply simulating a linear continuous-time state-space representation ˙x=Ax+Bu,y=Cx+Du. Theoretically, we show that LSSL models are closely related to the three aforementioned families of models and inherit their strengths. For example, they generalize convolutions to continuous-time, explain common RNN heuristics, and share features of NDEs such as time-scale adaptation. We then incorporate and generalize recent theory on continuous-time memorization to introduce a trainable subset of structured matrices A that endow LSSLs with long-range memory. Empirically, stacking LSSL layers into a simple deep neural network obtains state-of-the-art results across time series benchmarks for long dependencies in sequential image classification, real-world healthcare regression tasks, and speech. On a difficult speech classification task with length-16000 sequences, LSSL outperforms prior approaches by 24 accuracy points, and even outperforms baselines that use hand-crafted features on 100x shorter sequences.more » « less
-
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
-
null (Ed.)Advances in speech and language processing have enabled the creation of applications that could, in principle, accelerate the process of language documentation, as speech communities and linguists work on urgent language documentation and reclamationnprojects. However, such systems have yet to make a significant impact on language documentation, as resource requirements limit the broad applicability of these new techniques. We aim to exploit the framework of shared tasks to focus the technology research community on tasks which address key pain points in language documentation. Here we presentninitial steps in the implementation of these new shared tasks, through the creation of data sets drawn from endangered language repositories and baseline systems to perform segmentation and speaker labeling of these audio recordings—important enabling steps in the documentation process. This paper motivates these tasks with a use case, describes data set curation and baseline systems, and presents results on this data. We then highlight the challenges and ethical considerations in developing these speech processing tools and tasks to support endangered language documentation.more » « less
-
Children’s automatic speech recognition (ASR) is always difficult due to, in part, the data scarcity problem, especially for kindergarten-aged kids. When data are scarce, the model might overfit to the training data, and hence good starting points for training are essential. Recently, meta-learning was proposed to learn model initialization (MI) for ASR tasks of different languages. This method leads to good performance when the model is adapted to an unseen language. How-ever, MI is vulnerable to overfitting on training tasks (learner overfitting). It is also unknown whether MI generalizes to other low-resource tasks. In this paper, we validate the effectiveness of MI in children’s ASR and attempt to alleviate the problem of learner overfitting. To achieve model-agnostic meta-learning (MAML), we regard children’s speech at each age as a different task. In terms of learner overfitting, we propose a task-level augmentation method by simulating new ages using frequency warping techniques. Detailed experiments are conducted to show the impact of task augmentation on each age for kindergarten-aged speech. As a result, our approach achieves a relative word error rate (WER) improvement of 51% over the baseline system with no augmentation or initialization.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.21437/Interspeech.2020-2883
